# CookiesForAI: every page

> CookiesForAI is a directory of agent skills, MCP servers and AI coding tools. Every page shows the facts AI answers get wrong, license, the agents it installs into, the install command and how recently it was maintained, with the date we checked them.

## Home

- [CookiesForAI: agent skills, MCP servers and AI coding tools](https://cookiesforai.app/): CookiesForAI is a directory of agent skills, MCP servers and AI coding tools. Every page shows the facts AI answers get wrong, license, the agents it installs into, the install command and how recently it was maintained, with the date we checked them.

## Sections and lists

- [91 agent skills with license, install command and checked date](https://cookiesforai.app/skills): 91 agent skills for Claude Code, Codex, Cursor, Gemini CLI and other coding agents, each with its license, install command and check date.
- [38 MCP servers for AI agents, with connect commands and free tiers](https://cookiesforai.app/mcp): 38 MCP servers: what each connects, how to add it, what it costs and when we checked.
- [20 AI coding agents and tools compared: free tier, license, skills and MCP](https://cookiesforai.app/tools): 20 AI coding agents, CLIs and editors with free tier, license, skills and MCP support, and check dates.
- [Guides: the best agent skills, MCP servers and coding tools for each job](https://cookiesforai.app/guides): Dated, sourced guides on agent skills, MCP servers and AI coding tools: which to pick for a job, alternatives, side-by-side comparisons, and how agents load skills.
- [Best agent skills and MCP servers for each job, compared](https://cookiesforai.app/best): Roundups that compare agent skills and MCP servers for one job on facts we checked: license, the agents each works in, whether it has a free tier and how recently its code changed.
- [Alternatives to AI coding tools and MCP servers, compared](https://cookiesforai.app/alternatives): Alternatives to AI coding tools and MCP servers, each compared on free tier, license, agent skills and MCP support, with the date we checked the facts.
- [Agent skills and AI coding tools compared side by side](https://cookiesforai.app/compare): Side-by-side comparisons of agent skills and AI coding tools, with the verdict first and every fact dated: license, free tier and the agents each works in.
- [Answers: is there an MCP server or agent skill for it?](https://cookiesforai.app/answers): Short, sourced answers to one question each about agent skills and MCP servers, such as whether a product has an official MCP server and what it costs.
- [Research: how AI assistants recommend tools, measured](https://cookiesforai.app/research): Our own dated tests of how ChatGPT, Gemini, Perplexity, Google AI Mode, Grok and Claude answer questions about software, agent skills and MCP servers, with the raw data.
- [What changed for getting found by AI: weekly notes](https://cookiesforai.app/changes): Weekly notes on changes to AI assistants and search engines that affect whether a small product gets found, with 3 to 7 items a week, each dated and linked to the maker's own source.
- [Free agent skills with a permissive license (MIT, Apache-2.0)](https://cookiesforai.app/skills/free-and-permissive): 76 of the 91 agent skills we list carry a permissive license (MIT, Apache-2.0, ISC or BSD), read from the skill's own LICENSE file or SKILL.md.
- [Agent skills that work the same in Codex, Cursor, Claude Code and more](https://cookiesforai.app/skills/cross-agent): 38 of the 91 agent skills we list install with the open skills CLI and, by our reading of their instructions, use no feature that only one agent has (no subagents, slash commands or one vendor's tools).
- [Agent skills updated in the last 30 days](https://cookiesforai.app/skills/recently-updated): 39 agent skills changed in the last 30 days, by the date of the last commit to the skill's own folder.
- [Agent skills for non-developers: documents, writing, marketing, video](https://cookiesforai.app/skills/for-non-developers): 21 agent skills for documents, writing, marketing, SEO, video and learning to use AI assistants.

## Agent skills by category

- [5 agent skills for infrastructure as code](https://cookiesforai.app/skills/category/infrastructure-as-code): 5 agent skills for infrastructure as code, each with license, install command and check date.
- [7 agent skills for cloud and deployment](https://cookiesforai.app/skills/category/cloud-and-deployment): 7 agent skills for cloud and deployment, each with license, install command and check date.
- [5 agent skills for databases](https://cookiesforai.app/skills/category/databases): 5 agent skills for databases, each with license, install command and check date.
- [6 agent skills for security](https://cookiesforai.app/skills/category/security): 6 agent skills for security, each with license, install command and check date.
- [7 agent skills for testing and debugging](https://cookiesforai.app/skills/category/testing-and-debugging): 7 agent skills for testing and debugging, each with license, install command and check date.
- [8 agent skills for code review and git](https://cookiesforai.app/skills/category/code-review-and-git): 8 agent skills for code review and git, each with license, install command and check date.
- [9 agent skills for frontend and design](https://cookiesforai.app/skills/category/frontend-and-design): 9 agent skills for frontend and design, each with license, install command and check date.
- [6 agent skills for coding and frameworks](https://cookiesforai.app/skills/category/coding-and-frameworks): 6 agent skills for coding and frameworks, each with license, install command and check date.
- [6 agent skills for video, images and media](https://cookiesforai.app/skills/category/video-and-media): 6 agent skills for video, images and media, each with license, install command and check date.
- [6 agent skills for documents and office files](https://cookiesforai.app/skills/category/documents-and-office): 6 agent skills for documents and office files, each with license, install command and check date.
- [4 agent skills for writing](https://cookiesforai.app/skills/category/writing): 4 agent skills for writing, each with license, install command and check date.
- [3 agent skills for marketing and seo](https://cookiesforai.app/skills/category/marketing-and-seo): 3 agent skills for marketing and seo, each with license, install command and check date.
- [8 agent skills for planning and agent workflow](https://cookiesforai.app/skills/category/planning-and-workflow): 8 agent skills for planning and agent workflow, each with license, install command and check date.
- [3 agent skills for building skills and mcp servers](https://cookiesforai.app/skills/category/building-skills-and-mcp): 3 agent skills for building skills and mcp servers, each with license, install command and check date.

## Agent skills by publisher

- [Anthropic agent skills: all 19, with install commands](https://cookiesforai.app/skills/anthropics): Anthropic publishes 19 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.
- [Cloudflare agent skills: all 2, with install commands](https://cookiesforai.app/skills/cloudflare): Cloudflare publishes 2 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.
- [Corey Haines agent skills: all 3, with install commands](https://cookiesforai.app/skills/coreyhaines31): Corey Haines publishes 3 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.
- [Expo agent skills: all 2, with install commands](https://cookiesforai.app/skills/expo): Expo publishes 2 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.
- [Sentry agent skills: all 4, with install commands](https://cookiesforai.app/skills/getsentry): Sentry publishes 4 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.
- [HashiCorp agent skills: all 4, with install commands](https://cookiesforai.app/skills/hashicorp): HashiCorp publishes 4 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.
- [Hugging Face agent skills: all 2, with install commands](https://cookiesforai.app/skills/huggingface): Hugging Face publishes 2 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.
- [Matt Pocock agent skills: all 2, with install commands](https://cookiesforai.app/skills/mattpocock): Matt Pocock publishes 2 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.
- [Microsoft agent skills: all 3, with install commands](https://cookiesforai.app/skills/microsoft): Microsoft publishes 3 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.
- [Jesse Vincent agent skills: all 15, with install commands](https://cookiesforai.app/skills/obra): Jesse Vincent publishes 15 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.
- [OpenAI agent skills: all 3, with install commands](https://cookiesforai.app/skills/openai): OpenAI publishes 3 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.
- [Supabase agent skills: all 2, with install commands](https://cookiesforai.app/skills/supabase): Supabase publishes 2 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.
- [Trail of Bits agent skills: all 4, with install commands](https://cookiesforai.app/skills/trailofbits): Trail of Bits publishes 4 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.
- [Vercel agent skills: all 10, with install commands](https://cookiesforai.app/skills/vercel-labs): Vercel publishes 10 agent skills listed on CookiesForAI, each with its license, install command and the date we checked it.

## Agent skills

- [academy-guide skill: Claude Academy courses for learning Claude](https://cookiesforai.app/skills/anthropics/academy-guide): Academy Guide is Anthropic's agent skill that ends Claude's answers about using Claude with one or two matching Claude Academy courses or tutorials, and only when the match is strong.
- [agent-browser skill: browser automation CLI for AI agents](https://cookiesforai.app/skills/vercel-labs/agent-browser): agent-browser is the agent skill for Vercel Labs' browser automation CLI: a native Rust tool that lets an agent open pages, read accessibility snapshots and click, fill and screenshot by element reference.
- [ai-seo skill: get cited in ChatGPT, Perplexity and AI Overviews](https://cookiesforai.app/skills/coreyhaines31/ai-seo): ai-seo is Corey Haines's agent skill for answer engine optimization: the agent audits whether AI assistants cite your site, then restructures content and site files so AI search can extract and cite it.
- [algorithmic-art skill: generative art in p5.js with seeds](https://cookiesforai.app/skills/anthropics/algorithmic-art): Algorithmic Art is Anthropic's open-source agent skill for generative art: the agent writes a short art philosophy, then builds an interactive p5.js piece with seeds and parameter sliders.
- [azure-deploy skill: run azd up and terraform apply with an agent](https://cookiesforai.app/skills/microsoft/azure-deploy): azure-deploy is Microsoft's agent skill for deploying an already prepared and validated app to Azure with azd, Bicep or Terraform, with error recovery, role checks and verified https endpoints at the end.
- [azure-diagnostics skill: troubleshoot Azure production issues](https://cookiesforai.app/skills/microsoft/azure-diagnostics): azure-diagnostics is Microsoft's agent skill for debugging Azure production problems with AppLens, Azure Monitor and resource health, with guides for App Service, Functions, Container Apps, AKS, VMs and messaging.
- [brainstorming skill: agree the design before your agent codes](https://cookiesforai.app/skills/obra/brainstorming): Brainstorming is an agent skill from Superpowers that makes your coding agent work out what you want and agree a design with you before it writes any code.
- [brand-guidelines skill: apply Anthropic's colors and fonts](https://cookiesforai.app/skills/anthropics/brand-guidelines): Brand Guidelines is Anthropic's open-source agent skill that holds Anthropic's own brand colors and fonts, so an agent can give a document, slide deck or web artifact the Anthropic look.
- [canvas-design skill: design posters and art as PNG or PDF](https://cookiesforai.app/skills/anthropics/canvas-design): Canvas Design is Anthropic's open-source agent skill for static visual work: the agent writes a design philosophy, then makes a poster or art piece as a finished PNG or PDF file.
- [claude-api skill: build apps with the Anthropic SDK and Claude](https://cookiesforai.app/skills/anthropics/claude-api): Claude API is Anthropic's open-source agent skill for code that calls Claude: current model IDs and prices, guides for seven SDK languages plus cURL, and guided migrations to newer models.
- [code-review skill: review pull requests the Sentry way](https://cookiesforai.app/skills/getsentry/code-review): code-review is Sentry's agent skill for reviewing pull requests by Sentry's engineering practices: runtime errors, performance, side effects, compatibility, security, design, tests and the tone of feedback.
- [database-migration skill: zero-downtime schema changes, rollbacks](https://cookiesforai.app/skills/wshobson/database-migration): database-migration is an agent skill from Seth Hobson's wshobson/agents marketplace for writing schema and data migrations in Sequelize, TypeORM and Prisma, with zero-downtime patterns and rollback strategies.
- [deploy-to-vercel skill: deploy your app and get a preview link](https://cookiesforai.app/skills/vercel-labs/deploy-to-vercel): Deploy to Vercel is Vercel's agent skill for getting a project live: the agent checks how your project is set up, picks a deploy method and returns a preview link unless you ask for production.
- [design-taste-frontend skill: landing pages without AI clichés](https://cookiesforai.app/skills/leonxlnx/design-taste-frontend): design-taste-frontend, the main skill in Leon Lin's Taste Skill repository, makes an AI agent read the brief, pick a design direction and build landing pages, portfolios and redesigns that avoid templated defaults.
- [diagnosing-superpowers skill: why an agent session went wrong](https://cookiesforai.app/skills/obra/diagnosing-superpowers): Diagnosing Superpowers is an agent skill from Superpowers that reads a session's transcripts when work went wrong and reports what happened, with every finding tied to a file and line.
- [differential-review skill: security review of a PR or diff](https://cookiesforai.app/skills/trailofbits/differential-review): differential-review is Trail of Bits' agent skill for security review of a pull request, commit or diff, using git history, blast radius counts and test coverage, and ending in a written markdown report.
- [discernment-nudge skill: questions to fact-check AI answers](https://cookiesforai.app/skills/anthropics/discernment-nudge): Discernment Nudge is Anthropic's agent skill that ends a substantive Claude answer with two or three specific follow-up questions, so you can check its facts, reasoning and assumptions.
- [dispatching-parallel-agents skill: fix independent bugs at once](https://cookiesforai.app/skills/obra/dispatching-parallel-agents): Dispatching Parallel Agents is an agent skill from Superpowers: when several problems are independent, your agent sends a focused subagent to each at once, then checks the results together.
- [doc-coauthoring skill: write specs, PRDs and design docs with AI](https://cookiesforai.app/skills/anthropics/doc-coauthoring): Doc Co-Authoring is Anthropic's agent skill that takes you and an AI agent through a document in three stages: gather context, draft section by section, then test it on a fresh reader.
- [docx skill: create, edit and redline Word files (Claude only)](https://cookiesforai.app/skills/anthropics/docx): DOCX is Anthropic's proprietary agent skill for creating, reading and editing Word files, including tracked changes, comments and tables of contents; its license limits it to Claude and Anthropic's own products.
- [eas-app-stores skill: ship Expo apps to App Store and Google Play](https://cookiesforai.app/skills/expo/eas-app-stores): eas-app-stores is the Expo team's agent skill for shipping mobile apps with EAS: build profiles, signing, version numbers, TestFlight and submissions to the App Store and Google Play.
- [executing-plans skill: carry out an implementation plan](https://cookiesforai.app/skills/obra/executing-plans): Executing Plans is an agent skill from Superpowers in which your agent works through a written plan itself, task by task with tests, then gets one fresh review of the whole branch.
- [expo-router skill: navigation, tabs and modals in Expo apps](https://cookiesforai.app/skills/expo/expo-router): expo-router is the Expo team's agent skill for navigation in Expo apps: file-based routes, native stacks and tabs, links with previews and context menus, modals, form sheets, headers and search bars.
- [finishing-a-development-branch skill: merge, open a PR or keep it](https://cookiesforai.app/skills/obra/finishing-a-development-branch): Finishing a Development Branch is an agent skill from Superpowers: when work is done, your agent runs the tests, offers to merge, open a pull request or keep the branch, then cleans up.
- [firebase-security-rules-auditor skill: red-team Firestore rules](https://cookiesforai.app/skills/firebase/firebase-security-rules-auditor): firebase-security-rules-auditor is the Firebase team's agent skill for auditing Firestore and Cloud Storage security rules for privilege escalation, update bypasses and missing limits, returning a 1 to 5 score in JSON.
- [firecrawl skill: web search, scraping and crawling for agents](https://cookiesforai.app/skills/firecrawl/firecrawl): firecrawl is Firecrawl's agent skill for live web work through its CLI: the agent searches the web, scrapes pages to clean markdown, maps and crawls sites, and interacts with pages that need clicks or logins.
- [frontend-design skill: UI that does not look AI-generated](https://cookiesforai.app/skills/anthropics/frontend-design): Frontend Design is Anthropic's open-source agent skill that steers an AI agent toward a look made for your product and away from the templated pages AI tends to produce.
- [gha-security-review skill: audit GitHub Actions workflows](https://cookiesforai.app/skills/getsentry/gha-security-review): gha-security-review is Sentry's agent skill for auditing GitHub Actions workflows for attacks an outsider can run, such as pwn requests, expression injection and credential theft, with a concrete exploit for each finding.
- [gh-address-comments skill: work through PR review comments](https://cookiesforai.app/skills/openai/gh-address-comments): gh-address-comments is OpenAI's agent skill for pull request review feedback: the agent fetches every comment and review thread on the open PR, numbers them, and fixes only the ones you pick.
- [gh-fix-ci skill: debug failing GitHub Actions checks on a PR](https://cookiesforai.app/skills/openai/gh-fix-ci): gh-fix-ci is OpenAI's agent skill for failing pull request checks: the agent uses the GitHub CLI to find failing GitHub Actions runs, pulls the logs, summarizes the failure and proposes a fix plan.
- [gws-gmail skill: send, read and manage Gmail from an AI agent](https://cookiesforai.app/skills/googleworkspace/gws-gmail): gws-gmail is the Gmail agent skill in Google Workspace's gws CLI repository: it lets an agent send, read, reply to, forward and triage Gmail messages through the gws command line.
- [grill-me skill: stress-test a plan with an agent interview](https://cookiesforai.app/skills/mattpocock/grill-me): grill-me is Matt Pocock's agent skill that turns your agent into a relentless interviewer, asking numbered rounds of questions about a plan or design until every decision is settled.
- [hf-cli skill: Hugging Face models, datasets and Hub jobs](https://cookiesforai.app/skills/huggingface/hf-cli): hf-cli is Hugging Face's agent skill for its hf command-line tool: it lets an agent download and upload models and datasets, manage repos, Spaces and buckets, read papers and run jobs on the Hub.
- [huggingface-llm-trainer skill: fine-tune LLMs on cloud GPUs](https://cookiesforai.app/skills/huggingface/huggingface-llm-trainer): huggingface-llm-trainer is Hugging Face's agent skill for fine-tuning language and vision models on its cloud GPUs, using TRL or Unsloth on Hugging Face Jobs, with no local GPU needed.
- [hyperframes skill: make videos from HTML with an AI agent](https://cookiesforai.app/skills/heygen-com/hyperframes): hyperframes is HeyGen's entry-point agent skill for HyperFrames, its open-source framework that renders HTML, CSS and animations into MP4 video; it captures your brief and routes to the right video workflow.
- [impeccable skill: design, critique and polish frontend UI](https://cookiesforai.app/skills/pbakaus/impeccable): Impeccable is Paul Bakaus's agent skill for frontend design: one skill with 24 commands such as audit, critique and polish, plus a launcher that runs deterministic checks for common AI design mistakes.
- [internal-comms skill: status reports, 3P updates, newsletters](https://cookiesforai.app/skills/anthropics/internal-comms): Internal Comms is Anthropic's open-source agent skill for writing inside a company: the agent drafts 3P updates, company newsletters, FAQs and other internal messages in set formats.
- [iterate-pr skill: fix CI failures and review comments on a PR](https://cookiesforai.app/skills/getsentry/iterate-pr): iterate-pr is Sentry's agent skill that keeps working on a GitHub pull request until CI passes and high and medium priority review comments are fixed, using bundled scripts and the gh CLI.
- [mcp-builder skill: build and test an MCP server for any API](https://cookiesforai.app/skills/anthropics/mcp-builder): MCP Builder is Anthropic's open-source agent skill for building MCP servers in TypeScript or Python, from API research and tool design to testing and a 10-question evaluation.
- [mutation-testing skill: run mewt or muton and analyze survivors](https://cookiesforai.app/skills/trailofbits/mutation-testing): mutation-testing is Trail of Bits' agent skill for configuring mutation testing campaigns with its mewt or muton tools, reading surviving mutants, telling equivalent mutants from real test gaps, and hunting bugs they expose.
- [neon-postgres skill: connect, migrate, branch and tune Neon](https://cookiesforai.app/skills/neondatabase/neon-postgres): neon-postgres is Neon's agent skill for working with Postgres on Neon: connection strings, pooled or direct connections, migrations, branching, built-in diagnostics, autoscaling, scale to zero and search.
- [obsidian-markdown skill: Obsidian wikilinks, callouts, properties](https://cookiesforai.app/skills/kepano/obsidian-markdown): obsidian-markdown is Steph Ango's agent skill for writing Obsidian Flavored Markdown: notes with properties, wikilinks, embeds, callouts and block references that render correctly in an Obsidian vault.
- [pdf skill: Anthropic's tool to merge, split, fill and read PDFs](https://cookiesforai.app/skills/anthropics/pdf): PDF is Anthropic's proprietary agent skill for reading, creating and editing PDF files, from pulling out tables to filling forms and OCR; its license limits it to Claude and Anthropic's own products.
- [pdf skill: OpenAI's tool to create, read and check PDF files](https://cookiesforai.app/skills/openai/pdf): pdf is OpenAI's open-source agent skill for making and reviewing PDF files: the agent builds them with Python libraries, renders each page to an image and checks the layout before delivering.
- [playwright-cli skill: browser automation and web testing](https://cookiesforai.app/skills/microsoft/playwright-cli): playwright-cli is Microsoft's agent skill for driving a real browser from the terminal: open pages, click and fill by element reference, take snapshots and screenshots, mock requests and generate Playwright tests.
- [supabase-postgres-best-practices skill: indexes, RLS, schemas](https://cookiesforai.app/skills/supabase/supabase-postgres-best-practices): Postgres Best Practices is Supabase's agent skill of Postgres rules for any Postgres database, ranked by impact: indexes, connection pooling, row level security and schema design.
- [pptx skill: build and edit PowerPoint decks (Claude only)](https://cookiesforai.app/skills/anthropics/pptx): PPTX is Anthropic's proprietary agent skill for building PowerPoint decks from scratch or from your template and checking every slide for overflow; its license limits it to Claude and Anthropic's products.
- [prisma-upgrade-v7 skill: migrate Prisma ORM 6 to 7 with an agent](https://cookiesforai.app/skills/prisma/prisma-upgrade-v7): prisma-upgrade-v7 is Prisma's agent skill for upgrading a project from Prisma ORM 6 to 7, covering every breaking change: the new generator, driver adapters, prisma.config.ts, ESM and removed features.
- [programmatic-seo skill: build SEO pages at scale from templates](https://cookiesforai.app/skills/coreyhaines31/programmatic-seo): programmatic-seo is Corey Haines's agent skill for building SEO pages at scale from templates and data, such as location, comparison or integration pages, without tripping search engine spam policies.
- [vercel-react-best-practices skill: faster React and Next.js](https://cookiesforai.app/skills/vercel-labs/vercel-react-best-practices): React Best Practices is Vercel Engineering's agent skill of 70 performance rules for React and Next.js, ranked by impact, which the agent applies when it writes or reviews code.
- [vercel-composition-patterns skill: replace React boolean props](https://cookiesforai.app/skills/vercel-labs/vercel-composition-patterns): React Composition Patterns is Vercel's agent skill for React component APIs: compound components, lifted state and explicit variants instead of a growing list of boolean props.
- [vercel-react-native-skills: faster React Native apps](https://cookiesforai.app/skills/vercel-labs/vercel-react-native-skills): React Native is Vercel's agent skill of React Native and Expo rules, ranked by impact: list performance, animations, native navigation and UI patterns for faster mobile apps.
- [vercel-react-view-transitions skill: animate route changes](https://cookiesforai.app/skills/vercel-labs/vercel-react-view-transitions): React View Transitions is Vercel's agent skill for animating route changes, shared elements and list reorders with React's ViewTransition component, in Next.js and other React apps.
- [receiving-code-review skill: check review feedback before acting](https://cookiesforai.app/skills/obra/receiving-code-review): Receiving Code Review is an agent skill from Superpowers: your agent checks review feedback against the code before acting, pushes back with reasons when it is wrong, and skips the flattery.
- [refactor-module skill: split Terraform code into modules](https://cookiesforai.app/skills/hashicorp/refactor-module): refactor-module is HashiCorp's agent skill for turning a monolithic Terraform configuration into reusable modules, with typed interfaces, documentation, tests and a state migration that recreates no resources.
- [remotion-best-practices skill: videos in React with an AI agent](https://cookiesforai.app/skills/remotion-dev/remotion-best-practices): remotion-best-practices is Remotion's own agent skill and the entry point to its other video skills: it routes an agent to the right guide for creating, previewing, captioning and rendering Remotion videos in React.
- [requesting-code-review skill: AI code review before you merge](https://cookiesforai.app/skills/obra/requesting-code-review): Requesting Code Review is an agent skill from Superpowers: your agent sends its changes to a separate reviewer subagent that checks them against the plan and grades each issue by severity.
- [security-review skill: find exploitable vulnerabilities in code](https://cookiesforai.app/skills/getsentry/security-review): security-review is Sentry's agent skill for reviewing code for exploitable vulnerabilities, such as injection, XSS, broken access control and weak crypto, reporting only findings it has confirmed with high confidence.
- [semgrep-rule-creator skill: write and test custom Semgrep rules](https://cookiesforai.app/skills/trailofbits/semgrep-rule-creator): semgrep-rule-creator is Trail of Bits' agent skill for writing custom Semgrep rules that detect vulnerabilities and bug patterns, test-first, with taint mode preferred and every test required to pass.
- [seo-audit skill: find technical and on-page SEO issues](https://cookiesforai.app/skills/coreyhaines31/seo-audit): seo-audit is Corey Haines's agent skill for diagnosing why a site is not ranking: the agent checks crawling, indexing, speed, on-page elements and content quality, then writes a prioritized fix list.
- [shadcn skill: add, compose and fix shadcn/ui components](https://cookiesforai.app/skills/shadcn-ui/shadcn): shadcn is the shadcn/ui project's own agent skill: it reads your components.json, then guides the agent to find, install, compose and style shadcn/ui components with the shadcn CLI and the project's rules.
- [skill-creator skill: create, test and improve agent skills](https://cookiesforai.app/skills/anthropics/skill-creator): Skill Creator is Anthropic's open-source agent skill for making skills: the agent drafts a SKILL.md with you, tests it with and without the skill, and tunes its description so it triggers.
- [slack-gif-creator skill: animated emoji and GIFs for Slack](https://cookiesforai.app/skills/anthropics/slack-gif-creator): Slack GIF Creator is Anthropic's open-source agent skill for animated GIFs sized for Slack: the agent draws the frames in Python, adds motion and checks the file meets Slack's limits.
- [stripe-best-practices skill: build Stripe payments correctly](https://cookiesforai.app/skills/stripe/stripe-best-practices): stripe-best-practices is Stripe's own agent skill for integration decisions: it steers the agent to the right Stripe API for payments, subscriptions, Connect, tax and security, using current API and SDK versions.
- [subagent-driven-development skill: a fresh subagent per task](https://cookiesforai.app/skills/obra/subagent-driven-development): Subagent-Driven Development is an agent skill from Superpowers: your agent carries out a plan by giving each task to a fresh subagent, reviewing every task, then reviewing the whole branch.
- [supabase skill: auth, RLS, Edge Functions and Postgres](https://cookiesforai.app/skills/supabase/supabase): Supabase is Supabase's own agent skill for any Supabase task, with a security checklist for auth and row level security and a rule to check the current docs first.
- [supply-chain-risk-auditor skill: audit npm, PyPI and Go packages](https://cookiesforai.app/skills/trailofbits/supply-chain-risk-auditor): supply-chain-risk-auditor is Trail of Bits' agent skill for auditing a project's npm, PyPI and Go dependencies for known advisories, abandoned upstreams, publisher concentration and install scripts, measured by bundled scripts.
- [systematic-debugging skill: find the root cause before fixing](https://cookiesforai.app/skills/obra/systematic-debugging): Systematic Debugging is an agent skill from Superpowers that makes your agent find the root cause of a bug or failing test before it proposes any fix, instead of guessing.
- [tdd skill: test-driven development with an AI coding agent](https://cookiesforai.app/skills/mattpocock/tdd): tdd is Matt Pocock's agent skill for test-driven development: the agent agrees which public interfaces to test with you, then works one failing test and one minimal fix at a time.
- [terraform-policy skill: write, test and convert Sentinel policies](https://cookiesforai.app/skills/hashicorp/terraform-policy): terraform-policy is HashiCorp's agent skill for writing Terraform Policy files (.policy.hcl), testing them with .policytest.hcl, and converting Sentinel policies to the new format.
- [terraform-skill: write, test and review Terraform and OpenTofu](https://cookiesforai.app/skills/antonbabenko/terraform-skill): terraform-skill is Anton Babenko's agent skill for writing, testing and reviewing Terraform and OpenTofu, which names the risk before it writes code and never recommends a production apply without a reviewed plan.
- [terraform-style-guide skill: write and review Terraform HCL](https://cookiesforai.app/skills/hashicorp/terraform-style-guide): terraform-style-guide is HashiCorp's agent skill for writing and reviewing Terraform HCL to the official style conventions: file layout, formatting, naming, typed variables, version pinning and a review checklist.
- [terraform-test skill: write and run Terraform tests with an agent](https://cookiesforai.app/skills/hashicorp/terraform-test): terraform-test is HashiCorp's agent skill for writing and running Terraform's built-in tests: .tftest.hcl files with run blocks, assertions, expected failures, mock providers and CI pipelines.
- [test-driven-development skill: AI agents write tests first](https://cookiesforai.app/skills/obra/test-driven-development): Test-Driven Development is an agent skill from Superpowers: your agent writes a failing test first, watches it fail, then writes only the code needed to make it pass.
- [theme-factory skill: color and font themes for slides and docs](https://cookiesforai.app/skills/anthropics/theme-factory): Theme Factory is Anthropic's open-source agent skill with 10 ready color and font themes, plus custom ones on request, that an agent applies to slides, documents and web pages.
- [ui-ux-pro-max skill: design systems and UX rules for agents](https://cookiesforai.app/skills/nextlevelbuilder/ui-ux-pro-max): ui-ux-pro-max is an agent skill from Next Level Builder that gives an agent a searchable local library of UI styles, color palettes, font pairings and UX rules, and generates a design system per project.
- [using-git-worktrees skill: an isolated worktree for agent work](https://cookiesforai.app/skills/obra/using-git-worktrees): Using Git Worktrees is an agent skill from Superpowers: before feature work, your agent makes sure it is in an isolated git worktree, sets up the project and checks that the tests pass.
- [using-superpowers skill: make your agent check and use its skills](https://cookiesforai.app/skills/obra/using-superpowers): Using Superpowers is the agent skill that makes your agent check for a relevant Superpowers skill before it responds, announce it, and follow it whenever one applies.
- [vercel-cli-with-tokens skill: deploy with a Vercel access token](https://cookiesforai.app/skills/vercel-labs/vercel-cli-with-tokens): Vercel CLI with Tokens is Vercel's agent skill for running the Vercel CLI with an access token instead of vercel login: deploys, environment variables, logs and domains.
- [vercel-optimize skill: lower your Vercel bill, speed up routes](https://cookiesforai.app/skills/vercel-labs/vercel-optimize): Vercel Optimize is Vercel's agent skill that audits a deployed project from its production metrics and returns ranked, verified fixes to cut cost and speed up slow routes.
- [verification-before-completion skill: test before claiming done](https://cookiesforai.app/skills/obra/verification-before-completion): Verification Before Completion is an agent skill from Superpowers: your agent runs the command that proves a claim and reads the output before it says work is done, fixed or passing.
- [watch skill: let your AI agent watch YouTube and other videos](https://cookiesforai.app/skills/bradautomates/watch): Watch is an open-source agent skill that turns a video link or file into frames and a transcript, or hands it to Google's Gemini, so your agent can answer questions about it.
- [web-artifacts-builder skill: React apps as Claude.ai artifacts](https://cookiesforai.app/skills/anthropics/web-artifacts-builder): Web Artifacts Builder is Anthropic's agent skill for complex Claude.ai artifacts: the agent sets up a React, Tailwind and shadcn/ui project, then bundles it into one HTML file.
- [web-design-guidelines skill: review UI code for accessibility](https://cookiesforai.app/skills/vercel-labs/web-design-guidelines): Web Design Guidelines is Vercel's agent skill for UI review: the agent checks your files against Vercel's Web Interface Guidelines and lists each issue by file and line.
- [webapp-testing skill: test local web apps with Playwright](https://cookiesforai.app/skills/anthropics/webapp-testing): Webapp Testing is Anthropic's open-source agent skill for testing local web apps: the agent writes Python Playwright scripts that click through your app, take screenshots and read console logs.
- [workers-best-practices skill: write and review Cloudflare Workers](https://cookiesforai.app/skills/cloudflare/workers-best-practices): workers-best-practices is Cloudflare's agent skill for writing, reviewing and configuring production Cloudflare Workers, built around a table of anti-patterns to flag and current docs over memorized APIs.
- [wrangler skill: deploy Cloudflare Workers with an AI agent](https://cookiesforai.app/skills/cloudflare/wrangler): wrangler is Cloudflare's agent skill for running and troubleshooting the Wrangler CLI: configuring Worker projects, local development, Previews, secrets, deployments, rollbacks and Cloudflare resources such as KV, R2 and D1.
- [writing-guidelines skill: review docs for style, tone, AI tells](https://cookiesforai.app/skills/vercel-labs/writing-guidelines): Writing Guidelines is Vercel's agent skill for docs review: the agent checks your pages against Vercel's Writing Guidelines and lists each style or tone issue by file and line.
- [writing-plans skill: turn a spec into an implementation plan](https://cookiesforai.app/skills/obra/writing-plans): Writing Plans is an agent skill from Superpowers: your agent turns a spec into a step-by-step implementation plan with exact files, signatures and tests, before touching code.
- [writing-skills: create and test agent skills test-first](https://cookiesforai.app/skills/obra/writing-skills): Writing Skills is an agent skill from Superpowers: your agent writes new skills test-first, running pressure scenarios with subagents before and after the skill exists.
- [xlsx skill: Excel files with working formulas (Claude only)](https://cookiesforai.app/skills/anthropics/xlsx): XLSX is Anthropic's proprietary agent skill for creating, editing and cleaning spreadsheets with live formulas checked for errors; its license limits it to Claude and Anthropic's own products.

## MCP servers by category

- [7 MCP servers for web search and scraping](https://cookiesforai.app/mcp/category/web-search-and-scraping): 7 MCP servers for web search and scraping, with connect commands, free tiers and check dates.
- [4 MCP servers for browser automation and testing](https://cookiesforai.app/mcp/category/browser-automation): 4 MCP servers for browser automation and testing, with connect commands, free tiers and check dates.
- [3 MCP servers for docs and code context](https://cookiesforai.app/mcp/category/docs-and-code-context): 3 MCP servers for docs and code context, with connect commands, free tiers and check dates.
- [6 MCP servers for databases](https://cookiesforai.app/mcp/category/databases): 6 MCP servers for databases, with connect commands, free tiers and check dates.
- [5 MCP servers for notes, docs and team tools](https://cookiesforai.app/mcp/category/productivity): 5 MCP servers for notes, docs and team tools, with connect commands, free tiers and check dates.
- [6 MCP servers for cloud and devops](https://cookiesforai.app/mcp/category/cloud-and-devops): 6 MCP servers for cloud and devops, with connect commands, free tiers and check dates.
- [3 MCP servers for game engines and 3d](https://cookiesforai.app/mcp/category/game-and-3d): 3 MCP servers for game engines and 3d, with connect commands, free tiers and check dates.

## MCP servers

- [Apify MCP server: ready-made web scrapers for AI agents](https://cookiesforai.app/mcp/apify): The Apify MCP server gives AI agents thousands of ready-made scrapers and automation tools from Apify Store, such as Google Maps, Instagram and search result scrapers, which the agent can find and run on demand.
- [Atlassian MCP server: Jira, Confluence and Bitbucket for AI agents](https://cookiesforai.app/mcp/atlassian): The Atlassian MCP server gives AI agents access to Jira, Confluence, Jira Service Management, Bitbucket, Compass and Loom on Atlassian Cloud: search, summarize, and create or update issues and pages.
- [AWS MCP servers: AWS APIs, docs and infrastructure for AI agents](https://cookiesforai.app/mcp/aws): The AWS MCP servers give AI agents access to AWS: a managed AWS MCP Server for API calls and docs, plus more than 50 open-source servers for services like CDK, EKS, Lambda and DynamoDB.
- [Blender MCP server: 3D modeling and scene control for AI agents](https://cookiesforai.app/mcp/blender): The Blender MCP server, MCP for Blender, gives AI agents control of a running Blender scene: create, change and delete objects, apply materials, inspect the scene and run Python in Blender.
- [Brave Search MCP server: web, news, image and local search for AI agents](https://cookiesforai.app/mcp/brave-search): The Brave Search MCP server gives AI agents Brave's independent search index: web, news, image, video, local and place search, plus pre-extracted page text for grounding and AI summaries.
- [Browser Use MCP server: an autonomous browser agent for AI tools](https://cookiesforai.app/mcp/browser-use): The Browser Use MCP server gives AI agents the Browser Use browsing agent, either as a local open-source server with direct browser tools or as a cloud server that runs whole web tasks.
- [Browserbase MCP server: cloud browsers for AI agents](https://cookiesforai.app/mcp/browserbase): The Browserbase MCP server gives AI agents a browser that runs in Browserbase's cloud, controlled with plain-language commands through Stagehand: navigate, act on the page, observe elements and extract data.
- [Chrome DevTools MCP server: debug and profile Chrome with AI agents](https://cookiesforai.app/mcp/chrome-devtools): The Chrome DevTools MCP server gives AI agents control of a live Chrome browser with DevTools access: performance traces, network requests, console errors, Lighthouse audits, memory snapshots and page automation.
- [Cloudflare MCP server: Workers, logs, DNS and docs for AI agents](https://cookiesforai.app/mcp/cloudflare): The Cloudflare MCP servers give AI agents access to a Cloudflare account through hosted endpoints: read Workers logs and builds, manage bindings, check DNS analytics, search the docs and render web pages.
- [Context7 MCP server: up-to-date library docs for AI coding agents](https://cookiesforai.app/mcp/context7): The Context7 MCP server gives AI coding agents current, version-specific documentation and code examples for thousands of libraries, fetched into the prompt so the agent stops guessing at outdated APIs.
- [DBHub MCP server: Postgres, MySQL, SQL Server and SQLite for AI agents](https://cookiesforai.app/mcp/dbhub): DBHub is an open-source MCP server by Bytebase that gives AI agents SQL access to PostgreSQL, MySQL, MariaDB, SQL Server, Oracle and SQLite through one server with two default tools.
- [DeepWiki MCP server: ask questions about any public GitHub repo](https://cookiesforai.app/mcp/deepwiki): The DeepWiki MCP server gives AI agents DeepWiki's generated documentation for public GitHub repositories, plus an ask tool that answers questions about a repo's code, free and without sign-in.
- [Exa MCP server: web search and page fetching for AI agents](https://cookiesforai.app/mcp/exa): The Exa MCP server gives AI agents web search and page reading through Exa's search engine, plus optional advanced filters and Exa Agent runs for multi-step research with structured output.
- [Figma MCP server: design context and canvas edits for AI agents](https://cookiesforai.app/mcp/figma): The Figma MCP server gives AI agents design context from Figma files, such as layout, variables and components, to generate code from frames, and can write native content back to the canvas.
- [Firecrawl MCP server: web scraping, crawling and search for AI agents](https://cookiesforai.app/mcp/firecrawl): The Firecrawl MCP server gives AI agents live web access through Firecrawl: search the web, scrape a URL into Markdown or JSON, map and crawl whole sites, and click through pages.
- [GitHub MCP server: repos, issues, pull requests and Actions for AI agents](https://cookiesforai.app/mcp/github): The GitHub MCP server gives AI agents access to GitHub through your account: read code and commits, create and review issues and pull requests, check Actions runs and read security alerts.
- [GitLab MCP server: merge requests, issues and pipelines for AI agents](https://cookiesforai.app/mcp/gitlab): The GitLab MCP server gives AI agents access to a GitLab instance through your account: read and create issues and merge requests, commit files, review diffs, and check CI pipelines and jobs.
- [Godot MCP server: run, debug and edit Godot projects with AI agents](https://cookiesforai.app/mcp/godot): The Godot MCP server gives AI agents control of the Godot engine: launch the editor, run projects in debug mode, capture errors and console output, and create scenes and nodes.
- [Jina AI MCP server: read URLs, web and arXiv search for AI agents](https://cookiesforai.app/mcp/jina): The Jina AI MCP server gives AI agents Jina's Reader, Search, Embeddings and Reranker APIs: read any web page or PDF as Markdown, search the web, arXiv and SSRN, and rerank results.
- [Kubernetes MCP server: pods, resources and Helm for AI agents](https://cookiesforai.app/mcp/kubernetes): The Kubernetes MCP server gives AI agents direct access to Kubernetes and OpenShift clusters: list and edit any resource, read pod logs, exec into pods, view events and install Helm charts.
- [Linear MCP server: issues, projects and comments for AI agents](https://cookiesforai.app/mcp/linear): The Linear MCP server gives AI agents access to your Linear workspace through Linear's hosted endpoint: find, create and update issues, projects and comments, with a read-only URL when you only need lookups.
- [Microsoft Learn MCP server: official Microsoft and Azure docs for AI agents](https://cookiesforai.app/mcp/microsoft-learn): The Microsoft Learn MCP server gives AI agents search and full-page reading over Microsoft's official documentation, plus official code samples for Azure, .NET and other Microsoft products, free and keyless.
- [MongoDB MCP server: query collections and manage Atlas with AI agents](https://cookiesforai.app/mcp/mongodb): The MongoDB MCP server gives AI agents access to MongoDB databases and MongoDB Atlas: run find and aggregate queries, inspect schemas and indexes, and create or manage Atlas clusters and users.
- [Neon MCP server: serverless Postgres projects and branches for AI agents](https://cookiesforai.app/mcp/neon): The Neon MCP server gives AI agents control of Neon serverless Postgres: create projects and branches, run SQL, inspect schemas, find slow queries and run migrations on a branch before applying them.
- [Notion MCP server: search, read and edit Notion pages with AI agents](https://cookiesforai.app/mcp/notion): The Notion MCP server gives AI agents access to your Notion workspace through Notion's hosted server: search pages and databases, read them as Markdown, and create or update pages, databases and views.
- [Obsidian MCP server: read, search and edit your vault with AI agents](https://cookiesforai.app/mcp/obsidian): The Obsidian MCP server gives AI agents access to your Obsidian vault through the Local REST API plugin: list and read notes, search across files, append or patch content and delete files.
- [Perplexity MCP server: web search, answers and deep research for AI agents](https://cookiesforai.app/mcp/perplexity): The Perplexity MCP server gives AI agents Perplexity's web search, quick answers with citations, step-by-step reasoning and long research runs, all billed to a Perplexity API account.
- [Playwright MCP server: browser automation for AI agents](https://cookiesforai.app/mcp/playwright): The Playwright MCP server gives AI agents a real browser driven by Microsoft's Playwright: navigate, click, type and fill forms using the page's accessibility tree instead of screenshots.
- [Postgres MCP Pro: PostgreSQL queries and index tuning for AI agents](https://cookiesforai.app/mcp/postgres-mcp-pro): Postgres MCP Pro is an open-source MCP server that gives AI agents access to a PostgreSQL database, with schema browsing, safe SQL execution, EXPLAIN plans, index recommendations and database health checks.
- [Redis MCP server: read, write and vector-search Redis data with AI agents](https://cookiesforai.app/mcp/redis): The Redis MCP server gives AI agents natural-language access to a Redis database: strings, hashes, lists, sets, sorted sets, streams, JSON documents, pub/sub and vector search indexes.
- [Sentry MCP server: errors, traces and issue triage for AI agents](https://cookiesforai.app/mcp/sentry): The Sentry MCP server gives AI coding agents access to your Sentry account: search errors and events, read issue details and stack traces, look at performance data and triage issues while fixing code.
- [Slack MCP server: search, read and send Slack messages for AI agents](https://cookiesforai.app/mcp/slack): The Slack MCP server gives AI agents access to a Slack workspace through Slack's hosted endpoint: search messages and files, read channels and threads, send messages, and edit canvases and lists.
- [Stripe MCP server: payments, billing and Stripe API for AI agents](https://cookiesforai.app/mcp/stripe): The Stripe MCP server gives AI agents access to a Stripe account through Stripe's hosted endpoint: read and write most of the Stripe API, search the docs and plan a Stripe integration.
- [Supabase MCP server: manage Postgres and migrations with AI agents](https://cookiesforai.app/mcp/supabase): The Supabase MCP server gives AI agents access to your Supabase projects: list tables, run SQL, apply migrations, read logs and advisors, deploy edge functions, manage branches and search Supabase docs.
- [Tavily MCP server: real-time web search and extraction for AI agents](https://cookiesforai.app/mcp/tavily): The Tavily MCP server gives AI agents real-time web search through the Tavily API, plus tools that extract page content, map a site's structure and crawl it.
- [Terraform MCP server: registry docs and HCP Terraform for AI agents](https://cookiesforai.app/mcp/terraform): The Terraform MCP server gives AI agents current Terraform Registry data on providers, modules and policies, and with a token manages HCP Terraform and Terraform Enterprise workspaces, runs and plans.
- [Unity MCP server: control the Unity Editor with AI agents](https://cookiesforai.app/mcp/unity): The Unity MCP server, MCP for Unity, gives AI agents control of the Unity Editor: create scenes and GameObjects, edit C# scripts, manage assets, run tests, profile and build.
- [Vercel MCP server: deployments, logs and projects for AI agents](https://cookiesforai.app/mcp/vercel): The Vercel MCP server gives AI agents access to your Vercel account through Vercel's hosted endpoint: search the docs, inspect projects and deployments, read runtime logs and errors, and query Web Analytics.

## AI coding tools

- [Aider: open-source AI pair programmer, free tier and alternatives](https://cookiesforai.app/tools/aider): Aider is an open source terminal coding agent from the Aider-AI project that edits files in your git repo with the model of your choice and commits each change automatically.
- [Amp: coding agent for the terminal and cloud, free tier and alternatives](https://cookiesforai.app/tools/amp): Amp is a coding agent by Amp Frontier Corporation, spun out of Sourcegraph, that runs in a terminal CLI, a web app and macOS and iOS apps, with per-thread cloud machines.
- [Claude Code: terminal coding agent, free tier and alternatives](https://cookiesforai.app/tools/claude-code): Claude Code is a terminal coding agent by Anthropic that reads a codebase, edits files and runs commands, and also works in VS Code, JetBrains, a desktop app and the web.
- [Cline: open-source coding agent for VS Code, free tier and alternatives](https://cookiesforai.app/tools/cline): Cline is an open source coding agent by Cline Bot Inc. that runs as a VS Code or JetBrains extension and a CLI, using your own model keys or local models.
- [Continue: open-source coding agent, current status and alternatives](https://cookiesforai.app/tools/continue): Continue is an open source coding agent for VS Code, JetBrains and the terminal by Continue Dev, Inc., which Cursor acquired; its GitHub repo is now read-only and no longer maintained.
- [Cursor: AI code editor, free tier and alternatives](https://cookiesforai.app/tools/cursor): Cursor is an AI code editor by Anysphere that pairs a desktop editor with an agent, a CLI and cloud agents, using models from several vendors plus its own Composer models.
- [Devin: cloud coding agent by Cognition, free tier and alternatives](https://cookiesforai.app/tools/devin): Devin is a cloud coding agent by Cognition that works in its own virtual machines, takes tasks from Slack, GitHub, Linear or Jira, and also ships as a CLI and the Devin Desktop editor.
- [Gemini CLI: open-source terminal agent, free tier and alternatives](https://cookiesforai.app/tools/gemini-cli): Gemini CLI is an open source terminal coding agent by Google that runs Gemini models from the command line, with MCP, agent skills, subagents and hooks, under the Apache-2.0 license.
- [GitHub Copilot: AI coding assistant, free tier and alternatives](https://cookiesforai.app/tools/github-copilot): GitHub Copilot is an AI coding assistant by GitHub that works in VS Code, JetBrains and other editors, in a CLI, and as a cloud agent that opens pull requests on GitHub.
- [Google Antigravity: AI coding platform, free tier and alternatives](https://cookiesforai.app/tools/antigravity): Google Antigravity is an agentic development platform by Google that runs coding agents in a desktop command center, a standalone IDE, a CLI called agy and extensions for other editors.
- [Goose: open-source desktop and terminal AI agent, free tier, alternatives](https://cookiesforai.app/tools/goose): Goose is an open source AI agent, created by Block and now part of the Agentic AI Foundation at the Linux Foundation, that runs as a desktop app and CLI with any model provider.
- [Hermes Agent: open-source personal AI agent, free tier and alternatives](https://cookiesforai.app/tools/hermes-agent): Hermes Agent is an open source personal AI agent by Nous Research that runs in the terminal, a desktop app and messaging apps, and writes new skills for itself from completed tasks.
- [Junie: JetBrains coding agent, free tier and alternatives](https://cookiesforai.app/tools/junie): Junie is a coding agent by JetBrains that runs as a CLI on macOS, Windows and Linux, inside JetBrains IDEs and in GitHub or GitLab pipelines, with any model you choose.
- [Kilo Code: open-source coding agent, free tier and alternatives](https://cookiesforai.app/tools/kilo-code): Kilo Code is an open source coding agent by Kilo Code, Inc., acquired by Anaconda in 2026, that runs in VS Code, JetBrains IDEs, a CLI and cloud agents with 500+ models.
- [OpenAI Codex: CLI and cloud coding agent, free tier and alternatives](https://cookiesforai.app/tools/codex): OpenAI Codex is a coding agent by OpenAI that runs as an open source CLI on your machine and as a cloud agent in ChatGPT, editing code, running commands and opening pull requests.
- [OpenClaw: open-source personal AI agent for chat apps, alternatives](https://cookiesforai.app/tools/openclaw): OpenClaw is an open source personal AI agent from the OpenClaw Foundation that runs on your own machine and takes tasks from WhatsApp, Telegram, Slack, Discord and other chat apps.
- [OpenCode: open-source terminal coding agent, free tier and alternatives](https://cookiesforai.app/tools/opencode): OpenCode is an open source terminal coding agent by Anomaly that works with 75+ model providers, local models included, and also ships as a desktop app and IDE extension.
- [Roo Code: VS Code coding agent, shutdown status and alternatives](https://cookiesforai.app/tools/roo-code): Roo Code was an open source coding agent extension for VS Code by Roo Code, Inc.; the extension was shut down on 2026-05-15 and its GitHub repository is archived.
- [Windsurf, now Devin Desktop: AI code editor, free tier and alternatives](https://cookiesforai.app/tools/windsurf): Windsurf is an AI code editor by Cognition, renamed Devin Desktop on 2026-06-02, that pairs a desktop editor and Tab completions with a local agent and handoff to Devin's cloud agents.
- [Zed: open-source AI code editor, free tier and alternatives](https://cookiesforai.app/tools/zed): Zed is an open source code editor by Zed Industries, written in Rust, with a built-in AI agent, edit predictions, external agents over ACP and real-time collaboration.

## Guides, comparisons, answers and research

- [Best agent skills for PowerPoint, Word, Excel and PDF (2026)](https://cookiesforai.app/best/agent-skills-for-office-documents): Anthropic's pptx, docx, xlsx and pdf skills are the most complete agent skills for Office files and PDFs, but only inside Claude; OpenAI's Apache-2.0 pdf skill is the one you may copy into any agent.
- [Best agent skills for making videos with code: 4 compared (2026)](https://cookiesforai.app/best/agent-skills-for-video-with-code): Remotion's remotion-best-practices is the agent skill AI assistants name first for making videos with code, in React; HeyGen's HyperFrames is the Apache-2.0 choice for videos written as plain HTML.
- [Best agent skills for database migrations: 5 compared (2026)](https://cookiesforai.app/best/best-agent-skills-for-database-migrations): database-migration from wshobson/agents is the best agent skill for safe migrations in Sequelize, TypeORM and Prisma apps; Supabase's Postgres Best Practices is the pick for SQL migrations on any Postgres.
- [Best agent skills for security review: 7 compared (2026)](https://cookiesforai.app/best/best-agent-skills-for-security-review): Sentry's security-review is the best agent skill for a security review of code, reporting only confirmed vulnerabilities; Trail of Bits' differential-review is the pick for reviewing one pull request with a written report.
- [Best Terraform agent skills to review Terraform plans: 5 compared (2026)](https://cookiesforai.app/best/best-terraform-agent-skills): terraform-test is the best Terraform agent skill for checking plans automatically and terraform-style-guide the best for reviewing HCL; none of HashiCorp's 20 skills reads terraform plan output for you (checked 2026-10-01).
- [Best MCP servers for web research: Exa, Tavily, Brave, Firecrawl (2026)](https://cookiesforai.app/best/mcp-servers-for-web-research): Exa is the best MCP server for web research for most agents, with search results that carry page text and a keyless start; Firecrawl is the pick for scraping and crawling known sites. 7 servers compared, and what 7 AI assistants recommend.
- [Aider alternatives: 5 terminal coding agents with MCP and skills (2026)](https://cookiesforai.app/alternatives/aider-alternatives): OpenCode is the best Aider alternative, free and MIT licensed with any model, local ones included, plus MCP and agent skills; Goose is the best free pick for local models, and Claude Code the best for git and CI automation.
- [Context7 alternatives: free, open source and local docs MCP servers (2026)](https://cookiesforai.app/alternatives/context7-alternatives): DeepWiki is the best overall Context7 alternative, free and keyless for any public GitHub repo; Microsoft Learn is the best free pick for Azure and .NET docs, and Grounded Docs the open source option that runs locally.
- [Gemini CLI alternatives: 5 free, open source and local picks (2026)](https://cookiesforai.app/alternatives/gemini-cli-alternatives): Google Antigravity is the closest Gemini CLI alternative, since Google moved free and Google AI Pro and Ultra users there on 2026-06-18; OpenCode is the best free open source pick, and Goose the best for local models with Ollama.
- [Playwright MCP alternatives: 3 browser servers for AI agents (2026)](https://cookiesforai.app/alternatives/playwright-mcp-alternatives): Chrome DevTools MCP is the best overall Playwright MCP alternative, free, open source and local, with performance and network debugging; Browser Use is the best open source pick for whole web tasks, and Browserbase the best for cloud browsers.
- [Roo Code alternatives after the shutdown: 5 VS Code agents (2026)](https://cookiesforai.app/alternatives/roo-code-alternatives): Roo Code was shut down on 2026-05-15. Cline is the closest replacement, since Roo Code was forked from it; Kilo Code is the best free pick for model choice and Roo-style modes, and OpenCode the best for terminal work.
- [Windsurf alternatives: 5 AI code editors compared (2026)](https://cookiesforai.app/alternatives/windsurf-alternatives): Cursor is the closest Windsurf alternative as a desktop AI editor with an agent and cloud agents; Google Antigravity is the best free pick, and Zed the best open source editor. Windsurf itself was renamed Devin Desktop on 2026-06-02.
- [How Codex, Claude Code and Gemini CLI load agent skills (2026)](https://cookiesforai.app/compare/how-codex-claude-code-and-gemini-cli-load-skills): Codex and Gemini CLI read agent skills from .agents/skills, while Claude Code reads .claude/skills; OpenCode reads both. All four load SKILL.md folders natively, connect MCP servers and bundle skills into plugins or extensions.
- [HyperFrames vs Remotion: which video skill for your AI agent (2026)](https://cookiesforai.app/compare/hyperframes-vs-remotion): Choose HyperFrames if you want videos written as plain HTML under Apache-2.0; choose Remotion if your team writes React and wants its mature cloud rendering, and can meet its license terms.
- [Superpowers vs Matt Pocock's skills: two coding agent methods (2026)](https://cookiesforai.app/compare/superpowers-vs-matt-pocock-skills): Choose Superpowers for a complete, automatic workflow from design to merged branch in 15 agents; choose Matt Pocock's skills for small skills you call yourself and edit. Both are MIT-licensed.
- [Is there an MCP server for Figma? Yes: Figma's official server, set up](https://cookiesforai.app/answers/is-there-an-mcp-server-for-figma): Yes. The Figma MCP server, first launched as the Dev Mode MCP server, is Figma's own server, hosted at mcp.figma.com with a local desktop version. It reads design context for code and can write to the canvas; tool calls depend on your seat.
- [Is there an MCP server for Jira? Yes: Atlassian's remote MCP server](https://cookiesforai.app/answers/is-there-an-mcp-server-for-jira): Yes. Jira is covered by the Atlassian Rovo MCP server, Atlassian's own hosted server at mcp.atlassian.com, which also reaches Confluence, Bitbucket and Loom. Every Atlassian Cloud plan has access, Free included, with hourly rate limits.
- [Is there an MCP server for Notion? Yes: Notion MCP and how to connect it](https://cookiesforai.app/answers/is-there-an-mcp-server-for-notion): Yes. Notion MCP is Notion's own hosted MCP server at mcp.notion.com, signed in with OAuth and set up in one command or config block in Claude Code, Codex, Cursor, VS Code and other clients. The older local repo is no longer maintained.
- [Is there an MCP server for Slack? Yes: Slack's official server, set up](https://cookiesforai.app/answers/is-there-an-mcp-server-for-slack): Yes. Slack runs its own hosted MCP server at mcp.slack.com, generally available since 2026-02-17. It connects through an admin-approved Slack app with OAuth, and Slack's plugin sets it up in Claude Code and Cursor with one command.
- [Where every coding agent looks for skills: folders for 78 agents (2026)](https://cookiesforai.app/guides/where-agents-look-for-skills): Coding agents read agent skills from a folder in your project, and 21 of the 78 agents in the open skills CLI share one folder, .agents/skills, including Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.
- [Agent skill and AI tool directories compared, October 2026](https://cookiesforai.app/research/agent-skill-and-ai-tool-directories-compared-october-2026): A dated comparison of 9 agent skill directories and 6 AI tool directories that AI assistants used in our October 2026 tests: size, item pages, how to get listed, agent extras and how often each was cited.
- [How 6 AI assistants answer AI tool questions: 110 runs, October 2026](https://cookiesforai.app/research/ai-assistants-field-study-october-2026): We asked ChatGPT, Gemini, Perplexity, Google AI Mode, Google AI Overviews and Grok the same 13 questions about software and AI tools, 110 times on 2026-10-01, and recorded every name and source they gave.
- [How Claude finds agent skills it does not know: 93 runs, October 2026](https://cookiesforai.app/research/how-claude-finds-agent-skills-october-2026): In 93 runs on Claude Opus 5.5, Sonnet 5.5 and Fable 5.1 on 2026-10-01, every question about a little-known agent skill made Claude search, and 13 of 18 answers linked a skill directory page.

## Changes to AI assistants and new tools, dated

- [AI assistants: model, search and crawler changes, dated](https://cookiesforai.app/research/engine-changes): The engine changes tracker lists dated changes to the models, web search and crawlers of Claude, ChatGPT, Google (Gemini, Search and AI features), Grok, Perplexity, Copilot and open models, one table per assistant, each row linked to the maker's own page.
- [What changed for getting found by AI, week of September 28, 2026](https://cookiesforai.app/changes/2026-w40): Google tightened its guidance on AI-written pages while its September spam update kept rolling out, Perplexity rebuilt how it ranks pages, and Anthropic opened a submission portal for its Claude directory.

## About this site

- [About CookiesForAI, an independent agent skills and MCP directory](https://cookiesforai.app/about): CookiesForAI is an independent directory of agent skills, MCP servers and AI coding tools that publishes the facts we checked, with dates, and our own research on how AI assistants recommend tools.
- [Open data: agent skills, MCP servers and AI coding tools as JSON](https://cookiesforai.app/data): CookiesForAI publishes its whole catalogue as JSON files that anyone may reuse with credit, the agent skills, MCP servers and AI coding tools with their check dates, and the 78 agents the open skills CLI installs into.
- [How CookiesForAI checks agent skills, MCP servers and coding tools](https://cookiesforai.app/method): Every fact on CookiesForAI comes from a named source, the publisher's GitHub repository, its own docs, or the official MCP Registry, and carries the date we read it.