# AgentHub

> AgentHub is a directory of Skills, MCP servers, CLIs and plugins that AI agents can use. Every resource links to its GitHub repository and comes with install commands for Claude Code and Codex.

- Every page has a Markdown version: append `.md` to the URL, or send the header `Accept: text/markdown`.
- Search: `GET https://hebbmind.com/api/v1/search?q=<keyword>&type=<cli|skill|plugin|mcp>&profession=<profession id>&tag=<tag>` returns JSON.
- Profession ids: `GET https://hebbmind.com/api/v1/professions`. The list is maintained by the site operators and changes over time.
- Tags: `GET https://hebbmind.com/api/v1/tags`. The `tag` parameter takes several tags separated by commas; a resource must carry all of them.
- Trending: `GET https://hebbmind.com/api/v1/hot`, the resources that got the most attention in the last 7 days.
- MCP endpoint: `https://hebbmind.com/api/mcp` (Streamable HTTP, no authentication).
- Every resource lives in its own GitHub repository. This site only provides the index, a README copy and install commands.
- Names, descriptions and READMEs are shown as their authors wrote them and may be in Chinese.

## Categories

- [Tools](https://hebbmind.com/tools.md): Every resource. Filter by type, profession or tag, or search by keyword
- [CLI](https://hebbmind.com/tools.md?type=cli): Command-line tools that agents can call directly from a terminal.
- [Skill](https://hebbmind.com/tools.md?type=skill): Skill packages loaded on demand (SKILL.md plus scripts and references) that teach agents specific tasks.
- [Plugin](https://hebbmind.com/tools.md?type=plugin): Plugins that bundle commands, subagents, skills, hooks and MCP servers.
- [MCP](https://hebbmind.com/tools.md?type=mcp): Servers that give agents tools and data through the Model Context Protocol.

## Rankings

- [Trending](https://hebbmind.com/hot.md): The resources that got the most attention in the last 7 days, ranked by views and install-command copies

## By profession

- [Full-stack / Indie](https://hebbmind.com/tools.md?profession=fullstack): 522 resources. General software work: coding-agent workflows, code review, debugging and Git collaboration.
- [Frontend](https://hebbmind.com/tools.md?profession=frontend): 447 resources. Web and mobile-web interfaces: building, debugging and performance tuning.
- [Backend](https://hebbmind.com/tools.md?profession=backend): 408 resources. Designing and building APIs, databases and middleware.
- [Mobile & desktop](https://hebbmind.com/tools.md?profession=mobile): 96 resources. Building and shipping iOS, Android and desktop apps.
- [Game development](https://hebbmind.com/tools.md?profession=gamedev): 29 resources. Gameplay, engine scripting, levels and 3D assets.
- [QA](https://hebbmind.com/tools.md?profession=qa): 101 resources. Functional testing, test automation and quality assurance.
- [DevOps / SRE](https://hebbmind.com/tools.md?profession=devops): 209 resources. Deployment, monitoring, cloud resources and reliability.
- [ML / AI](https://hebbmind.com/tools.md?profession=algorithm): 162 resources. Model training, evaluation and LLM application development.
- [Data engineering](https://hebbmind.com/tools.md?profession=data-engineering): 81 resources. Data pipelines, warehouse modeling, ETL and data quality.
- [Data analysis](https://hebbmind.com/tools.md?profession=data): 152 resources. Querying, statistical analysis, reporting and visualization.
- [GIS / Surveying](https://hebbmind.com/tools.md?profession=gis): 12 resources. Spatial data and analysis, QGIS mapping, remote sensing, geocoding, routing and map services.
- [Security](https://hebbmind.com/tools.md?profession=security): 71 resources. Code audits, vulnerability triage, penetration testing and compliance.
- [Product / Projects](https://hebbmind.com/tools.md?profession=product): 246 resources. Specs, user research, roadmaps, scheduling and project delivery.
- [Design](https://hebbmind.com/tools.md?profession=design): 239 resources. Interface, interaction, visual and brand design.
- [Architecture / Civil](https://hebbmind.com/tools.md?profession=architecture): 19 resources. Building design and BIM, CAD drawings, structural analysis, quantities, costing and site paperwork.
- [Hardware engineering](https://hebbmind.com/tools.md?profession=hardware): 17 resources. Part and assembly modeling, schematics and PCB review, simulation, and BOM and production files.
- [Operations](https://hebbmind.com/tools.md?profession=operations): 233 resources. Content, campaign, community, user and e-commerce operations, plus performance reviews.
- [Marketing & sales](https://hebbmind.com/tools.md?profession=marketing): 306 resources. Marketing content, ad campaigns, market research and sales support.
- [Admin / Office](https://hebbmind.com/tools.md?profession=office): 238 resources. Docs, spreadsheets and slides, reports, email and calendars, meeting notes and daily admin.
- [Writing / Content](https://hebbmind.com/tools.md?profession=writing): 229 resources. Writing and editing articles, books, technical docs and social content.
- [Video / Media](https://hebbmind.com/tools.md?profession=media): 187 resources. Video editing, image and audio generation, music production, podcasts and short videos.
- [Customer support](https://hebbmind.com/tools.md?profession=support): 65 resources. Tickets, customer questions, knowledge-base upkeep and service quality.
- [HR](https://hebbmind.com/tools.md?profession=hr): 88 resources. Screening, interviews, onboarding, training and employee relations.
- [Legal](https://hebbmind.com/tools.md?profession=legal): 94 resources. Contract drafting and review, legal research, litigation documents, compliance and IP.
- [Finance / Accounting](https://hebbmind.com/tools.md?profession=finance): 142 resources. Bookkeeping, reconciliation, financial statements, budgets and tax.
- [Investing / Analysis](https://hebbmind.com/tools.md?profession=investment): 104 resources. Market data, company research, valuation models and quant trading.
- [Teachers / Students](https://hebbmind.com/tools.md?profession=education): 212 resources. Lesson prep, quizzes, grading and course materials; self-study and exam prep.
- [Research / Academia](https://hebbmind.com/tools.md?profession=research): 255 resources. Literature search and reviews, experimental data analysis, paper writing and submission.
- [Healthcare](https://hebbmind.com/tools.md?profession=healthcare): 19 resources. Clinical notes and coding, drug and guideline lookup, FHIR and imaging data, clinical research.
- [Translation / L10n](https://hebbmind.com/tools.md?profession=translation): 84 resources. Translating documents and software, localization and multilingual QA.
- [Founders](https://hebbmind.com/tools.md?profession=founder): 280 resources. Business plans, fundraising decks, business analysis and team management.

## By tag

- [anthropic](https://hebbmind.com/tools.md?tag=anthropic): 201 resources
- [web-development](https://hebbmind.com/tools.md?tag=web-development): 165 resources
- [python](https://hebbmind.com/tools.md?tag=python): 158 resources
- [financial-analysis](https://hebbmind.com/tools.md?tag=financial-analysis): 128 resources
- [writing](https://hebbmind.com/tools.md?tag=writing): 109 resources
- [teaching](https://hebbmind.com/tools.md?tag=teaching): 103 resources
- [ui-design](https://hebbmind.com/tools.md?tag=ui-design): 100 resources
- [data-analysis](https://hebbmind.com/tools.md?tag=data-analysis): 98 resources
- [translation](https://hebbmind.com/tools.md?tag=translation): 88 resources
- [copywriting](https://hebbmind.com/tools.md?tag=copywriting): 86 resources
- [All tags](https://hebbmind.com/tags.md): The tag list and how many resources carry each tag

## Editors’ picks

- [Browser Use](https://hebbmind.com/cli/browser-use.md): [CLI] Open-source browser agent project. Its browser-use CLI lets Claude Code, Codex and other agents drive your logged-in local Chrome with Python snippets, or connect to a cloud browser; also ships a Python agent library. The cloud browser needs an API key.
- [Browser Use](https://hebbmind.com/skill/browser-use.md): [Skill] Controls your local Chrome over CDP to navigate, click, type, take screenshots and scrape data, reusing logged-in sessions. Official browser-use skill; install the browser-use CLI with uv first.
- [mattpocock/skills](https://hebbmind.com/plugin/mattpocock-skills.md): [Plugin] Matt Pocock's engineering skills: /grill-me interrogates requirements to align on intent, then a spec-and-ticket flow, TDD, code review and domain modeling. Small, composable skills, listed in the official Claude Code plugin marketplace.
- [MarkItDown-MCP](https://hebbmind.com/mcp/markitdown-mcp.md): [MCP] From Microsoft: converts PDF, Word, Excel, PowerPoint, HTML and other files or URLs to Markdown so agents can read and search them. A single convert_to_markdown tool over STDIO or local HTTP.
- [Superpowers](https://hebbmind.com/plugin/superpowers.md): [Plugin] A complete development methodology for coding agents: brainstorm to clarify requirements, write an implementation plan, then build with subagents, with red-green TDD, systematic debugging and code review throughout. In the official Claude Code and Codex marketplaces.
- [Stripe MCP](https://hebbmind.com/mcp/stripe-modelcontextprotocol.md): [MCP] Lets agents call the Stripe API to manage customers, payments, subscriptions, invoices and refunds, and search Stripe docs and support articles. Maintained by Stripe; the remote server uses OAuth, or run it locally via npx with a secret key.
- [Knowledge Work Plugins](https://hebbmind.com/plugin/knowledge-work-plugins.md): [Plugin] Anthropic's knowledge-work plugin marketplace, bundling skills, commands and connectors by role: sales, support, product, marketing, legal, finance, HR, data and more, plus many partner plugins. Built mainly for Cowork; also works in Claude Code.
- [Claude for Financial Services](https://hebbmind.com/plugin/financial-services.md): [Plugin] Anthropic's financial-services plugin marketplace: skills, commands and agents for valuation models (DCF, LBO, comps), banking materials, sell-side research, private equity and fund ops, with FactSet, Morningstar and other connectors that may need vendor subscriptions or keys.
- [Knowledge Work Plugins](https://hebbmind.com/skill/knowledge-work-plugins.md): [Skill] Anthropic's role-based skill collection covering sales, finance, legal, HR, support, marketing, product, design, operations and data analysis: over a hundred skills you can install one at a time. Works best with CRM, data warehouse and other connectors.
- [Marketing Skills](https://hebbmind.com/plugin/marketingskills.md): [Plugin] Marketing skills for technical marketers and founders: 50 skills covering conversion optimization, copywriting, SEO and AI search, paid ads, email and cold outreach, pricing, customer research and launch strategy, all sharing one product-marketing context.
- [Cloudflare MCP Server](https://hebbmind.com/mcp/mcp-server-cloudflare.md): [MCP] Cloudflare's official remote MCP servers: manage Workers and bindings such as KV, R2 and D1, and query logs and observability, builds, DNS analytics and Radar data. Authorizes with Cloudflare OAuth; some features need a paid plan.
- [Context7](https://hebbmind.com/mcp/context7.md): [MCP] Injects up-to-date, version-specific docs and code examples for libraries and frameworks into the agent's context, so it stops using outdated or invented APIs. By Upstash; works anonymously, and a free API key raises the limits.
- [GitHub CLI](https://hebbmind.com/cli/gh.md): [CLI] GitHub's official CLI: manage pull requests, issues, releases and Actions workflows from the terminal. Most commands support --json output that agents can parse, and an official agent skill is available. Run gh auth login first.
- [Frontend Design](https://hebbmind.com/skill/frontend-design.md): [Skill] Has the agent commit to a visual direction before building or redesigning an interface, making deliberate choices on color, type and layout instead of generic, templated AI UI. Official Anthropic skill.
- [Knowledge Graph Memory Server](https://hebbmind.com/mcp/memory.md): [MCP] Gives agents long-term memory across sessions with a local knowledge graph of entities, relations and observations, stored in a local JSONL file you can query and edit. Official MCP reference implementation.
- [PDF](https://hebbmind.com/skill/pdf.md): [Skill] Extracts text and tables from PDFs; merges, splits and rotates pages, adds watermarks, fills forms and OCRs scanned documents. The official Anthropic skill behind Claude's document features; source-available, not open source.
- [yt-dlp](https://hebbmind.com/cli/yt-dlp.md): [CLI] Command-line audio and video downloader supporting thousands of sites: pick formats and quality, grab subtitles and metadata, and merge or transcode with FFmpeg. The actively maintained fork of youtube-dl.
- [DuckDB](https://hebbmind.com/cli/duckdb.md): [CLI] In-process analytical SQL database. Its CLI queries CSV, Parquet and JSON files directly with SQL, no import or server needed, so agents can sample and aggregate large files. Officially maintained.
- [Frontend Design](https://hebbmind.com/plugin/frontend-design.md): [Plugin] Has the agent settle on a clear aesthetic direction first, then write distinctive, production-ready frontend interfaces that avoid the generic AI look. Official Anthropic plugin.
- [Playwright MCP](https://hebbmind.com/mcp/playwright.md): [MCP] Lets agents drive a real browser through the accessibility tree: navigate, click, fill forms and take screenshots, without needing a vision model. Maintained by Microsoft.
- [MarkItDown](https://hebbmind.com/cli/markitdown.md): [CLI] Converts PDF, Word, Excel, PowerPoint, HTML, images, audio and more into Markdown that keeps headings, lists and tables, ready for LLMs to read and analyze. Maintained by Microsoft; requires Python 3.10+.
- [GitHub MCP Server](https://hebbmind.com/mcp/github.md): [MCP] GitHub's official MCP server: lets agents read and write repositories and code, manage issues and pull requests, and check Actions workflows and code-scanning alerts. Use the hosted remote server or run it locally in Docker; needs a personal access token or OAuth.
- [Code Review](https://hebbmind.com/plugin/code-review.md): [Plugin] Reviews pull requests with several parallel subagents, scores each finding by confidence to filter out false positives, and can post the results as PR comments. Official Anthropic plugin; requires a logged-in GitHub CLI.
- [Skill Creator](https://hebbmind.com/skill/skill-creator.md): [Skill] Guides the agent through writing or improving a skill: clarify intent, draft SKILL.md, run scored evals with and without the skill, then tune the description so it triggers accurately. Official Anthropic skill.

## Collections

- [Spec, TDD and review for coding agents](https://hebbmind.com/collections/spec-tdd-review-coding-agents.md): For developers and tech leads who want coding agents to work like careful engineers: guardrails first, then interview, spec, test-first build, debug, verify, review. Most run in Claude Code or Codex; the three Anthropic plugins are Claude Code only. Agent review assists; a person approves merges. (12 resources)
- [UI design taste for agent-built apps](https://hebbmind.com/collections/ui-design-taste.md): For designers and frontend devs making agent-built web UI look designed. Most items need a coding agent like Claude Code or Codex, Node.js and web code. Set the system, explore, commit, review, polish, animate, test accessibility. Figma MCP: paid Dev/Full seat. Checks don't replace design review. (12 resources)
- [Code-made video: launches and explainers](https://hebbmind.com/collections/code-to-video-launch-explainers.md): For founders, marketers, developer advocates and teachers: Claude Code or Codex on your computer scripts, voices, builds, captions and publishes the video. ElevenLabs, HeyGen and Postiz cloud have paid plans; for-profit firms over 3 people need a Remotion license. Label AI voices and avatars. (15 resources)
- [Office documents: Word, Excel, slides](https://hebbmind.com/collections/office-documents-word-excel-slides.md): For office staff, analysts, consultants: read files and scans, build the sheet, write the report, make the deck, handle PDFs, share. Anthropic's docx, xlsx, pptx and pdf skills power Claude's file features; others need Python or Node. Check every number; keep confidential files in approved tools. (15 resources)
- [Product discovery, specs and delivery](https://hebbmind.com/collections/product-discovery-specs-delivery.md): For PMs and founders, in order: research, market scans, competitors, priorities, spec, prototype, tickets, analytics, re-planning, updates. Most install from a terminal into Claude Code or Codex. Lovable, Linear, Jira, PostHog need accounts. Keep customer data in approved tools; you set priorities. (15 resources)
- [SEO and AI search visibility](https://hebbmind.com/collections/seo-ai-search-visibility.md): For in-house marketers, content leads and solo founders: connect Search Console, audit, check AI crawlers and citations, research keywords, refresh posts, edit. Most run in Claude Code. Search-volume data costs money; AI-citation tracking is immature. Improve your pages; don't mass-produce. (13 resources)
- [Contract review and NDA triage](https://hebbmind.com/collections/contract-review-nda-triage.md): In-house counsel and legal ops: triage NDAs, review clauses and DPAs, score risk, redline in Word, sign. US-law defaults. Plugins need Claude Cowork or Code; others also run in Codex. Use an employer-approved plan for client data; counterparty files can hide prompt injections. A lawyer reviews all. (12 resources)
- [Month-end close and reconciliation](https://hebbmind.com/collections/month-end-close-reconciliation.md): Controllers, accountants, FP&A: plan the close, pull GL and bank data, draft accruals and JEs, reconcile, build statements, explain variances, QA the workbook. Skills run in Claude Code or Codex. Let agents draft, not post; a qualified accountant reviews. Assumes US GAAP/SOX. Use approved AI only. (14 resources)
- [K-12 lesson planning and classroom tools](https://hebbmind.com/collections/k12-lesson-planning.md): For US K-12 teachers and instructional coaches: unpack standards, plan, differentiate, write math checks, make slides, prep, post to Google Classroom or Canvas. K-12 skills use US standards and come with Claude for Teachers. De-identify student data, follow district AI policy, review before class. (11 resources)
- [Literature review to journal submission](https://hebbmind.com/collections/literature-review-to-submission.md): For grad students and postdocs in any field: search, screen and read, draft, fit a journal, check claims, tidy references, review and revise. Some steps need keys or sign-ins. Tools assist; you verify every citation and claim, follow the journal's AI policy and keep unpublished data private. (15 resources)
- [Building agents: from model API to evals](https://hebbmind.com/collections/build-your-first-agent.md): For engineers new to agent work, in build order: model API, first agent, tools over MCP (the open protocol for agent tools), data, context and memory, a framework, evals, tracing, sandboxing. Skills run in Claude Code or Codex, plugins in Claude Code. Your agents need a model API key, usually paid. (13 resources)
- [Investment research: filings and models](https://hebbmind.com/collections/investment-research-filings-models.md): For analysts, finance students and investors: get market and macro data, read SEC filings and transcripts, build and check comps and DCF models, test ideas with quant tools. Some need paid plans or keys; keep non-public data out of hosted tools. Research aid, not investment advice; check figures. (13 resources)
- [Applied economics with coding agents](https://hebbmind.com/collections/applied-economics-with-agents.md): For economics PhD students, applied microeconomists and policy analysts: set up a project, get FRED and SEC data, run Stata, R or Python, draft and revise. Agents assist; check every merge, estimate and sentence. Local tools still send what the agent reads to the AI provider: check data agreements. (14 resources)
- [Bioinformatics for bench biologists](https://hebbmind.com/collections/bioinformatics-for-bench-biologists.md): For wet-lab biologists moving to computational work: look up genes, find public data, run sequencing pipelines, then single-cell, stats and figures. Works in Claude Code and Codex unless noted; most need local Python. Keep patient data off untrusted services; have a bioinformatician review results. (12 resources)
- [All collections](https://hebbmind.com/collections.md): Hand-picked sets of resources built around one job, with a note on every item

## Blog

- [Claude Code for applied economists: data, Stata or R, and a replication package](https://hebbmind.com/blog/claude-code-applied-economists.md): 2026-10-12 A practical guide for economics PhD students and applied researchers: connect Claude Code to Stata or R, script your FRED, EDGAR and Census downloads, run and audit identification designs, and assemble an AEA-style replication package, plus the checks a human still has to do.
- [Give your agent a browser: choosing browser automation tools](https://hebbmind.com/blog/give-your-agent-a-browser.md): 2026-10-12 Which browser tool to give an AI agent for four jobs: checking a frontend change, end-to-end testing, working in sites you are signed in to, and collecting web data. Setup commands, example prompts, privacy defaults to switch off, and safety rules for logged-in sessions.
- [Getting cited by AI answer engines without spamming: an SEO and GEO audit workflow](https://hebbmind.com/blog/seo-geo-ai-answer-engines.md): 2026-10-12 A step-by-step audit for in-house marketers and founders: fix technical SEO, check which AI crawlers you let in, test whether ChatGPT, Perplexity and Google cite you, pick pages with Search Console, refresh and edit them, and earn honest third-party mentions. Tools, setup, prompts and limits.
- [A systematic literature review with agents: search, screen, extract and cite](https://hebbmind.com/blog/systematic-literature-review-agents.md): 2026-10-12 A stage-by-stage guide for graduate students and early-career researchers: register a protocol, test searches with agents and run them in each database, pilot screening against your own labels, extract with page citations, verify every reference and disclose AI use. Agents assist; you decide.
- [Before you file: verifying AI-drafted citations](https://hebbmind.com/blog/verify-legal-citations-before-filing.md): 2026-10-12 A routine for litigators, paralegals and law students: screen the other side's papers for hidden instructions, make the record searchable, draft with every authority tagged, check each citation exists and says what you claim, and check redactions with x-ray before filing.
- [A product manager's week with agents: briefs, research synthesis, specs and tickets](https://hebbmind.com/blog/pm-agent-assisted-week.md): 2026-10-12 A week of PM work handed partly to agents: a morning brief from Slack, email and notes, research synthesis with checkable quotes, a spec from a measurable goal, PRD to Linear or Jira tickets, a read-only PostHog check and the stakeholder update, with setup for Cowork, Claude Code and Codex.
- [Month-end close with agents: what to automate and what to review](https://hebbmind.com/blog/month-end-close-agent-drafts.md): 2026-10-12 A T+1 to T+5 guide for controllers and staff accountants: which close steps an agent can draft (accruals, reconciliations, statements and flux commentary, workbook checks, SOX samples), how to set up the skills, and why the agent drafts but never posts.
- [Make a product launch video from your codebase with HyperFrames or Remotion](https://hebbmind.com/blog/launch-video-from-codebase.md): 2026-10-12 A step-by-step guide for founders, product marketers and devrel: brief, voiceover, scenes built from your own product, captions, encoding and publishing with HyperFrames or Remotion, plus licenses, voice service costs and when to disclose AI voices and music.
- [A K-12 teacher's week with Claude: planning, differentiation and checks for understanding](https://hebbmind.com/blog/k12-teacher-week-claude.md): 2026-10-12 A day-by-day guide for US K-12 teachers: set up Claude for Teachers (free for a year for verified teachers), keep student data out of prompts, then plan, differentiate, check understanding in math, post to Google Classroom or Canvas, and reflect, with grading left to you.
- [All posts](https://hebbmind.com/blog.md): Tutorials, comparisons and notes from using these tools, newest first

## Access

- [Guide for agents](https://hebbmind.com/agents.md): How to use llms.txt, Markdown, the JSON API and MCP
- [OpenAPI description](https://hebbmind.com/openapi.json): Machine-readable definition of the public JSON API
- [Make a suggestion](https://hebbmind.com/suggest.md): A form for people to send feedback, recommend a tool or describe what they need; agents cannot submit it

## Optional

- [Full resource list](https://hebbmind.com/llms-full.txt): Description, repository and install commands of every listed resource
- [Sitemap](https://hebbmind.com/sitemap.xml): URLs of all pages