thedixitjain/the-mega-skill-library

35,802 agent skills, subagents, slash commands, prompts and rules files curated from 186 GitHub repositories β€” browsable, greppable, installable.

Python

4

4 commits

updated Jul 30, 2026

See the code

README

🧠 The Mega Skill Library

The largest open catalog of AI agent skills on GitHub

35,802 ready-to-use skills, subagents, slash commands, prompts and rules β€” harvested, deduplicated and organized from 186 repositories across the Claude Code / Cursor / Codex / Copilot skill ecosystem, so you never have to write one from scratch again.

Validate catalog License: MIT PRs Welcome GitHub stars Assets Source repos Categories

Browse the index Β· Search the catalog Β· Quick start Β· Credits Β· Contribute


Why this exists

AI coding agents (Claude Code, Cursor, Codex, Copilot…) got a superpower this year: Skills β€” small, self-contained instruction packs that teach an agent how to do one thing well (write a spec, review a PR, design an API, run a security audit, format a resume). The problem: they're scattered across hundreds of individual GitHub repos, half-documented, and impossible to search in one place.

This repo fixes that. Every skill-bearing repo in the ecosystem, pulled together, deduplicated, categorized, and made greppable in one file. Whether you're a student who just discovered agent skills exist, or a staff engineer wiring up a fleet of subagents in production β€” the same catalog works for you.

What's inside

KindCountWhereWhat it is
🧩 Agent Skills18,681library/Full SKILL.md bundles (+ scripts, templates, references)
πŸ€– Subagents2,888agents/Specialized agent role definitions
⚑ Slash Commands2,773commands//command shortcuts
πŸ’¬ Prompts10,074prompts/System prompts, prompt corpora, leaked prompts
πŸ“ Rules1,386rules/CLAUDE.md / AGENTS.md / .cursorrules exemplars
πŸ“– Reference543reference/Awesome-lists, cheatsheets, handbooks (verbatim)

πŸš€ Quick start

git clone https://github.com/thedixitjain/the-mega-skill-library.git

Pick the path that matches how much you already know:

πŸŽ“ New to agent skills? β€” one command, zero config

Copy the router skill. It searches the other 35,801 assets for you β€” nothing else loads into context or slows your agent down.

cp -r the-mega-skill-library/master-skill ~/.claude/skills/master-skill-library

Now just talk to Claude Code normally. When a task matches something in the library, it finds the right skill and uses it automatically. That's it β€” you're done.

πŸ’Ό Know exactly what you want? β€” install specific skills

Claude Code reads every installed skill's frontmatter at startup, so only install what you'll actually use β€” dozens, not thousands.

cp -r the-mega-skill-library/library/engineering-core/tdd-guide ~/.claude/skills/

Project-only instead of global? Copy into <project>/.claude/skills/ instead of ~/.claude/skills/.

⌨️ Power user? β€” grep it, script it, pipe it
grep -i "pdf" CATALOG.tsv
awk -F'\t' '$2=="security-and-compliance" && $1=="skill"' CATALOG.tsv
grep -i "code review" CATALOG.tsv | awk -F'\t' '$1=="agent"' | cut -f3,6

CATALOG.tsv is one row per asset: kind Β· category Β· name Β· path Β· source_repo Β· description.

πŸ› οΈ Using Cursor, Codex, Copilot, or something else?

Most files here are plain Markdown with YAML frontmatter β€” portable by design. library/ bundles follow the Agent Skills spec (works with any harness that supports it); rules/ files map directly to .cursorrules / AGENTS.md / custom instructions; prompts/ and commands/ are copy-paste text you can drop into any system-prompt or slash-command config.

πŸ—‚οΈ Browse by category

22 categories, auto-sorted by asset count. Click through for the full browsable table of every skill/agent/command/prompt in that category.

CategoryAssetsCovers
πŸ“¦ General purpose5,575Uncategorized / cross-cutting
πŸ€– AI agents & harness4,583Agent design, orchestration, subagents, context engineering
πŸ’¬ Prompt engineering2,868Prompt techniques, system prompts, optimizers, persona design
βš™οΈ Engineering core2,805Refactoring, debugging, review, architecture, git, TDD
πŸ”¬ Research & academic2,483Literature review, papers, journals, grants, regulatory science
☁️ DevOps & infra1,605Docker, K8s, Terraform, CI/CD, cloud, observability, SRE
πŸ”’ Security & compliance1,604AppSec, pentest, OSINT, threat modeling, SOC2/ISO/GDPR
πŸ“£ Marketing & growth1,584SEO/AEO, ads, CRO, social, campaigns, growth loops
πŸ—„οΈ Backend & data1,583APIs, databases, schemas, queues, caching, pipelines
πŸ”Œ MCP & integrations1,524MCP servers/clients, third-party integrations, browser automation
πŸ§ͺ Testing & QA1,506Test generation, E2E, coverage, QA process, browser testing
🎨 Frontend & design1,359UI/UX, design systems, CSS, React, accessibility
✍️ Writing & content1,345Copywriting, editing, humanizing, translation, narrative
πŸ“ Docs & knowledge mgmt1,158Documentation, ADRs, technical writing, note systems
πŸ’Ό Business & finance1,152Finance, pricing, legal, sales, HR, exec advisory
🎬 Media & creative778Video, image, slides/PPTX, audio, game dev, generative art
πŸ“Š Data science & ML722ML/DL, training, fine-tuning, evaluation, statistics
πŸ“‹ Product & PM473PRDs, roadmaps, user stories, discovery, analytics
πŸ“± Mobile & platform398iOS/Android/Flutter, desktop, extensions, BI platforms
⚑ Productivity & workflow353Planning, automation, meetings, scaffolds, coaching
πŸ“š RAG, memory & knowledge333RAG, vector search, embeddings, agent memory, knowledge graphs
🧩 Skill authoring meta11Creating, testing, auditing and improving skills themselves

Full index with descriptions and navigation: INDEX.md

πŸ“ Repo layout

the-mega-skill-library/
β”œβ”€β”€ INDEX.md                 master index β€” start here
β”œβ”€β”€ CATALOG.tsv               one row per asset β€” grep/awk this
β”œβ”€β”€ master-skill/SKILL.md     router skill β€” install this one, it finds the rest
β”œβ”€β”€ library/<category>/<slug>/SKILL.md    18,681 Agent Skills (+ bundled resources)
β”œβ”€β”€ agents/<category>/<slug>.md           2,888 subagent definitions
β”œβ”€β”€ commands/<category>/<slug>.md         2,773 slash commands
β”œβ”€β”€ prompts/<category>/<slug>.md          10,074 system prompts / corpora
β”œβ”€β”€ rules/<category>/<slug>.md            1,386 CLAUDE.md / AGENTS.md / .cursorrules
β”œβ”€β”€ reference/<owner~repo>/...            543 awesome-lists, cheatsheets, handbooks
β”œβ”€β”€ _index/<category>.md      per-category browsable tables
└── _logs/                    harvest run logs

The raw upstream git clones used to build this (_sources/, ~9 GB, 186 repos) aren't part of this repository β€” only the curated, deduplicated output above is published. See Refreshing below.

πŸ”Ž Provenance, credits & licensing

This is a curated aggregation, not original work. Every skill, agent, command, prompt and rules file was written by its original author β€” full attribution for all 237 source repositories lives in CREDITS.md, linked directly to each one's GitHub page.

Every single harvested file also carries source_repo, source_path and source_url in its own frontmatter, plus a human-readable Source footer linking upstream β€” open any file to see exactly where it came from. Duplicates across repos were collapsed by content hash, keeping the most authoritative copy (official vendor repos first, then by star count); collapsed copies are listed in each file's "Also appears in" footer, so nothing is silently lost.

This repo's own layer β€” the categorization, indexing, catalog, router skill, and documentation β€” is MIT licensed. The 35,802 harvested files themselves come from 186 different repositories (plus 51 more kept as reference material) under their own original licenses β€” check the upstream repo (linked in every file's footer, and in CREDITS.md) before redistributing or using an individual file commercially.

πŸ”„ Refreshing / regenerating

The curated buckets here (library/, agents/, commands/, prompts/, rules/, reference/, _index/, CATALOG.tsv) were generated once from local clones of all 186 source repos. To regenerate: re-clone each repo listed in CATALOG.tsv / _index/by-source-repo.md, then re-run a categorize β†’ dedup-by-hash β†’ catalog pipeline against them. See CONTRIBUTING.md if you want to help formalize that pipeline into a script others can run.

🀝 Contributing

Found a skill-bearing repo that isn't here yet? Found a broken path or a duplicate that should've been collapsed? PRs and issues are very welcome β€” see CONTRIBUTING.md for the frontmatter convention and how to add an entry to CATALOG.tsv.

❓ FAQ

What's the difference between a "skill", "agent", "command", "prompt" and "rule"?
  • Skill β€” a full SKILL.md bundle (+ optional scripts/templates) an agent loads on demand for one task.
  • Agent / subagent β€” a role definition (persona + tools + instructions) spawned to handle a sub-task.
  • Command β€” a /slash-command shortcut that expands to a fixed prompt or workflow.
  • Prompt β€” a standalone system prompt or prompt corpus, not packaged as a skill.
  • Rule β€” a CLAUDE.md / AGENTS.md / .cursorrules style always-on instruction file.
Will installing the router skill slow down my agent or eat my context window?

No. The router (master-skill/) is the only thing that ever loads, and it's one small file. It searches CATALOG.tsv on demand and reads just the one or two matching files per task β€” the other 35,800 assets sit untouched on disk.

Can I use this commercially?

The curation layer is MIT. Individual harvested files retain their original upstream license β€” check the source before commercial use of a specific file. See Provenance & licensing.

My favorite skill repo isn't in here β€” why?

Either it hasn't been discovered yet, or it didn't fit the harvest criteria (skill-shaped content: SKILL.md, subagent defs, slash commands, system prompts, or rules files). Open a PR β€” see Contributing.

⭐ Support

If this saved you time, star the repo β€” it's the main way other people find it. Issues, PRs, and "hey you should add X" suggestions are all welcome.

agent-skills
ai-agents
awesome-list
claude
claude-code
cursor
developer-tools
llm
productivity
prompt-engineering

Contributors

thedixitjain

4 commits

thedixitjain/the-mega-skill-library

35,802 agent skills, subagents, slash commands, prompts and rules files curated from 186 GitHub repositories β€” browsable, greppable, installable.

Python

4

4 commits

updated Jul 30, 2026

See the code

README

🧠 The Mega Skill Library

The largest open catalog of AI agent skills on GitHub

35,802 ready-to-use skills, subagents, slash commands, prompts and rules β€” harvested, deduplicated and organized from 186 repositories across the Claude Code / Cursor / Codex / Copilot skill ecosystem, so you never have to write one from scratch again.

Validate catalog License: MIT PRs Welcome GitHub stars Assets Source repos Categories

Browse the index Β· Search the catalog Β· Quick start Β· Credits Β· Contribute


Why this exists

AI coding agents (Claude Code, Cursor, Codex, Copilot…) got a superpower this year: Skills β€” small, self-contained instruction packs that teach an agent how to do one thing well (write a spec, review a PR, design an API, run a security audit, format a resume). The problem: they're scattered across hundreds of individual GitHub repos, half-documented, and impossible to search in one place.

This repo fixes that. Every skill-bearing repo in the ecosystem, pulled together, deduplicated, categorized, and made greppable in one file. Whether you're a student who just discovered agent skills exist, or a staff engineer wiring up a fleet of subagents in production β€” the same catalog works for you.

What's inside

KindCountWhereWhat it is
🧩 Agent Skills18,681library/Full SKILL.md bundles (+ scripts, templates, references)
πŸ€– Subagents2,888agents/Specialized agent role definitions
⚑ Slash Commands2,773commands//command shortcuts
πŸ’¬ Prompts10,074prompts/System prompts, prompt corpora, leaked prompts
πŸ“ Rules1,386rules/CLAUDE.md / AGENTS.md / .cursorrules exemplars
πŸ“– Reference543reference/Awesome-lists, cheatsheets, handbooks (verbatim)

πŸš€ Quick start

git clone https://github.com/thedixitjain/the-mega-skill-library.git

Pick the path that matches how much you already know:

πŸŽ“ New to agent skills? β€” one command, zero config

Copy the router skill. It searches the other 35,801 assets for you β€” nothing else loads into context or slows your agent down.

cp -r the-mega-skill-library/master-skill ~/.claude/skills/master-skill-library

Now just talk to Claude Code normally. When a task matches something in the library, it finds the right skill and uses it automatically. That's it β€” you're done.

πŸ’Ό Know exactly what you want? β€” install specific skills

Claude Code reads every installed skill's frontmatter at startup, so only install what you'll actually use β€” dozens, not thousands.

cp -r the-mega-skill-library/library/engineering-core/tdd-guide ~/.claude/skills/

Project-only instead of global? Copy into <project>/.claude/skills/ instead of ~/.claude/skills/.

⌨️ Power user? β€” grep it, script it, pipe it
grep -i "pdf" CATALOG.tsv
awk -F'\t' '$2=="security-and-compliance" && $1=="skill"' CATALOG.tsv
grep -i "code review" CATALOG.tsv | awk -F'\t' '$1=="agent"' | cut -f3,6

CATALOG.tsv is one row per asset: kind Β· category Β· name Β· path Β· source_repo Β· description.

πŸ› οΈ Using Cursor, Codex, Copilot, or something else?

Most files here are plain Markdown with YAML frontmatter β€” portable by design. library/ bundles follow the Agent Skills spec (works with any harness that supports it); rules/ files map directly to .cursorrules / AGENTS.md / custom instructions; prompts/ and commands/ are copy-paste text you can drop into any system-prompt or slash-command config.

πŸ—‚οΈ Browse by category

22 categories, auto-sorted by asset count. Click through for the full browsable table of every skill/agent/command/prompt in that category.

CategoryAssetsCovers
πŸ“¦ General purpose5,575Uncategorized / cross-cutting
πŸ€– AI agents & harness4,583Agent design, orchestration, subagents, context engineering
πŸ’¬ Prompt engineering2,868Prompt techniques, system prompts, optimizers, persona design
βš™οΈ Engineering core2,805Refactoring, debugging, review, architecture, git, TDD
πŸ”¬ Research & academic2,483Literature review, papers, journals, grants, regulatory science
☁️ DevOps & infra1,605Docker, K8s, Terraform, CI/CD, cloud, observability, SRE
πŸ”’ Security & compliance1,604AppSec, pentest, OSINT, threat modeling, SOC2/ISO/GDPR
πŸ“£ Marketing & growth1,584SEO/AEO, ads, CRO, social, campaigns, growth loops
πŸ—„οΈ Backend & data1,583APIs, databases, schemas, queues, caching, pipelines
πŸ”Œ MCP & integrations1,524MCP servers/clients, third-party integrations, browser automation
πŸ§ͺ Testing & QA1,506Test generation, E2E, coverage, QA process, browser testing
🎨 Frontend & design1,359UI/UX, design systems, CSS, React, accessibility
✍️ Writing & content1,345Copywriting, editing, humanizing, translation, narrative
πŸ“ Docs & knowledge mgmt1,158Documentation, ADRs, technical writing, note systems
πŸ’Ό Business & finance1,152Finance, pricing, legal, sales, HR, exec advisory
🎬 Media & creative778Video, image, slides/PPTX, audio, game dev, generative art
πŸ“Š Data science & ML722ML/DL, training, fine-tuning, evaluation, statistics
πŸ“‹ Product & PM473PRDs, roadmaps, user stories, discovery, analytics
πŸ“± Mobile & platform398iOS/Android/Flutter, desktop, extensions, BI platforms
⚑ Productivity & workflow353Planning, automation, meetings, scaffolds, coaching
πŸ“š RAG, memory & knowledge333RAG, vector search, embeddings, agent memory, knowledge graphs
🧩 Skill authoring meta11Creating, testing, auditing and improving skills themselves

Full index with descriptions and navigation: INDEX.md

πŸ“ Repo layout

the-mega-skill-library/
β”œβ”€β”€ INDEX.md                 master index β€” start here
β”œβ”€β”€ CATALOG.tsv               one row per asset β€” grep/awk this
β”œβ”€β”€ master-skill/SKILL.md     router skill β€” install this one, it finds the rest
β”œβ”€β”€ library/<category>/<slug>/SKILL.md    18,681 Agent Skills (+ bundled resources)
β”œβ”€β”€ agents/<category>/<slug>.md           2,888 subagent definitions
β”œβ”€β”€ commands/<category>/<slug>.md         2,773 slash commands
β”œβ”€β”€ prompts/<category>/<slug>.md          10,074 system prompts / corpora
β”œβ”€β”€ rules/<category>/<slug>.md            1,386 CLAUDE.md / AGENTS.md / .cursorrules
β”œβ”€β”€ reference/<owner~repo>/...            543 awesome-lists, cheatsheets, handbooks
β”œβ”€β”€ _index/<category>.md      per-category browsable tables
└── _logs/                    harvest run logs

The raw upstream git clones used to build this (_sources/, ~9 GB, 186 repos) aren't part of this repository β€” only the curated, deduplicated output above is published. See Refreshing below.

πŸ”Ž Provenance, credits & licensing

This is a curated aggregation, not original work. Every skill, agent, command, prompt and rules file was written by its original author β€” full attribution for all 237 source repositories lives in CREDITS.md, linked directly to each one's GitHub page.

Every single harvested file also carries source_repo, source_path and source_url in its own frontmatter, plus a human-readable Source footer linking upstream β€” open any file to see exactly where it came from. Duplicates across repos were collapsed by content hash, keeping the most authoritative copy (official vendor repos first, then by star count); collapsed copies are listed in each file's "Also appears in" footer, so nothing is silently lost.

This repo's own layer β€” the categorization, indexing, catalog, router skill, and documentation β€” is MIT licensed. The 35,802 harvested files themselves come from 186 different repositories (plus 51 more kept as reference material) under their own original licenses β€” check the upstream repo (linked in every file's footer, and in CREDITS.md) before redistributing or using an individual file commercially.

πŸ”„ Refreshing / regenerating

The curated buckets here (library/, agents/, commands/, prompts/, rules/, reference/, _index/, CATALOG.tsv) were generated once from local clones of all 186 source repos. To regenerate: re-clone each repo listed in CATALOG.tsv / _index/by-source-repo.md, then re-run a categorize β†’ dedup-by-hash β†’ catalog pipeline against them. See CONTRIBUTING.md if you want to help formalize that pipeline into a script others can run.

🀝 Contributing

Found a skill-bearing repo that isn't here yet? Found a broken path or a duplicate that should've been collapsed? PRs and issues are very welcome β€” see CONTRIBUTING.md for the frontmatter convention and how to add an entry to CATALOG.tsv.

❓ FAQ

What's the difference between a "skill", "agent", "command", "prompt" and "rule"?
  • Skill β€” a full SKILL.md bundle (+ optional scripts/templates) an agent loads on demand for one task.
  • Agent / subagent β€” a role definition (persona + tools + instructions) spawned to handle a sub-task.
  • Command β€” a /slash-command shortcut that expands to a fixed prompt or workflow.
  • Prompt β€” a standalone system prompt or prompt corpus, not packaged as a skill.
  • Rule β€” a CLAUDE.md / AGENTS.md / .cursorrules style always-on instruction file.
Will installing the router skill slow down my agent or eat my context window?

No. The router (master-skill/) is the only thing that ever loads, and it's one small file. It searches CATALOG.tsv on demand and reads just the one or two matching files per task β€” the other 35,800 assets sit untouched on disk.

Can I use this commercially?

The curation layer is MIT. Individual harvested files retain their original upstream license β€” check the source before commercial use of a specific file. See Provenance & licensing.

My favorite skill repo isn't in here β€” why?

Either it hasn't been discovered yet, or it didn't fit the harvest criteria (skill-shaped content: SKILL.md, subagent defs, slash commands, system prompts, or rules files). Open a PR β€” see Contributing.

⭐ Support

If this saved you time, star the repo β€” it's the main way other people find it. Issues, PRs, and "hey you should add X" suggestions are all welcome.

agent-skills
ai-agents
awesome-list
claude
claude-code
cursor
developer-tools
llm
productivity
prompt-engineering

Contributors

thedixitjain

4 commits

Languages

Python

75.9%

JavaScript

7.5%

Shell

5.4%

TypeScript

3.3%

HTML

2.3%

Go Template

1.6%