aidentity / index

Agent skills · indexed · verified weekly

The index of agent skills that still work.

Aidentity is a verified index of 526 AI agent skills from 25 sources. Every entry carries its author, its license, and the date it was last checked. Install any of them into Claude Code, OpenCode, Codex, Cursor, Copilot or Gemini CLI with one command.

npx aidentity add code-review

Browse all 526 → Where they come from Source on GitHub

526Skills indexed
507Installable here
25Upstream sources
6Agents supported

Why an index, and not another list

01

Links rot. Quietly.

Most skill collections are a markdown file that was accurate once. Every source here is re-checked weekly by CI, and the date is printed on the page. If a source dies, it gets flagged, not ignored.

02

Licenses are invisible until they aren't.

Each entry states its license and author. Content we can't redistribute is indexed but not hosted — clearly marked. That is the difference between a useful index and a takedown notice.

03

Every agent invents its own folder.

One skill ID installs into six different agents. You shouldn't have to learn each tool's directory layout, or re-copy files when you switch editors.

Start here

All 526 skills →
grill-with-docs A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go. mattpocock/skills MIT tdd Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests. mattpocock/skills MIT code-review Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X". mattpocock/skills MIT planning-and-task-breakdown Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. addyosmani/agent-skills MIT debugging-and-error-recovery Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing. addyosmani/agent-skills MIT security-and-hardening Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services. Use when personal data or privacy compliance (GDPR, CCPA) is involved. addyosmani/agent-skills MIT

By category

Filter the full index →
cloud 110 skills azure 61 skills corporate 43 skills mobile 23 skills project-management 20 skills engineering 19 skills design 17 skills ads 16 skills growth 16 skills copywriting 12 skills film 12 skills finance 12 skills music 12 skills planning 12 skills quant 12 skills docs 11 skills context 10 skills security 9 skills testing 9 skills agents 8 skills analytics 6 skills git 6 skills sales 6 skills code-review 5 skills cro 5 skills quality 5 skills seo 5 skills architecture 4 skills frontend 4 skills media 4 skills api 3 skills debugging 3 skills email 3 skills pricing 3 skills social 3 skills database 2 skills developer-tools 2 skills devops 2 skills education 2 skills motion 2 skills legal 1 skill memory 1 skill migration 1 skill people 1 skill performance 1 skill tooling 1 skill video 1 skill

Sources

Full provenance →
RepositoryAuthorLicenseSkills
google/skills Google LLC Apache-2.0 127
microsoft/skills Microsoft Corporation MIT 61
OpenSenseNova/SenseNova-Skills OpenSenseNova MIT 59
coreyhaines31/marketingskills Corey Haines MIT 52
mattpocock/skills Matt Pocock MIT 37
addyosmani/agent-skills Addy Osmani MIT 25
expo/skills Expo (650 Industries) MIT 23
anthropics/skills Anthropic, PBC Proprietary 19
abrahamFerga/scrum-skills abrahamFerga MIT 17
obra/superpowers Jesse Vincent MIT 14
agentii-ai/agentii-investment-intelligence agentii-ai Apache-2.0 12
agiprolabs/claude-trading-skills agiprolabs MIT 12
jtydhr88/lyric-writing-skills jtydhr88 MIT 12
jtydhr88/screenwriting-skills jtydhr88 MIT 12
affaan-m/everything-claude-code Affaan Mustafa MIT 10
JuliusBrussee/caveman Julius Brussee Apache-2.0 8
trailofbits/skills Trail of Bits CC-BY-SA-4.0 7
nextlevelbuilder/ui-ux-pro-max-skill Next Level Builder MIT 6
emmapbingham/agentic-newsroom emmapbingham MIT 4
codeswithroh/tastemaker codeswithroh MIT 2
supabase/agent-skills Supabase MIT 2
lukedj78/dev-flow lukedj78 MIT 2
AkshatNaruka/aidentity Aidentity contributors MIT 1
haidrrrry/claude-remotion-skill haidrrrry MIT 1
Agents365-ai/drawio-skill Agents365-ai MIT 1
On the proprietary entries. 19 skills from anthropics/skills are indexed with their metadata and an upstream link, but their content is not hosted here — the upstream license does not permit redistribution. They are marked Proprietary everywhere they appear.

Add a skill

One JSON record, one pull request. If it's accurate and correctly licensed, it ships the same day. No editorial committee, no backlog.

./scripts/check-all.sh

Contributing guide →

Set up with your agent

Copy this prompt into Claude Code, Cursor, Codex or any agent that can fetch a URL. It reads the index, asks what you are building, and installs only what you approve.

AI setup prompt 
Set up my agent with Aidentity.

1. Fetch https://akshatnaruka.github.io/aidentity/llms.txt and read it.
2. Fetch https://akshatnaruka.github.io/aidentity/search.json.
3. Ask me what I am building. Recommend the closest bundle and up to five skills.
4. For each skill I approve, run: npx aidentity add <id>
5. Skip content_url:null and any status other than "stable".
6. Tell me the license before installing. Never install an index-only skill.

Agent setup page →llms.txtagent.json