mcpbeat Sign in

Claude Skills

The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.

Every Agent Skill we could find on GitHub, deduplicated by content. 80 149 files from 1 774 authors, of which 62 489 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.

62 489
unique skills
out of 80 149 files found on GitHub
17 660
are copies
same content, someone else's repository
1 741
tokens, median
what a typical skill costs you in context
7 984
name collisions
two skills with one name cannot sit side by side

31 861–31 920 of 62 489

page 532 of 1 042
Gsd Audit Uat
by coco-research

Cross-phase audit of all outstanding UAT and verification items

154 tokens
Gsd Audit Milestone
by coco-research

Audit milestone completion against original intent before archiving

307 tokens
Gsd Cleanup
by coco-research

Archive accumulated phase directories from completed milestones

162 tokens
Gsd Autonomous
by coco-research

Run all remaining phases autonomously — discuss→plan→execute per phase

479 tokens
Gsd Check Todos
by coco-research

List pending todos and select one to work on

314 tokens
Gsd Code Review Fix
by coco-research

Auto-fix issues found by code review in REVIEW.md. Spawns fixer agent, commits each fix atomically, produces REVIEW-FIX.md summary.

536 tokens
Gsd Code Review
by coco-research

Review source files changed during a phase for bugs, security issues, and code quality problems

620 tokens
Gsd Complete Milestone
by coco-research

Archive completed milestone and prepare for next version

1k tokens
Gsd Discuss Phase
by coco-research

Gather phase context through adaptive questioning before planning. Use --auto to skip interactive questions (Claude picks recommended defaults). Use --chain for interactive discuss followed by automatic plan+execute. Use --power for bulk question generation into a file-based UI (answer at your own pace).

802 tokens
Gsd Debug
by coco-research

Systematic debugging with persistent state across context resets

1k tokens
Gsd Do
by coco-research

Route freeform text to the right GSD command automatically

222 tokens
Gsd Execute Phase
by coco-research

Execute all plans in a phase with wave-based parallelization

747 tokens
Gsd Docs Update
by coco-research

Generate or update project documentation verified against the codebase

565 tokens
Gsd Fast
by coco-research

Execute a trivial task inline — no subagents, no planning overhead

226 tokens
Gsd Explore
by coco-research

Socratic ideation and idea routing — think through ideas before committing to plans

197 tokens
Gsd Forensics
by coco-research

Post-mortem investigation for failed GSD workflows — analyzes git history, artifacts, and state to diagnose what went wrong

593 tokens
Gsd Health
by coco-research

Diagnose planning directory health and optionally repair issues

161 tokens
Gsd Help
by coco-research

Show available GSD commands and usage guide

157 tokens
Gsd Intel
by coco-research

Query, inspect, or refresh codebase intelligence files in .planning/intel/

1k tokens
Gsd Import
by coco-research

Ingest external plans with conflict detection against project decisions before writing anything.

222 tokens
Gsd Insert Phase
by coco-research

Insert urgent work as decimal phase (e.g., 72.1) between existing phases

271 tokens
Gsd Join Discord
by coco-research

Join the GSD Discord community

99 tokens
Gsd List Phase Assumptions
by coco-research

Surface Claude's assumptions about a phase approach before planning

366 tokens
Gsd List Workspaces
by coco-research

List active GSD workspaces and their status

153 tokens
Gsd Manager
by coco-research

Interactive command center for managing multiple phases from one terminal

391 tokens
Gsd Map Codebase
by coco-research

Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents

649 tokens
Gsd Milestone Summary
by coco-research

Generate a comprehensive project summary from milestone artifacts for team onboarding and review

482 tokens
Gsd New Project
by coco-research

Initialize a new project with deep context gathering and PROJECT.md

420 tokens
Gsd New Milestone
by coco-research

Start a new milestone cycle — update PROJECT.md and route to requirements

434 tokens
Gsd New Workspace
by coco-research

Create an isolated workspace with repo copies and independent .planning/

451 tokens
Gsd Next
by coco-research

Automatically advance to the next logical step in the GSD workflow

199 tokens
Gsd Note
by coco-research

Zero-friction idea capture. Append, list, or promote notes to todos.

236 tokens
Gsd Pause Work
by coco-research

Create context handoff when pausing work mid-phase

261 tokens
Gsd Plan Milestone Gaps
by coco-research

Create phases to close all gaps identified by milestone audit

262 tokens
Gsd Plant Seed
by coco-research

Capture a forward-looking idea with trigger conditions — surfaces automatically at the right milestone

217 tokens
Gsd Pr Branch
by coco-research

Create a clean PR branch by filtering out .planning/ commits — ready for code review

194 tokens
Gsd Plan Phase
by coco-research

Create detailed phase plan (PLAN.md) with verification loop

574 tokens
Gsd Profile User
by coco-research

Generate developer behavioral profile and create Claude-discoverable artifacts

405 tokens
Gsd Progress
by coco-research

Check project progress, show context, and route to next action (execute or plan)

182 tokens
Gsd Quick
by coco-research

Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents

506 tokens
Gsd Reapply Patches
by coco-research

Reapply local modifications after a GSD update

3k tokens
Gsd Remove Phase
by coco-research

Remove a future phase from roadmap and renumber subsequent phases

249 tokens
Gsd Remove Workspace
by coco-research

Remove a GSD workspace and clean up worktrees

193 tokens
Gsd Research Phase
by coco-research

Research how to implement a phase (standalone - usually use /gsd-plan-phase instead)

1k tokens
Gsd Review
by coco-research

Request cross-AI peer review of phase plans from external AI CLIs

293 tokens
Gsd Resume Work
by coco-research

Resume work from previous session with full context restoration

286 tokens
Gsd Review Backlog
by coco-research

Review and promote backlog items to active milestone

488 tokens
Gsd Scan
by coco-research

Rapid codebase assessment — lightweight alternative to /gsd-map-codebase

185 tokens
Gsd Secure Phase
by coco-research

Retroactively verify threat mitigations for a completed phase

210 tokens
Gsd Set Profile
by coco-research

Switch model profile for GSD agents (quality/balanced/budget/inherit)

93 tokens
Gsd Settings
by coco-research

Configure GSD workflow toggles and model profile

253 tokens
Gsd Session Report
by coco-research

Generate a session report with token usage estimates, work summary, and outcomes

151 tokens
Gsd Ship
by coco-research

Create PR, run review, and prepare for merge after verification passes

174 tokens
Gsd Stats
by coco-research

Display project statistics — phases, plans, requirements, git metrics, and timeline

136 tokens
Gsd Thread
by coco-research

Manage persistent context threads for cross-session work

765 tokens
Gsd UI Phase
by coco-research

Generate UI design contract (UI-SPEC.md) for frontend phases

206 tokens
Gsd UI Review
by coco-research

Retroactive 6-pillar visual audit of implemented frontend code

191 tokens
Gsd Validate Phase
by coco-research

Retroactively audit and fill Nyquist validation gaps for a completed phase

220 tokens
Gsd Update
by coco-research

Update GSD to latest version with changelog display

241 tokens
Gsd Undo
by coco-research

Safe git revert. Roll back phase or plan commits using the phase manifest with dependency checks.

248 tokens

Claude Skills — questions

Answers built from the skills we actually parsed.

What is a Claude Skill?
A folder with a SKILL.md file: instructions that teach an agent to do one thing well, optionally with scripts and reference files alongside. The format is open and called Agent Skills — Claude Code, Codex and other agents read the same files. It is not a program you run; it is knowledge the agent loads when the task calls for it.
How is a skill different from an MCP server?
A server gives the agent new abilities — it connects to something and exposes tools. A skill gives the agent knowledge: how to use what it already has. They combine, and often literally: 11 696 of the skills here declare which MCP servers they need to work.
Why are there fewer skills here than in other catalogues?
Because we deduplicate by content. Of 80 149 files found on GitHub, 62 489 are unique — the rest is the same skill copied into someone else's repository, word for word. Catalogues that count files rather than skills show every copy as a separate entry.
What does the token count mean?
A skill is loaded into the model's context when it is used, so its size is a running cost on every request that touches it. We measure the whole folder, not just SKILL.md: one official skill is 377 tokens, another drags 83 files of fonts behind it.
How do I install a skill?
Copy the skill folder into ~/.claude/skills for personal use, or into .claude/skills inside a project. The agent picks it up by the name in the SKILL.md header — which is worth checking: 7 984 skills here share a name with another skill, and two of them cannot sit side by side.