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

34 741–34 800 of 62 489

page 580 of 1 042
Finishing A Development Branch
by arbiterForge

The terminal step of /feature and /sprint. Routed to once commit-gate has cleared, to decide the branch's fate — merge via PR, open a PR, or discard. Direct merge to the default branch is forbidden; every change lands through a PR. Under /sprint the skill auto-selects "open PR" and surfaces the merge decision to the user.

2k tokens
Post Merge Cleanup
by arbiterForge

Finish an already-merged branch. Proves the branch is an ancestor of the fetched default, classifies leftover artifacts as unique / redundant / superseded, returns to a clean --ff-only default checkout, and deletes the merged local branch — every discard confirmed per item. Routed to by $ca-cleanup.

2k tokens
Release
by arbiterForge

The single permitted path to a version tag, for any target declared in the project's .codearbiter/release-targets.md. Routed to when the user invokes /release on a non-default branch with a green suite. Takes the declared target as its one argument, derives the SemVer bump from Conventional-Commits history since that target's last tag, rolls the commits into that target's CHANGELOG, writes an annotated tag in that target's namespace, and on authorization publishes it as a GitHub Release with the changelog section as its notes. A release commit, if needed, routes through commit-gate; the tag and Release are never published without explicit authorization.

18k tokens
Secret Handling
by arbiterForge

The secret-source gate. Routed to when changed code reads, writes, or passes a secret — API key, token, password, connection string, signing key, certificate, or any value that grants access. Validates that every secret comes from the approved store and never lands in source, log, test fixture, error response, image, or LLM prompt. The auth-crypto-reviewer agent is dispatched as the reviewer.

1k tokens
Security Architecture
by arbiterForge

Optional, opt-in STRIDE threat pass for a sensitive feature — invoked deliberately via /threat-model, never forced on ordinary changes. Walks the change's attack surface and security boundaries (governed by <project-root>/.codearbiter/security-controls.md), surfaces threats and unmitigated gaps, and MAY dispatch security-reviewer or auth-crypto-reviewer. Not a routine gate; it can hard-STOP only on a genuinely critical unmitigated threat it surfaces.

1k tokens
Skill Author
by arbiterForge

The authoring gate for new skills. Routed to when the user invokes /new-skill "<gap>". Five gated phases — gap evidence, scope, authoring, self-review against the v2 house style, routing integration. A new skill is not written until an existing one is proven not to cover the gap, and not shipped until it carries gated phases, hard rules, and a routing entry. Every authored skill matches the v2 format (frontmatter name+description, # name, Pre-flight, Phase N · gate, Hard rules).

3k tokens
Subagent Driven Development
by arbiterForge

The implementation engine. Routed to by /sprint (full plan, autonomous) and by executing-plans (scoped batch, checkpoint-gated). One fresh subagent per task — test-first via tdd — followed by spec-compliance review, quality review, and fresh-run verification. No single context accumulates drift, and nothing is accepted on a subagent's word.

5k tokens
Tdd
by arbiterForge

The test-first gate. Routed to by /feature (after the spec is approved), /fix, and /refactor before any implementation code is written. Six gated phases — obligation scan, red, green, obligation verify, coverage, lint. No feature code exists before Phase 1 clears; nothing reaches commit-gate until all six are green.

2k tokens
Tribunal
by arbiterForge

The deep, rarely-convened whole-codebase audit lane. Routed to when the user invokes $ca-tribunal. Seven gated phases — cost/model, map, roster dispatch, triage, report, approval+filing, telemetry. Costs on the order of millions of tokens; proceeds only after the user acknowledges the estimate; never a required gate; nothing filed or sent without explicit authorization.

13k tokens
Using Git Worktrees
by arbiterForge

OPTIONAL per-task isolation for autonomous parallel work. Routed to only on explicit opt-in by subagent-driven-development or dispatching-parallel-agents, so parallel units mutate files without colliding. Stands up one worktree per unit, works it in isolation, then integrates each unit back onto the caller's working branch for the caller's single commit-gate + finishing-a-development-branch exit. Never on the default path; it does not bypass a gate or finish per unit.

1k tokens
Writing Plans
by arbiterForge

The spec-to-plan bridge. Routed to by /feature once the brainstormed spec is approved, and by /sprint before execution. Decomposes the spec into 2–5 minute tasks, each carrying its exact file path(s) and a concrete verification step that maps to a tdd obligation. Writes the plan to .codearbiter/plans/<slug>.md, ordered with dependencies flagged and an MVP slice identifiable. Nothing executes until every task has a path and a verification and the task set covers every acceptance criterion.

3k tokens
Ca Add Dep
by arbiterForge

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

1k tokens
Ca Adr Status
by arbiterForge

Report the health of Architecture Decision Records — aged, unchallenged, supersession candidates, unresolved CONFIRM-NN. Read-only.

311 tokens
Ca Arbiter
by arbiterForge

Exit maintainer dev mode — restore orchestration, remove the dev marker, log the exit.

429 tokens
Ca Adr
by arbiterForge

Author a numbered, dated, user-attributed Architecture Decision Record under .codearbiter/decisions/.

339 tokens
Ca Audit
by arbiterForge

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.

700 tokens
Ca Btw
by arbiterForge

Lightweight Q&A about the project — answer from context and return, no routing, no state change.

246 tokens
Ca Checkpoint
by arbiterForge

Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.

656 tokens
Ca Chore
by arbiterForge

Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.

766 tokens
Ca Commands
by arbiterForge

Show the codeArbiter command catalog — the public command list and what each routes to.

183 tokens
Ca Cleanup
by arbiterForge

Finish an already-merged branch — classify the leftover artifacts, return to a fast-forwarded default checkout, and delete the merged local branch. Every discard confirmed per item; ancestry proven, never assumed.

639 tokens
Ca Context Check
by arbiterForge

Optional manual drift audit — report stale provenance-tracked docs, then per stale doc offer re-scout, re-baseline, or defer. Not the daily loop; commit-gate auto-heal owns routine maintenance.

344 tokens
Ca Commit
by arbiterForge

Run the full commit gate — the only sanctioned path to a git commit.

247 tokens
Ca Conflict
by arbiterForge

Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.

578 tokens
Ca Create Context
by arbiterForge

Brownfield back-fill — scout an existing codebase and populate .codearbiter/, then lock it initialized.

437 tokens
Ca Debug
by arbiterForge

Investigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to $ca-fix, $ca-adr, or a no-action close.

569 tokens
Ca Decompose
by arbiterForge

Greenfield decomposition interview — a layered interview that populates .codearbiter/ and locks it initialized.

434 tokens
Ca Doctor
by arbiterForge

Verify the active host install, package, command ownership, enforcement, and harmless live-fire probe. Read-only.

338 tokens
Ca Dev
by arbiterForge

Maintainer override — suspend orchestration to edit codeArbiter itself. Env-gated (CODEARBITER_DEV=1), entry/exit logged to overrides.log.

466 tokens
Ca Feature
by arbiterForge

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.

1k tokens
Ca Init
by arbiterForge

Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

711 tokens
Ca Fix
by arbiterForge

Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.

496 tokens
Ca New Skill
by arbiterForge

Author a new codeArbiter skill: prove the gap is real, get the spec approved, then write it.

409 tokens
Ca Metrics
by arbiterForge

Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.

960 tokens
Ca Override
by arbiterForge

Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.

908 tokens
Ca Preview
by arbiterForge

Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.

1k tokens
Ca Pr
by arbiterForge

Open a pull request the only sanctioned way — clear every BLOCK-level review finding, then stage the PR. Never a direct write to the default branch.

850 tokens
Ca Reconcile
by arbiterForge

SMARTS arbitration — reconcile architectural artifacts against the scaffold and prior decisions; every variance resolved by an explicit, user-attributed choice.

708 tokens
Ca Release
by arbiterForge

Cut a release the only sanctioned way — SemVer bump from the commit log, a CHANGELOG section, an annotated tag. Takes the declared target's name as its only argument. The only path to a version tag.

909 tokens
Ca Refactor
by arbiterForge

Restructure code with behavioral parity proven through unmodified pre-existing tests, then refactor. No behavior change.

572 tokens
Ca Spike
by arbiterForge

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or $ca-feature.

548 tokens
Ca Review
by arbiterForge

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.

1k tokens
Ca Sprint
by arbiterForge

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.

560 tokens
Ca Standup
by arbiterForge

Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.

1k tokens
Ca Status
by arbiterForge

Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.

520 tokens
Ca Task
by arbiterForge

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

898 tokens
Ca Threat Model
by arbiterForge

Opt-in lightweight STRIDE pass for a sensitive feature before implementation. Not a routine gate — invoke it when a change warrants security thought.

425 tokens
Ca Tribunal
by arbiterForge

Deep, rarely-convened whole-codebase audit — eleven specialist lenses, a resumable on-disk audit log, findings filed as GitHub issues on approval. Expensive; estimates cost and STOPs before running. Never a required gate.

759 tokens
Ca Watch
by arbiterForge

Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.

892 tokens
Brainstorming
by arbiterForge

The Socratic spec-refinement front of /feature, and the planning front of /sprint. Routed to BEFORE any code — it takes a one-line idea and drives it to an approved, concrete spec with testable acceptance criteria. Four gated phases — frame, refine, write, approve. No implementation and no handoff to tdd until the spec is on disk and approved; each acceptance criterion becomes one tdd Phase 1 obligation.

2k tokens
Commit Gate
by arbiterForge

The only path to a commit. Routed to when the user invokes /commit or otherwise instructs codeArbiter to persist staged changes. Nine gated phases — permission, branch, classification, verification (test/lint/secrets), behavioral proof, diff review, selective stage, message, commit. Nothing reaches version control without clearing every gate; "it looks good" is not authorization.

4k tokens
Context Check
by arbiterForge

Optional manual drift audit — report stale provenance-tracked docs (via _provenancelib drift detection across .codearbiter/.provenance/), then per stale doc offer re-scout / re-baseline / defer. Not the daily loop; commit-gate auto-heal owns routine maintenance.

877 tokens
Context Creation
by arbiterForge

The brownfield back-fill. Routed to by /create-context, and by startup when .codearbiter/CONTEXT.md lacks the <!--INITIALIZED--> body marker but source code exists. Six gated phases — pre-flight, scout dispatch, synthesis, gap interview, write, lock. Reads the existing codebase through parallel scouts, drafts every surviving project-state doc, resolves gaps with the user, and locks the project as initialized.

4k tokens
Debug
by arbiterForge

Investigate-then-decide root-cause analysis for a defect whose cause is unknown (distinct from /fix, which assumes a known bug). Five gated phases: capture, hypothesize, gather, decide, hand off. Investigation only, no code changes; exits to /fix, /adr, or a no-action close.

2k tokens
Crypto Compliance
by arbiterForge

The banned-primitive gate. Routed to when changed code hashes, signs, encrypts, derives keys, generates security-relevant randomness, configures TLS, or imports a crypto library. Rejects broken primitives, disabled TLS verification, and home-rolled crypto; the approved-primitive list lives in security-controls.md. The auth-crypto-reviewer agent is dispatched as the reviewer.

790 tokens
Decompose
by arbiterForge

The greenfield decomposition interview. Routed to at startup when .codearbiter/CONTEXT.md lacks the <!--INITIALIZED--> body marker and no source code exists, or when the user invokes /decompose. A senior-architect persona drives a six-layer interview, persists every layer to disk so a context reset loses nothing, then populates .codearbiter/ and locks it initialized. No project-state doc is written before the layers are solid; orchestration does not resume until the lock is set.

5k tokens
Dispatching Parallel Agents
by arbiterForge

The parallel fan-out primitive. Routed to by any skill or command that splits work across independent units and dispatches an agent per unit — subagent-driven-development, /sprint, parallel /review. It owns the dispatch/collect/funnel discipline: bound concurrency, isolate units, collect every result, dedupe overlap, and funnel through finding-triage then checkpoint-aggregator. Raw agent output is never consumed before the funnel runs; an agent that errors drops its unit without corrupting the batch.

2k tokens
Decision Variance
by arbiterForge

Reconcile the project's architectural artifacts against the scaffold and prior decisions, then present each variance as a SMARTS analysis for the user to decide. Routed to when the user asks to arbitrate, reconcile, or consolidate architectural context, requests a variance report, mentions ADR conflicts, or asks which downstream artifacts the current state supports. Never decides alone — every arbitration is user-attributed and logged.

2k tokens
Decision Lifecycle
by arbiterForge

Author and track Architecture Decision Records. Routed to when the user invokes /adr to record a new decision or /adr-status to list ADR health. Authors numbered, dated, user-attributed ADRs under .codearbiter/decisions/, maintains supersede chains, and reports status read-only. Never authors an ADR as its own judgment — every ADR carries explicit user attribution.

3k tokens
Finishing A Development Branch
by arbiterForge

The terminal step of /feature and /sprint. Routed to once commit-gate has cleared, to decide the branch's fate — merge via PR, open a PR, or discard. Direct merge to the default branch is forbidden; every change lands through a PR. Under /sprint the skill auto-selects "open PR" and surfaces the merge decision to the user.

2k 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.