341 tagged claude-code-skill, measured the same way as everything else here.
Browse within: claude-code-skills 46claude-ai 37claude-code-plugins 33claude-code-hooks 26claude-code-commands 21claude-plugin 19claude-code-marketplace 13agent-skill 12claude-skill 12ecosystem-audit 10skill-creator 10agentic-skill 9open-source 9prompt 9
snowmead/questionably-ultrathink
Plugin Claude Code
Bundles 1 skill · 102 tokens together
Advanced reasoning plugin integrating Chain of Verification (CoVe) and Atom of Thoughts (AoT) frameworks for rigorous, verifiable analysis.
snowmead/questionably-ultrathink
Plugin Claude Code
Bundles 1 skill, 3 commands, 6 agents, 2 MCP servers · 895 tokens together
Advanced reasoning plugin integrating Chain of Verification (CoVe) and Atom of Thoughts (AoT) frameworks for rigorous, verifiable analysis.
Plugin Claude Code
Bundles 1 skill · 290 tokens together
Turn your solo Claude Code conversation into a turn-based group discussion with codex / gemini / other CLI agents — you stay in as a participant, not a report reader.
Plugin Claude Code
Bundles 1 skill · 85 tokens together
Legacy project onboarding for Claude Code — analyzes the codebase, generates a token-budgeted CLAUDE.md, wires 4 guard hooks, manages forbidden zones, and aligns CI with local commands. Default --local-only writes zero PROJECT files (no team pollution). Use when setting up Claude Code on a legacy project, configuring.
Plugin Claude Code
Bundles 2 skills · 172 tokens together
Makes a website start in the visitor's own theme and language, with no flash and no forced redirects.
Plugin Claude Code
Bundles 3 skills · 234 tokens together
Unity / C# performance optimization and code standards skill library. Three skills: performance optimization, zero-GC engineering plans, and code standards & review.
Plugin Claude Code
Bundles 1 skill, 3 hooks · 85 tokens together
Verifies test-count claims against what your suite actually did, before a commit lands. Supports pytest, vitest and jest. If the message makes no claim, it does nothing.
Plugin Claude Code
Bundles 2 skills, 1 hook · 204 tokens together
Forces the agent to answer in numbered steps you can execute: a one-sentence verdict, the exact commands, and a separate list of what is missing.
Plugin Claude Code
Bundles 1 skill, 8 commands, 6 agents · 609 tokens together
Generic plan-orchestration pipeline for Claude Code — walks any structured plan file to completion via scout/executer/verifier subagents with state persistence and per-Part review checkpoints.
Plugin Claude Code
Bundles 1 skill · 115 tokens together
Safely free up disk space on macOS. Scans caches, developer & AI-model caches, Trash, Xcode build data, Docker, and leftover data from uninstalled apps, then deletes only what you approve.
joey114132/fable-workflow-skill
Plugin Claude Code
Bundles 1 skill, 2 hooks · 162 tokens together
Fable-style agentic working method for any model — surface the unknowns before building on vague specs or unfamiliar code (blind-spot pass, interview, variants, log assumptions, stay in the loop).
Plugin Claude Code
Bundles 2 skills, 2 commands · 156 tokens together
Cover images and in-article illustrations. Imagen direct adapter and Grok or Codex engine hints.
Plugin Claude Code
Plugin marketplace listing 1 plugin: writing-readme.
chardigio/nord-electro-6-skill
Plugin Claude Code
Bundles 1 skill · 86 tokens together
Manage program presets on a Nord Electro 6 keyboard over USB.
Plugin Claude Code
Bundles 1 skill · 200 tokens together
Send a rendered one-tap note or open a temporary two-way Slip with a human.
GuillaumeLessard/qector-claude-plugin
Plugin Claude Code
QECTOR quantum error correction toolkit for Claude Code and Claude Desktop.
GuillaumeLessard/qector-claude-plugin
Plugin Claude Code
Bundles 28 skills, 11 commands, 5 agents, 2 hooks, 2 MCP servers · 3,569 tokens together
Local QECTOR quantum error correction plugin for Claude Code and Claude Desktop with strict math skills, focused agents, and qector-decoder-v3 MCP servers.
Plugin Claude Code
Bundles 1 skill · 141 tokens together
Orquestador multi-agente que, a partir de un prompt, corre el loop plan → code → QA → review → iterar sobre un gateway local OpenAI-compatible (OmniRoute). Sirve para proyectos de software de cualquier tipo (frontend, backend, CLIs, scripts, librerías, config); el QA visual con la skill websight es OPCIONAL y lo…
PiotrLason/video-to-code-skill
Plugin Claude Code
Bundles 3 skills · 136 tokens together
Transforms video content (screen recordings, demos, bug reports) into structured multimodal data — keyframes synced with audio transcription — for AI analysis.
adamyodinsky/interactive-docs-skill
Plugin Claude Code
Bundles 1 skill · 58 tokens together
Generate interactive documentation websites from any codebase. Produces a React + Vite + TypeScript app with 10 cross-linked views: architecture, components, data flows, sequences, ERD, state machines, APIs, dependencies, tech stack, and ADRs.
Plugin Claude Code
Critique-led architecture views and a security/privacy/compliance/cost audit for Claude Code, grounded in real code and git history.
Plugin Claude Code
Bundles 2 skills · 358 tokens together
Critique-led architecture views for Claude Code: a high-altitude, code- and git-grounded system map whose headline output is a findings overlay (hidden coupling, hotspots, SPOFs, performance/efficiency/correctness pains, edge-case risks). Ships a companion /audit skill for security, privacy/compliance, legal, and cost.
Plugin Claude Code
Bundles 2 skills · 246 tokens together
Defense against LLM Rust failure modes: 58 categories of bugs that survive rustc, clippy, and cargo test — async cancellation, unsafe/FFI, concurrency, crypto, supply-chain, tests-that-pass-by-luck, semantic conformance, and systemic performance cost. Ships the rust-intel skill plus /rust-intel:audit, /rust-intel:fix.
Plugin Claude Code
Bundles 1 skill, 3 agents · 394 tokens together
Review every code change before the turn ends: fresh-context reviewer agents, a verified finding standard, honest convergence, and a measured token budget — enforced by a Stop hook, graph-aware when you have a code graph, zero-cost when you don't.