50,330 tagged Claude Code, measured the same way as everything else here.
Browse within: agentic-ai 337antigravity 270agentic-skills 191ai-workflows 185coding-agents 175agentic-framework 109agentic-workflow 109swarm 109Autonomous Agents 106LLM 103ci 97actions 96cai 96gh-extension 96
Skill Claude CodeCodex
Skill "security-claude" from rahozosman/security-claude, covering security architecture & threat modeling intelligence, how this skill is organized (progressive disclosure), 1. pick a mode, 2. core method (applies to every mode) and 3. doing a focused review.
CarterIrish/code-architecture-skill
Skill Claude CodeCodex
Plans, documents, and reviews code architecture for software projects. Produces structured architecture documents with Mermaid diagrams through a collaborative interview workflow. Triggers on architecture planning, project structuring, folder organization, system design, component design, data flow planning, codebase…
Skill Claude CodeCodex
Idiomatic React — hooks, composition, and clear state boundaries. Use when writing or reviewing React components.
Skill Claude CodeCodex
Delegate bulk LLM work - classifying, extracting, summarising or rewriting many items - to a cheap model via the sidequest CLI, so results go to a file instead of into context. Use when a task involves running the same instruction over tens, hundreds or thousands of items.
Skill Claude Code
Homer L6 — Sleep-time routing weight tuner. Mines Brain's decisions.jsonl + advisorcalls.jsonl, computes tier / model / guardrail distributions, and proposes routingmanifest.toml weight adjustments based on observed data. Aurora PROPOSES; the user decides. No auto-apply. Sacred Rule.
Skill Claude Code
Format standards and an anti-AI-slop reference for writing and editing documents — READMEs, changelogs, commit messages, PR descriptions, release notes, and general prose or docs. Use when drafting or editing any of these, or when asked to make writing clear and honest. Supplies the standard for each document type…
Skill Claude CodeCodex
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code…
Skill Claude Code
A skill that collects recent news from RSS feeds about hackers, artificial intelligence, security, and technology, then categorises and summarises it in Traditional Chinese. RSS is a format websites use to publish updates.
Skill Claude CodeCodex needs its repo
Manage a backchannel room. Start, join, check status, set the share policy, or leave a shared, E2E-encrypted session with another AI coding session. Use when the user asks to start, join, check, or leave a backchannel, or to share context with a teammate's session.
felipeelias/claude-marketplace
Skill Claude Code
This skill should be used when the user asks to "validate the marketplace", "check marketplace sync", "verify plugin manifests", "validate marketplace.json", or mentions marketplace validation or plugin sync issues.
developer239/michals-opencode-cookbook
Skill Claude CodeCodex
TypeScript conventions with generic guidance plus a monorepo-specific addendum.
Skill Claude CodeCodex
Transcribe and translate audio/video files locally using OpenAI Whisper. Use when the user mentions: transcribe, transcription, speech to text, audio to text, translate audio, what does this say, convert speech, subtitle, caption, detect language, whisper, dictation, translate this video, translate this audio, what…
astropham1808/astro-agent-skills
Skill Codex
Run a repository story through two isolated Codex sessions, with one implementer working in a Git worktree and one independent reviewer inspecting the branch, followed by a bounded fix pass, deterministic verification, and a human PR and merge gate. Use when the user explicitly asks for a dual-agent Codex workflow, an…
brackendev/clojurescript-skills
Skill Claude CodeCodex
Use when writing, editing, reviewing, or discussing ClojureScript code that compiles to JavaScript and runs on a JS host (browser, Node.js, or other JS runtime). Triggers: .cljs files, .cljc files compiled to JS, shadow-cljs.edn, figwheel-main.edn, ClojureScript deps.edn projects, cljs.test, JavaScript interop (js/…
Elliotoh-jin/claude-memory-loop
Skill Claude Code
Bootstrap the memory loop into any repo or Obsidian vault. Triggers: (1) "set up the memory loop / second brain / warm layer here" or "install this structure in another repo/vault", (2) a new project asking "make the AI remember across sessions and surfaces".
Skill Claude Code
Run work in an isolated workspace: git worktree + devcontainer, driven through the fr isolation CLI (exec-bridge). Use when feature work must not touch the base repo, when fr-brainstorming or fr-goal needs a workspace, when the operator says "isolate this" / "run it in the container", or to clean up after a merged PR.…
Skill Claude CodeCodex
Use when a new source document has been added to a KB's raw/ folder and needs to be filed into the wiki — read the source, write its summary page, create or update concept and entity pages, update the index and log, and lint.
Skill Claude CodeCodex
The Dependency Auditor is a comprehensive toolkit for analyzing, auditing, and managing dependencies across multi-language software projects. This skill provides deep visibility into your project's dependency ecosystem, enabling teams to identify vulnerabilities, ensure license compliance, optimize dependency trees…
capsrock/reid-miles-design-skill
Skill Claude CodeCodex
A Claude Skill for reproducing Reid Miles' (1927-1993) Blue Note Records typography-led design style in layouts that cannot use large photography (app UI, splash screens, cards, banners, slides). No large portrait photography is used; instead, typographic contrast, flat color blocks, asymmetric composition, and…
jerryzhang1011/waterlooworks-application-plugins
Skill Codex
Apply to WaterlooWorks Full-Cycle Service jobs from a valid WaterlooWorks job ID using the user's logged-in Chrome session. Use when the user asks Codex to apply on WaterlooWorks by job id and provides or can provide both the job ID and the resume/application document label to use. Handles recoverable WaterlooWorks…
jleonceo/skill-adherencia-reglas
Skill Claude Code
Mide qué fracción de las reglas propias del proyecto se cumple de verdad, contándolo sobre el historial de sesiones que Claude Code ya guarda en disco. Se activa al preguntar si una norma, protocolo o convención se está aplicando, al revisar si un CLAUDE.md sirve de algo, al decidir si una regla debe pasar a ser hook…
Skill Claude CodeCodex
Standing session rules that must be loaded at the start of every session, before any other work. Covers the quality bar (never trade correctness for token savings), the total ban on em-dashes, the useEffect ban, the comment policy, and per-commit/per-push authorization. After loading, wait for the user's actual…
Skill Claude CodeCodex
The inverse of /sfl. Where sfl saved each window for later, /nil says later is now: it reopens them. You choose which to bring back.
Skill Claude CodeCodex
Use when a Claude Code session is ending and the user wants to preserve context before /clear, or wants to add session logging to a new project.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: