Everything for Claude Code

Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 368,145 indexed, measured the same four ways as everything else here.

tracely

1441

Jwuthri/Tracely-ai

Skill Claude CodeCodex

Instrument AI agents with Tracely and turn their production traces into CI gates. Use when the user mentions Tracely, tracely-ai, tracelysdk, the tracely CLI, or asks to trace/observe an AI agent, add LLM evaluators or LLM-as-a-judge columns, debug why a trace or conversation isn't showing up, wire agent regression…

not rated 1.4k +211 yesterday A SkillSpector: warn 120 tokens original MIT

clawd-media-track

1442

fancydirty/mediary-scout

Skill Claude CodeCodex

Resource tracking and acquisition workflow for media resources. MUST use when the user asks to get, add, track, monitor, search, acquire, transfer, or initialize movies, TV shows, anime, Pansou resources, or 115 cloud storage items with the clawd-media-track system. For every clawd-media-track task: first read…

not rated 1.4k +13 8d ago A 115 tokens original 0BSD

agentflow

1443

agentenv/agentflow

Skill Claude CodeCodex

Build and run multi-agent pipelines using AgentFlow. Use when the user wants to orchestrate codex, claude, or kimi agents in parallel, in sequence, or in iterative loops. Trigger when the user mentions multi-agent workflows, fan-out tasks, code review pipelines, iterative implementation loops, running agents on…

not rated 1.4k +16 18d ago A SkillSpector: pass 112 tokens original MIT

agent0ai/space-agent

Skill Claude CodeCodex

Use HTML adapters, JS hook seams, and component loading correctly in the layered module system.

not rated 1.4k +2 3mo ago A SkillSpector: pass 22 tokens original MIT

h-reason

1445

m0n0x41d/haft

Skill Claude Code

Source-first umbrella for FPF-aware reasoning in a Haft project. Use when the operator asks to think through an ambiguous engineering, management, architecture, specification, or project question without naming a narrower Haft capability. Recover the current object and question, query the bundled FPF source, inspect…

not rated 1.4k +1 1mo ago A 112 tokens

autoreview

1446

openclaw/crabbox

Skill Claude CodeCodex

Structured Codex, Claude, Amp, Pi, or Kimi code review when explicitly requested.

not rated 1.4k +19 today A SkillSpector: warn 22 tokens original MIT

daymade/claude-code-skills

Skill Claude CodeCodex

Investigates network, streaming, and protocol failures with falsification-first layered experiments. Use for ECONNRESET, HTTP/2 RSTSTREAM, SSE or long-polling stalls, fixed-time drops, CDN/proxy/CGNAT timeouts, client-side proxy/TUN misrouting, CNAME-rule surprises, certificate errors, generic throughput collapse…

not rated 1.4k +11 changed today A Socket: passSnyk: warnSkillSpector: warn 194 tokens original MIT

feishu-cli-meetings

1448

riba2534/feishu-cli

Skill Claude Code

A Feishu video-meeting and Minutes skill for finding past meetings and retrieving their notes, recordings, transcripts, and AI-generated summaries. Feishu Minutes is the service's meeting-record system.

not rated 1.4k +4 15d ago A SkillSpector: pass 115 tokens original MIT

apple-targets

1449

EvanBacon/expo-apple-targets

Skill Claude CodeCodex

Build, configure, and debug native Apple extension and target types (widgets, App Clips, share extensions, watchOS apps, Safari extensions, notification extensions, VPN/network extensions, and 40+ more) in an Expo app using the @bacons/apple-targets config plugin. Use when a user wants to add home screen presence…

not rated 1.4k +3 1mo ago A Socket: passSnyk: pass 109 tokens

mastg

1450

ChiChou/grapefruit

Skill Claude CodeCodex

Autonomous mobile security audit aligned with OWASP MASTG v2. Performs checklist-driven analysis across MASVS categories: storage, crypto, network, platform, code, resilience, privacy. Exports structured markdown report with MASTG test references.

not rated 1.4k +4 1mo ago A SkillSpector: warn 53 tokens original MIT

challenge-run-agent

1451

AgibotTech/genie_sim

Skill Claude CodeCodex

Use when the contestant wants to launch the inference Agent that connects to the Simulation gateway via WebSocket. Wraps the inference repo's ./scripts/tunnel.sh and scales to PARALLELISM processes. This is side-effecting (consumes GPUs and a parallelism slot) — confirm before launching.

not rated 1.4k +5 5d ago A SkillSpector: pass 64 tokens

shinka-setup

1452

SakanaAI/ShinkaEvolve

Skill Claude CodeCodex

Create ShinkaEvolve task scaffolds from a target directory and task description, producing evaluate.py and initial. (multi-language). Use when asked to set up new ShinkaEvolve tasks, evaluation harnesses, or baseline programs for ShinkaEvolve.

not rated 1.4k +11 22d ago A SkillSpector: warn 62 tokens original Apache-2.0

merge

1453

peterkrueck/Claude-Code-Development-Kit

Command Claude Code

Finalize work on a branch: verify docs + tree are clean, merge to main, clean up. Supports both standard git checkout -b branches and git worktree flows — auto-detected at pre-flight.

not rated 1.4k +1 1mo ago A 0 tokens original MIT

https-deeplearning-ai/sc-agent-skills-files

Skill Claude CodeCodex

Generate educational practice questions from lecture notes to test student understanding. Use when users request practice questions, exam preparation materials, study guides, or assessment items based on lecture content.

not rated 1.4k +4 3mo ago A 41 tokens

horse-database-pooling

1456

HashLoad/horse

Skill Claude CodeCodex

Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.

not rated 1.4k +2 3d ago A SkillSpector: pass 30 tokens original MIT

aetherviz-master

1457

andyhuo520/aetherviz-master

Skill Claude CodeCodex

A tool for turning a teaching topic into an interactive educational webpage with animated 2D and 3D visual elements.

not rated 1.4k +5 4mo ago A 39 tokens original MIT

burrow-system-tools

1458

caezium/burrow

Skill Claude CodeCodex

Diagnose and fix the user's Mac with Burrow's local MCP tools (burrowdoctor, burrowsnapshot, burrowtopprocesses, burrowprocessusage, burrowports, burrowanalyze, burrowdiskforecast, burrowdupes, burrowanomalies, burrowagentaudit, burrowclean, …). Use whenever the Mac is slow, hot, loud, low on disk, draining battery…

not rated 1.4k +16 today A SkillSpector: pass 194 tokens original MIT

emailmd

1459

anypost/emailmd

MCP server Claude CodeCodexCursor +2

Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails. Runs locally from the emailmd npm package.

not rated 1.4k +3 17d ago A tokens not measured original MIT

react-call

1460

desko27/react-call

Skill Claude CodeCodex

Reach for the react-call library (createCallable) when building UI that resolves a value back to its caller — confirmations, dialogs, form modals, toasts, notifications, context menus, pickers. Use when a React task involves any such "await the UI" interaction, when code imports createCallable, useMutationFlow…

not rated 1.4k +1 11d ago A SkillSpector: pass 135 tokens

kodustech/kodus-ai

Skill Claude Code

Validate PR code changes against task requirements to identify missing, forgotten, or overlooked business logic implementations.

not rated 1.4k +16 today A SkillSpector: warn 23 tokens

ideation

1462

OpenRaiser/NanoResearch

Command Claude Code

You are the Ideation Agent for NanoResearch. Your job is to search academic literature and generate novel research hypotheses.

not rated 1.4k +1 18d ago A 0 tokens original MIT

e2e-runner

1463

cfrs2005/claude-init

Agent Claude Code needs its repo

An end-to-end testing assistant built around Playwright, a tool that controls real browsers to test complete user journeys.

not rated 1.4k +1 6mo ago A 70 tokens original MIT

truongduy2611/app-store-preflight-skills

Skill Claude CodeCodex

Scan an iOS/macOS Xcode project for common App Store rejection patterns before submission. Use when preparing an app for App Store review, after receiving a rejection from Apple, or when auditing metadata, subscriptions, privacy manifests, entitlements, or design compliance. Integrates with the asc CLI for metadata…

not rated 1.4k +10 3mo ago A 69 tokens original MIT

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: