Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 378,678 indexed, measured the same four ways as everything else here.
taylor0017-creator/skill-review
Skill Claude CodeCodex
A structured review of a coding-agent skill file, usually named SKILL.md. It checks the file against published standards and produces a scored report with specific fixes.
Stephen-Kimoi/harness-engineering-template
Skill Claude CodeCodex
Use when building software with AI agents and you need a serious end-to-end workflow instead of vibe coding. Covers harness choice, context discipline, cleanup, review loops, launch pressure, and security basics.
Skill Claude CodeCodex
A security review method for an external coding-agent skill file. It looks for prompt injection, credential theft, unsafe code execution, misleading names, and social-engineering tactics before installation.
Emily2040/parallel-codegen-orchestrator
Skill Claude CodeCodex
Plan, resume, verify, and safely parallelize substantial code work.
Skill Claude CodeCodex
Perform a security audit on code, checking for common vulnerabilities including injection, auth bypass, secrets leakage, and unsafe dependencies.
Skill Claude CodeCodex
Discover, install, and run reusable AI prompt skills from the BetterPrompt registry via the CLI (betterprompt / bp). Use when a user needs to find a prompt skill, generate AI output (text, images, video), or manage their skill library. Covers installation, auth, skill discovery, generation, and output review for…
jiangyuxue666/skill-auto-maintain
Skill Claude CodeCodex
Automated lifecycle management for non-bundled Hermes skills. Scans all skill directories, migrates orphans to userskills/, registers in userskills.json, detects merge candidates via multi-dimensional similarity, and optimises SKILL.md format. No SOUL framework dependency — works on any standard Hermes Agent…
Skill Claude CodeCodex
Use when the user asks to build a feature using test-driven development.
Skill Claude CodeCodex
Search Israeli movie showtimes, ratings, and cinema info from seret.co.il. Use when user asks about movies playing in Israel, Israeli cinema showtimes, "ma makrineem hayom", "sratim hadashim", "seret", movie tickets in Israel, what's showing in theaters, or upcoming Israeli film releases. Fetches real-time data from…
Skill Claude CodeCodex
Cross-chain token swap integration using NEAR Intents 1Click API. Use when building swap widgets, bridge interfaces, or multi-chain transfers.
Skill Claude CodeCodex
Extract EastMoney sector fund-flow data from data.eastmoney.com/bkzj using browser-harness and Chrome CDP network interception. Use when Codex needs EastMoney industry sector list data, sector fund-flow rankings, or historical sector fund-flow detail data, especially requests mentioning bkzj, hy.html…
wumingyu1688-sudo/AI-CADdrawing
Skill Claude CodeCodex
A skill for drawing mechanical engineering plans in AutoCAD according to a defined AI drawing standard.
Skill Claude CodeCodex
Plugin-shipped skill that wraps the workspace test runner (pytest / jest / go test) so the tester role can issue a single command and parse a single exit code. Defines the CLI surface and exit-code contract.
Skill Claude CodeCodex
Run user-created frontend/backend/WebSocket services and expose them through Cloudflare by default when the user asks to start, deploy, preview, share, or make the service accessible. Local-only is allowed only when explicitly requested.
elimydlarz/claude-code-plugins
Plugin Claude Code
Bundles 15 skills, 2 hooks · 896 tokens together
Test trees as living requirements — TDD with auto-synced specifications in TESTTREES.md.
ali4o/visual-identity-designer
Skill Claude CodeCodex
Build a professional, precise visual identity (brand identity) for a project, startup, or business — logo direction, color system, typography, application mockups — via a structured 9-stage agency workflow ending in two polished deliverables — a Brand Identity Guide and a Design Language System (built with the docx…
mustafaakben/outlook-suite-plugin
Plugin Claude Code
Bundles 6 skills · 354 tokens together
Modular Outlook automation skills for Claude Code: mail, calendar, contacts, tasks, and notes.
Skill Claude CodeCodex
Self-applied interviewer that walks a first-time agent user (Cowork, Codex, Claude Code, or any Skills-aware system) through producing a v1 voice SKILL.md scaffold of their own. Conducts a structured interview across identity, modes, sample harvest, pattern extraction, tropes, and worked examples; then generates a…
Skill Claude CodeCodex
Complete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind maps, threat modeling), vulnerability hunting (IDOR, SSRF, XSS, auth bypass, CSRF, race conditions, SQLi, XXE, file upload…
hugomrtz/skill-vetting-clawhub
Skill Claude CodeCodex
Vet ClawHub skills before installation. Use when the user asks about evaluating, auditing, or safely installing OpenClaw/ClawHub skills, or when a skill’s trustworthiness is in question.
Skill Claude CodeCodex
Model-agnostic behavioral skill that makes the agent collaborate as a partner — investigating freely but always sharing findings and getting feedback before taking any action that modifies something. Runs an invisible self-review loop for quality. Eliminates unnecessary questions, fake tests, and verbose…
flthibau/sample-OpenClaw-on-Azure-with-AI-Foundry
Skill Claude CodeCodex
A procedure for downloading online videos and audio with yt-dlp, a command-line downloader. It supports YouTube, Bilibili, Twitter, and many other websites.
Skill Claude CodeCodex
Local smart routing layer for Bankr LLM Gateway traffic. Use when explaining or installing Bankr Router, switching auto/eco/premium profiles, configuring OpenClaw providers, verifying routing, or debugging router/Bankr model issues.
Skill Claude CodeCodex
Collect natural-language environment context and generate evidence collection guidance for Mandate 2.2.3 Secure Training and Fine-Tuning. Use when code is insufficient and operational proof is required for final compliance evaluation.
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: