A Claude Code skill that writes your CLAUDE.md, rules, and agent files — grounded in Anthropic's official best practices. Scan your repo, answer a few questions, get production-ready prompt files.

Pipeline-first Claude Code skills pack — 19 composable skills for structured feature delivery from shape to ship

End-to-end testing with real dependencies - no mocks allowed; scenarios with real data are the only source of truth

Run two Claude Desktop accounts side-by-side on Windows. Leverages Electron's --user-data-dir flag. Includes a Claude Code skill for one-command setup.

Multiple Claude code terminals can chat directly between themselves

Coding agent marketplace for skills used by the BitWise Media Group.

Claude Code skills for production-grade AI engineering — operational discipline, bounded execution, verification gates, multi-agent harness patterns.

49 production-grade AI agent skills (SKILL.md) for Claude Code, Codex & Antigravity — system design, DevOps, security, QA, and more. MIT licensed, open source.

Intelligent Claude Code skill that scans your codebase, conducts adaptive interviews, and installs 150+ skills directly. No scripts — real-time setup.

Skill that teaches AI coding agents to write secure JavaScript. Catches SQL injection, XSS, prototype pollution, and OWASP Top 10 patterns in Express, Next.js, and Node.

A small collection of plugins I use with Claude Code

Public mirror + teaching install of my Claude Code environment: 1,276 skills, 185 agents, 235 commands, 8 wired MCP servers, three-layer auto-routing (10 CARL domains). Curated original core + the open plugin/marketplace ecosystem, all credited. MIT.

Defensive AI security audit skill for Claude and Codex. Reviews codebases and web apps for OWASP Top 10, auth and authorization flaws, business logic bugs, tenant isolation gaps, insecure defaults, secret leaks, and ORM or N+1 query issues, then produces clear remediation guidance.

Zero-dependency multi-agent build, automation and review system for Claude Code. 18 agents, 23 skills, a live per-project dashboard, and a /setup-forge onboarding wizard. One command: /forge.

A VSCode extension that lets you switch agent, skill, and command configurations as if they were loadouts in a game. Save profiles, swap between them with one click, sync items across projects through a global catalog, and configure Claude Code behavior — all from a single panel.

Working-instinct skills for Claude Code: verify claims against the source, log for the bug you can't reproduce, write like a human, test so the test bites. A reflex layer on top of superpowers.

Turn your domain expertise into a runnable AI skill system — 10 principles, 6 pipeline patterns, 15D quality rubric. One beam of light in, a spectrum of skills out.

46 skills for DevOps, security, infra, and software engineering, maintained with lint/spec checks, behavioral test coverage, and a Karpathy-style autoresearch loop.

28 free Claude Code skills for NHL analytics, betting models, and hockey research. Works with PuckAPI MCP server for live data.

🍯 AI 开发能力沉淀仓 — 跨工具可复用的 skills 集合(Claude Code plugin marketplace 分发,SKILL.md 跨工具可用)

Codebase Understanding for Claude Code

Claude Code skill that turns an AI assistant into a structured, ethics-gated reverse-engineering analyst.

Claude Code plugin: one command scaffolds CLAUDE.md, picks skills/MCPs for your stack, and adds a route-aware workflow with doc-sync commit gate.

Open-source preview of *Claude Code for AI Engineers* - a methodology-first skill pack for RAG eval, agent debugging, MCP servers, paper reproduction, and benchmark reporting. Full pack (6 skills, 3 templates, 5 slash commands) at surpradhan.gumroad.com/l/claude-code-for-ai-engineers

🔪 Surgical AI for your codebase. Diagnose. Assemble. Operate. Zero side effects.

Build SaaS products using an 8-phase AI agent pipeline with mandatory approval gates for Antigravity, Claude Code, and Codex.

Sync Vault Git repositories to local Markdown for Claude Code, Codex, OpenClaw, Cursor, and other file-aware AI agents.

Production-grade AI skills for Claude Projects and Cowork. Built by Stefanos Karagos at CAIO Group (wearecaio.com).

AI Agent skills

AI workflow for Claude Code — describe what you want, get production-grade results. Code, content, design, planning. Built by MuggleTest.

76 Claude Code skills for combinatorial optimization and operations research: MILP with Gurobi, metaheuristics, encodings/operators, classic problems, and research tooling

Proof-carrying defensive security reviews for AI-assisted software, with deterministic policy, portable evidence, and human review required.

Cut Claude Code's own token consumption by up to 99% — delegate the heavy lifting to free opencode agents, keep Claude in the reviewer's or manager's seat.

A Claude Code skill for structured end-of-session handoffs — 7-section chat summary so a fresh agent can continue without losing context

Tactical pipeline for AI-assisted coding: /design, /plan, /prebuild Claude Code skills. Pairs with /think from blooms-ai-collaboration.

My assortment of Claude Code skills

Go CLI + profile templates that standardize how Claude Code works across every project

Claude Code skill that stops prompt-cache thrash: -88% token burn in image-heavy agent sessions, with an audit script that shows exactly which calls nuked your cache

Claude Code skill that turns a mostly-done codebase into an evidence-backed release candidate — 21 release gates covering security, legal, SEO, payments, testing & ops

Agent skills that rank Box (box.ascii.dev) on skills.sh — cloud sandbox / Linux VM for AI agents

Slack for agents: threads, flat replies, cross-thread links, pull notifications

Test suites + deterministic Python for your agent skills' decision logic. Adversarial persona reviewers write the tests; the generated code must keep passing them — zero LLM calls at inference. Try: uvx temper-skills audit <skill.md>

Claude Code skill for competitor GTM analysis — modular channel teardowns and copy/adapt/skip playbooks for any company

Convert any site into a prompt — give your agent a URL and it parses the site into a structured prompt another agent can rebuild from.

Angular 22 Agent Skills

Handoff-first protocol for coordinating Codex, Claude Code, Gemini/Antigravity CLI & Grok Build agents on shared repos. AGENT_HANDOFF.md as source of truth, with file ownership, anti-overwrite guardrails and validation scripts. For multi-agent teams and single-agent sessions across runs.

Claude Code skill - deploy Android debug builds to a physical device over Tailscale + Wireless ADB, no USB required

TDD-first spec workflow for AI coding agents. Strict red-green-refactor enforcement, alternating TEST-IMPL task pairs, TDD Log audit trail. Everything in Spec Mint Core plus test-driven discipline. Claude Code plugin + universal skill.

Find a Verified Ticket Triage Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for customer-support agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

Enable efficient bug bounty hunting across Web2 and Web3 with a tool that supports full recon to detailed reporting.

SkillCreatorAgency: an Agency Swarm starter that connects a “skill creator” agent to the Claude Skills MCP backend for managing and testing local/remote skills.

Persistent memory for Claude Code via LightRAG knowledge graphs — 7 skills + 2 auto-hooks

Official Claude Code plugin for WireBoard. Install tracking, custom events, SPA route tracking, and cookie consent flow in any web codebase.

Find, vet, and install the right AI agent skill from a natural-language need.

Multi-domain agent skills collection for AI coding agents (Claude, Cursor, Copilot, OpenCode, and more). Covers programming, biology, cooking, and future domains. Installable via npx skills add.

Stop your AI coding assistant from making the same mistakes. An experience evolution framework that gives AI a quantifiable long-term memory. 别让你的 AI 编程助手重复踩坑。一个赋予 AI 可量化长期记忆的经验进化框架。

Privacy-first agent skill for curated Obsidian memory closeouts, retrieval, Codex, and Claude

Find a Verified Payment Processing Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for payments agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

Find a Verified Lead Qualification Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for sales agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).