A murder-mystery game for Claude Code, refereed by an AI that genuinely can't see who did it. The culprit is sealed to disk and only revealed through scripted output and forked context.

Scientist agent mode for AI coding agents — hypothesis-driven, evidence-based, uncertainty-aware.

The why behind your code, as plain markdown in your repo. Agent skill to capture decisions, dashboard to browse them.

Agent Skills for Claude (Claude Code / Claude Desktop): Chrome Web Store asset generation, paid-app Stripe licensing with offline-verified keys, and ServiceNow update-set QA + ATF test generation.

collection of reusable engineering skills for AI coding agents

My Public Agent Skills

delegate-skills — Offload implement / investigate / git tasks to cheaper models. File-based md2idx protocol keeps the main agent's context lean.

🦾 Skills for App Store Connect metadata, screenshots, App Review details, and regional pricing audits

A Codex skill pack for long-running project work

Production-grade SaaS UI skills for AI coding agents (React + Tailwind + shadcn/ui) — Codex, Claude Code, Cursor, OpenCode. One npx command to install.

Document-driven agent pipeline for software R&D: analyze → plan → review → develop → test. Portable skills for Cursor, Claude Code & Codex.

Loop + Goal Agent Skills by Saido Labs: a Plan-Build-Test-Reflect-Improve project cadence (/loop) and an objective-mode driver (/goal) with persistent .md state. Works in Claude Code and Cowork.

Standardized AI Looping Language

AI agent skills for everything after the AI builds your app — launch, get users, grow. Works with Claude Code, Cursor, Windsurf.

Portable agent skills for building honest AI-tool income systems — the agentic-income brain + affiliate-audit. Claude Code / Cursor compatible.

skillet — a package manager for AI agent skills (SKILL.md). Find, install, version & share skills from a Git-backed registry. Zero infra, MCP-native, reproducible.

Practical agent skills for repeatable workflows and durable product or business context.

Production-grade Agent Skills for Web3 AI agents: 15 workflows, 6 MCP servers, DeFi/NFT/compliance guardrails, and VS Code/JetBrains installers.

Community-curated Hermes Agent skills, workflows, and reusable task automation recipes.

INFP-oriented Claude/Agent Skills for deep Chinese longform reading across AI, art & culture, and crypto sociology.

An AI engineering skill suite that takes one idea from Ideate → Spec → Plan → Implement → Verify → Review → Ship — the human owns intent, the agent owns execution, ending at risk-banded draft PRs. Installable across Claude Code, Cursor, Gemini CLI, and more.

21 markdown-first software delivery workflow skills for Claude Code, Codex, and compatible agents. Standalone skill kit covering planning, debugging, CI, review, security, rollout, performance, data quality, and post-incident workflows.

Production-grade AI agent skills — enhanced alternative to addyosmani/agent-skills. 23 lifecycle skills for Define, Plan, Build, Verify, Review, Ship. Works with OpenCode, Claude Code, Codex, Cursor, Gemini CLI.

Multi-agent Lang-graph framework for autonomous software developement

Loom — a cross-harness, self-improving agent pack (OMP, Codex, Claude Code)

Local-first CLI to scan, audit, route, and test Codex Skills.

Personal agent skills, packaged for anyone to steal. SKILL.md format, works with Claude Code.

Unofficial port of openai/role-specific-plugins (Codex plugins) to Claude Code, installable as a plugin marketplace

Agent skills that give AI agents the operational competence of expert practitioners (Salesforce, AWS, GitHub Actions, web). SKILL.md format; Claude Code plugins. Not test-prep — certification is the scaffold and benchmark, not the product.

One-shot Claude Code plugin to bootstrap an AI-agent documentation system (CLAUDE.md + rules + agent-guide).

Certified Kubernetes Administrator (CKA) exam practice environment running locally, powered by Vagrant (VirtualBox) and Ansible.

Aegis — 12 judgment-style agent skills for secure, production-grade .NET on Azure (security, design, performance, concurrency, observability). Works with Claude Code, Codex, Cursor, Gemini.

Peter Zhou: 周伯通和 Peter Pan 的合体，一个面向学生的超级老师综合 skill

Open-source agent skills for Claude Code & the AI-agent ecosystem. Install: npx skills add yarrasys/skills@<name>. First skill: kdbx (per-project/per-env KeePassXC credentials).

An agent with subskills that audits, optimizes, tests, and self-heals agentic skills and prompt-based tools (Claude SKILL.md + Agent SDK / MCP).

Pre-delivery evidence gate for 12 AI coding agents: unsupported completion claims stay private until verified.

Full-stack Claude Code pack for marketers: FTC claim-substantiation, CAN-SPAM, deliverability, privacy & no-fabricated-metrics guardrails + skills for positioning, ad copy, landing pages, email, SEO, A/B tests & analytics, loops & review agents. Not legal advice.

A composable Loop Engineering skill group for Codex and Claude Code - interview your task and emit a top-tier, paste-ready agentic loop (harness). 4 skills: spec, engineering, eval, review.

Replicable agent development system: curated Claude Code/Codex skills + bootstrap for the external tools (GSD, caveman, ponytail) that complete the stack.

Glyph is a workbench for composing the forms intelligence takes today — and discovering the language it will speak tomorrow.

一组可独立装载的 Agent / Claude Code Skills：编码行为准则、横切规范、多仓脚手架与多 agent 代码审计

Thin agent adapters for @paniolo/scan — run the AI Technical Debt Scanner from any coding agent and optionally remediate findings. Portable skill (npx skills add paniolo-ai/scan --all), Claude Code plugin (/paniolo-scan), Antigravity workflow, GitHub Action. Not the scanner source.

SDD, but for landing pages — a phased multi-agent workflow that ships modern, high-converting landings that don't look AI-generated. One-command install.

Agent skills for working with jsPsych — best-practice guides for building plugins and timelines, usable in Claude Code, Cursor, Copilot, and other skills-compatible agents.

Open Agent Skill for PE-grade system design interview prep. Generates 10 artifacts per problem with quality gates, cross-file checks, and a Python validator. Works with Cursor, Codex, Claude Code, Copilot, and Gemini CLI.

Upgrade GitHub Actions versions interactively from your terminal

Shippo's AI distribution surfaces: Agent Skills + plugins for Claude Code, OpenAI Codex, ClawHub, and the Claude apps.

An AI council that picks its own experts — adaptive multi-persona panel with preserved dissent. Skill for Claude Code, Codex & the Claude app. EN+PL.

bathe your agents in engineering rigour and flames

Skills and guardrails that make AI coding agents prove their work: planning gates, test preflights, fail-closed deployment, and a self-improving skill library.

An AI second brain with an action layer — Notion + Claude.

Session handoff skills for coding agents — Claude Code, Codex, Cursor, Gemini CLI & Grok Build. Capture a session to a file, then resume it fresh.

Codex Agent Bus skill family for local multi-agent coordination

Talk to a humanoid in a 3D apartment — on screen, in VR, or in your real room (MR). Voice/text commands, an open-source BYO-key LLM brain, and ~950 composable motion skills. Three.js + WebXR (Quest 3).

Forkable, draft-only multi-agent GitHub-notification triage on ZeroClaw / Claude Code

Config-driven SDLC skills for coding agents: task flow, releases, debugging, and security triage.

mcp server serving coding agent skills with helper tools

Consensus & debate board for error-not-allowed work: diverse lenses either verify new work before it ships (Generate), or inspect existing work and report findings (Audit/Review). Bounded cost + zero-breakage. Cross-agent - validated on Claude Code + Antigravity. Part of TheColliery.

🏃 Sprint — every TODO item gets a full mini-sprint: autonomous plan→implement→review for Claude Code via git-hook agent chain, isolated worktree, deterministic gate & fail-closed review