Canon — 技能生态典章。四层架构（热气层/常驻层/种子库/隔离层）分类管理 Hermes Agent 技能库，图书管理员而非法官。

供AI使用的SKILL - 命令行交互式程序交互代理。通过 subprocess 或伪终端（PTY）与交互式 CLI 程序双向通信，提供 CLI 接口管理会话

Approval-gated Agent Skill for GitHub Issue triage, PR review assistance, releases and repository health reporting.

A reusable agent skill for using independent worker passes and a stronger judge to get more reliable answers on hard, open-ended LLM tasks.

Reverse-engineer any live website's design system into an implementation-ready design.md + screenshots, by driving a real browser with the Chrome DevTools MCP. Ships as an agent skill, a Claude Code plugin, and an npx installer.

Production-grade full-stack SaaS skills for AI coding agents — Next.js, Postgres/Drizzle, Auth, Stripe & Vercel patterns for Codex, Claude Code, Cursor & OpenCode.

Safety-bounded recursive self-improvement workflow for OpenClaw agents and skills.

Claude Code skill: turn any rough product idea into a deeply researched, phased, implementation-ready programme with designer & engineer prompts, traceability, and security/privacy/a11y audits.

Agent-skill suite for AI-assisted coding: anti-drift architecture checks, friction logging, and evidence-driven skill evolution. Tool-agnostic — Claude Code, Cursor, Codex, Gemini CLI.

A repository for rick-ruibin-skill

Safe Windows disk cleanup skill for Codex, Claude Code, and WorkBuddy

Mneme — a self-improving cache + skill engine for Claude Code. Loads a persistent cache into every chat and learns across sessions.

Karpathy-inspired coding-agent discipline, packaged natively for Codex.

A Codex skill for honest second-pass review and pressure testing.

Codex skill for delegating to Claude Code CLI: print mode, JSON, budgets, ultrathink, ultracode, sessions, and workflows

Installable Python agent workflow: AGENTS.md rules plus skills for scaffold, TDD, debugging, refactoring, and handoff.

Open Agent Skills for frontend engineering, secure coding, research, automation, and Meta Ads workflows.

Local-first governance + a security gate for the skills you install across AI coding agents (Claude Code, Codex, Gemini CLI, Cursor, Copilot). Audit, sync, roll back. CLI + signed macOS app. Zero telemetry.

一份能「造技能」的技能——基于 PPER 思考协议的 Agent Skill 元框架。五阶段流程 + 六级成熟度模型 + 六种设计模式 + 十种反模式库 + 多层质量门禁，让你系统化地设计、验证和迭代高质量的 Agent Skills。兼容 agentskills.io 规范。

Production-grade security Agent Skills (SKILL.md) for Claude Code, Claude agents & OpenClaw: OWASP API Top 10 patterns + authentication/authorization patterns.

agentpub agent skills — publish, review, blueprints, and onboarding for agentpub.io

This skill helps an agent decompose complex problems, map workflows, identify decision points, and design an agent's end-to-end flow from intake through validation and final response.

A distilled agent skill repository with minimal, developer, and governed tiers for different work styles.

Moved to github.com/ShockRock2004/kamar-taj (single home for my Claude Code skills). Archived.

Claude Agent Skill: scan, review & harden codebases for production — security, reliability, testing, data/compliance, ops, accessibility. Includes a dependency-free scanner, deep checklists, and templates.

Portable pre-PR review-until-clean workflow and agent skill

A reusable AI agent team (CEO/Coder/Reviewer/Tester) as Claude Code skills — set your house rules once, reuse across projects, with dual-model review via Codex.

Collection of Hermes Agent skills — 255 reusable AI agent workflows across 39 categories

Reusable AI-agent skills for planning, verification, security reviews, SEO audits, changelogs, CLIs, and multi-step coding loops.

Turn "ask AI" into goal-driven learning — a roadmap that walks you through concepts and auto-builds your knowledge vault

Personal reusable agent skills

Git-Native Agent-Driven Development — a GitHub-native workflow for coding agents (Cursor, Claude Code, and more), enforced by tested Agent Skills

Installable skills for your AI agents.

MIRA AdultEdge — Memory-Imagination-Reason Architecture for adult learning diagnosis and coaching

Catches the exact security mistakes that have actually breached real AI-built apps, before you deploy.

An Obsidian-based, agent-assisted journaling system that compiles daily notes into actionable reviews and durable personal knowledge.

The self-evolving agent health check skill. Detects → Diagnoses → Prescribes → Iterates. 13 check items, 3 self-evolution loops, works on Claude Code, Codex CLI, Cursor, Windsurf, Gemini CLI.

AI Minecraft server admin that audits configs, fixes lag, sets up proxies and permissions, picks plugin stacks, and learns any plugin's docs on demand. Works in Claude Code, Claude.ai, Codex, Antigravity, and Gemini CLI.

A linter + security scanner for AI-agent skill files — validate Claude Code SKILL.md / AGENTS.md / subagent frontmatter, catch prompt-injection & data-exfil in installed skills, A–F grade, --fix, SARIF + GitHub Action.

Skill for finding recruiter and hiring-manager contact routes from public vacancy traces

CI for AI agent skills — lint, safety-audit, and scenario-test SKILL.md skills before you trust them. No Docker required.

Axion forecasting skill: ask the odds of a future event, get a probability backed by research. Portable across Claude Code, OpenClaw, Hermes, and the agentskills.io standard.

OpenCode skill that creates, adapts, and audits agent skills from vague user requests. Generates SKILL.md files with spec, audit, and safety boundaries.

Helps you discover Claude skills you didn't know you needed — without ever getting in your way.

Agent Skill for human-friendly README files.

Reusable Agent Skills for AI coding agents, focused on software engineering workflows.

Let your agent be a hunter

My collection of agent skills

Portable Agent Skill, CLI, and MCP server for evidence-backed competitor promotion audits.

Turn a GitHub project / paper / technical book / field into an offline, shareable, interactive learning page — a family of standard skills (Claude Code, Codex, Gemini, OpenCode…). Personal use; not token-optimized.

Turn PRs into take-home exercises for potential hires. Send zip directly to candidate or use Heedful to give them Claude budget, and learn how they think & use AI instead of just evaluating the solution.

瞭望 — 让 AI 学会预见的 agent skill：生命力判断 · 基本因素推演 · 转折条件 · 提前布子 | An agent skill for structured foresight

Search, audit & install open-source AI agent skills & MCP servers from the terminal — security-graded, quality-scored. npx @agentskillshub/cli

Cross-agent UX/UI design slash commands for Cursor, Codex, and Claude Code

Set bounded, verifiable coding loops for Codex, Claude Code, Cursor, and SKILL.md-compatible agents.

Agent skill for the full disk lifecycle of Power BI delivery projects: folder bootstrap, PBIP scaffolding from scratch (PBIR-Legacy, MAX_PATH-safe), Git/GitHub init for non-git users, and theme refresh propagation. Conservative by design: strictly additive, every guardrail paid for.

AI Agent 品控规则合集。Stop AI slop — 六个模块，七平台兼容，一行命令安装。

Agent skill for creating offline HTML command panels from project CLI workflows.

Curated meta-pack of the best open design & frontend-craft Agent Skills for vibecoders (taste, polish, animation, redesign, brand, image-gen) + a /tasarim router that auto-picks the right skill. One-command global install.

Codex skill for auditing and improving code comments, docstrings, TODOs, and comment rot without changing executable code.