Curated skills library for Claude Code, Cowork, and any Claude surface

One git checkout drops a shared AI coding setup (skills, subagents, MCP servers, OpenSpec scaffolding) into any project, across Claude Code, Kilo, OpenCode, Codex, and Copilot.

Agent-engineering patterns and portable, prompt-only skills for LLM coding agents — multi-agent orchestration, adversarial multi-LLM council, learned guardrails. Vendor-neutral, MIT.

A portable Claude Code plugin system for orchestrating software development through parallel specialist agents, enforced engineering standards, and automated quality gates. One command to plan. Parallel agents to build. Automated gates to ship.

Personal collection of agent skills for use with Claude Code and other LLM agents.

Local-first skill pack manager and verifier for agent instructions.

macOS bootstrap dotfiles: Brewfile, declarative symlinks, app prefs, macOS defaults, agent skills, vault secrets, make doctor. Fork-friendly.

macOS bootstrap dotfiles: Brewfile, declarative symlinks, app prefs, macOS defaults, agent skills, vault secrets, make doctor. Fork-friendly.

Make AI Agents great again!

my agent skills

my agent skills

my agent skills

my agent skills

my agent skills

Personalized Development Skills

14 auto-triggering Claude Code skills that inject production engineering rules into your AI agent — trigger precision + deterministic option-spaces, distilled from a ~60K-line FastAPI/Next.js/Flutter codebase

Minimalist Cross-Agent Skills Manager

Curated, sanitized export of 21 agent-skill packages for Claude Code and Codex, gated by an automated publication audit (no secrets, no local paths).

Curated, sanitized export of 21 agent-skill packages for Claude Code and Codex, gated by an automated publication audit (no secrets, no local paths).

A collection of practical, production-ready AI agent skills for the skills.sh ecosystem.

Self-learning AI companion — 29 skills: adaptive knowledge base + Carmack Council + impeccable design. Every session makes it smarter.

AI-native engineering harness: doctrine-only, fork-and-curate scaffold for standards, agent skills, tool adapters, and review rubrics.

AI-native engineering harness: doctrine-only, fork-and-curate scaffold for standards, agent skills, tool adapters, and review rubrics.

Practical workflow skills for coding agents: scope, debugging, cleanup, subagents, GitHub tracking, and verification.

Self-correcting knowledge corpus for Claude Code — 9 stable shape clusters, bias-correction pipeline baked into contribution flow. 47 papers, 45 techniques, 1.1k skills.

Self-correcting knowledge corpus for Claude Code — 9 stable shape clusters, bias-correction pipeline baked into contribution flow. 47 papers, 45 techniques, 1.1k skills.

Self-correcting knowledge corpus for Claude Code — 9 stable shape clusters, bias-correction pipeline baked into contribution flow. 47 papers, 45 techniques, 1.1k skills.

Self-correcting knowledge corpus for Claude Code — 9 stable shape clusters, bias-correction pipeline baked into contribution flow. 47 papers, 45 techniques, 1.1k skills.

Self-correcting knowledge corpus for Claude Code — 9 stable shape clusters, bias-correction pipeline baked into contribution flow. 47 papers, 45 techniques, 1.1k skills.

Policy-as-code admission controller for AI agent skills and MCP tools. SkillBOM, lockfiles, and supply-chain baselines.

Agent Skills for Conventional Commits, maintainability code reviews, and pull request descriptions.

Enforcement & release-hygiene layer for Cursor agents — blocking git/DB/license guardrails, commit hygiene, and docs-ops.

Reusable AI agent skills for engineering, product, architecture, planning, and delivery workflows.

Hermes Agent distribution with Ask DongFeng bundled as a built-in control-loop framework skill

Hermes Agent distribution with Ask DongFeng bundled as a built-in control-loop framework skill

A collection of portable, domain-focused AI agents managed by kman.

A collection of portable, domain-focused AI agents managed by kman.

A collection of portable, domain-focused AI agents managed by kman.

Generated by Codex. Read with caution.

Generated by Codex. Read with caution.

Portable Codex agent harness and config monorepo with reusable roles, skills, validation, eval tooling, and safe project install sync.

Portable Codex agent harness and config monorepo with reusable roles, skills, validation, eval tooling, and safe project install sync.

Agent skill teaching Google's code-review standards (eng-practices) for Claude Code, Codex, and any agentskills.io-compatible agent. Cross-agent install via symlink + install.sh.

🧠 Self-growing Claude agent skill system — auto-discovers, fetches from GitHub, creates via web research, and self-improves. Works in Claude.ai + Claude Code.

A collection of reusable skills for Claude Code agents, dedicated for swe and developers

Cross-project agent workflow skills — session onboarding, handoffs, PR review, and merge workflows

Portable, open catalogue of agent skills for Cursor, Claude Code, Windsurf, Copilot, and other AI coding assistants.

Sixteen Claude Code skills for the parts of shipping I'd rather not do myself: ADRs, specs, audits, PR composition, review iteration.

Sixteen Claude Code skills for the parts of shipping I'd rather not do myself: ADRs, specs, audits, PR composition, review iteration.

Handy AI skills

Handy AI skills

Reusable CrewAI Flow using agent-skills as operating procedures with pluggable headless coders (Codex and Grok)

Reusable CrewAI Flow using agent-skills as operating procedures with pluggable headless coders (Codex and Grok)

Centralized manifest for AI agent skills. Synced via ai-agent-skills.

Centralized manifest for AI agent skills. Synced via ai-agent-skills.

Centralized manifest for AI agent skills. Synced via ai-agent-skills.

Centralized manifest for AI agent skills. Synced via ai-agent-skills.

Centralized manifest for AI agent skills. Synced via ai-agent-skills.

Personal APM marketplace — skills, prompts, agents, and instructions for AI coding agents