Author, evaluate, security-review, and autonomously improve Claude agent skills - 21-check harness, behavioral/trigger/value-add evals, self-tested + CI

A curated collection of reusable AI agent skills, playbooks, and prompts for security audits, engineering workflows, and automation.

A curated collection of reusable AI agent skills, playbooks, and prompts for security audits, engineering workflows, and automation.

A curated collection of reusable AI agent skills, playbooks, and prompts for security audits, engineering workflows, and automation.

Reusable Agent Skills for Claude Code

Open-source agent workflow skills and governance templates

Open-source agent workflow skills and governance templates

Open-source agent workflow skills and governance templates

Open-source agent workflow skills and governance templates

Hands-on git coaching skills for AI coding agents: real commands, plain-English why, undo-first recovery, and safe practice drills.

Agent skills for UnoPim — domain-specific context for AI agents (Claude Code, Cursor, Windsurf) working in an UnoPim PIM codebase. Install: npx skills add unopim/agent-skills

Agent skills for UnoPim — domain-specific context for AI agents (Claude Code, Cursor, Windsurf) working in an UnoPim PIM codebase. Install: npx skills add unopim/agent-skills

Practical bilingual skills that make AI coding agents more disciplined, testable, and useful in real engineering work.

Practical bilingual skills that make AI coding agents more disciplined, testable, and useful in real engineering work.

Agent skills for building and navigating memory palaces — the skills layer for the Mind Intelligence System.

Agent skills for building and navigating memory palaces — the skills layer for the Mind Intelligence System.

Agent skills for building and navigating memory palaces — the skills layer for the Mind Intelligence System.

Claude Code skills for delegating to external coding agents (Codex, Cursor, opencode), plus an ultracode workflow orchestration layer

Claude Code skills for delegating to external coding agents (Codex, Cursor, opencode), plus an ultracode workflow orchestration layer

Production-grade Codex skills with explicit triggers, deterministic validation, and reusable AI agent workflows.

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

AI agent that accumulates SRE knowledge from every incident — built on Agent Skills spec for Claude Code

Benchmark, lint, and standardize reusable skills for AI coding agents.

Claude Code plugin: token-optimized dev workflow — cached project context, pattern scanners, build & wiring verification, session persistence, self-review. 23 skills, 3 agents, 4 commands.

Claude Code plugin: token-optimized dev workflow — cached project context, pattern scanners, build & wiring verification, session persistence, self-review. 23 skills, 3 agents, 4 commands.

Claude Code plugin: token-optimized dev workflow — cached project context, pattern scanners, build & wiring verification, session persistence, self-review. 23 skills, 3 agents, 4 commands.

Claude Code plugin: token-optimized dev workflow — cached project context, pattern scanners, build & wiring verification, session persistence, self-review. 23 skills, 3 agents, 4 commands.

Claude Code plugin: token-optimized dev workflow — cached project context, pattern scanners, build & wiring verification, session persistence, self-review. 23 skills, 3 agents, 4 commands.

Claude Code plugin: token-optimized dev workflow — cached project context, pattern scanners, build & wiring verification, session persistence, self-review. 23 skills, 3 agents, 4 commands.

Workflow skills for AI coding agents: plan, execute, and maintain a persistent knowledge base across sessions.

Workflow skills for AI coding agents: plan, execute, and maintain a persistent knowledge base across sessions.

Workflow skills for AI coding agents: plan, execute, and maintain a persistent knowledge base across sessions.

Workflow skills for AI coding agents: plan, execute, and maintain a persistent knowledge base across sessions.

Workflow skills for AI coding agents: plan, execute, and maintain a persistent knowledge base across sessions.

Workflow skills for AI coding agents: plan, execute, and maintain a persistent knowledge base across sessions.

Workflow skills for AI coding agents: plan, execute, and maintain a persistent knowledge base across sessions.

Workflow skills for AI coding agents: plan, execute, and maintain a persistent knowledge base across sessions.

Agent-first Kometa skill library for Codex and Claude: generate, review, and debug Plex automation YAML for configs, collections, overlays, metadata, playlists, defaults, operations, and reports.

Production-grade quality skills for AI coding agents: red-first TDD, quality gates, and golden benchmark uplift loops.

Thin core + domain sets for a fast, stack-aware project start. Cross-agent (Claude Code, Cursor, Codex, Gemini) via the SKILL.md standard. MIT.

Thin core + domain sets for a fast, stack-aware project start. Cross-agent (Claude Code, Cursor, Codex, Gemini) via the SKILL.md standard. MIT.

Thin core + domain sets for a fast, stack-aware project start. Cross-agent (Claude Code, Cursor, Codex, Gemini) via the SKILL.md standard. MIT.