skill-framework

The official skills marketplace for Agents Inc, an agent composition framework that builds stacks and compiles specialized subagents for Claude Code

9 humanity skills for AI agents — crisis detection, WCAG audits, empathy, cultural sensitivity, and more. MCP + npm.

The Kaizen System is a five-layer approach (SAVMI) to continually improving workflows for agentic coding work. It can be used by humans, Codex, Claude, local models, or multi-agent workflows. Like a delicious 5 layer (original) burrito, you'll keep coming back for more... improvements.

Multi-agent AI skill orchestration — 13 skills, 7 lifecycle phases, from idea to post-release. Works with Claude Code, Codex, Gemini CLI, Cursor, Windsurf, OpenCode, and any agent that reads Markdown or speaks MCP.

Behavioral execution framework for AI agents — define deterministic, portable skills & agents across OpenCode, Claude Code, Gemini CLI, and Qwen Code.

Safety-hardened fork of obra/superpowers. Same skills library, plus a mandatory safety-check preflight (5 hard gates) before any skill runs. Defends computer, hardware, budget, and data.

L0-L4 AI Agent Skill Governance Framework - 200+ Skills, YAML Templates, Classification System

A universal skill to keep your agent workspace clean and organized

zao-skill: AI meta-skill framework - design, verify, evolve production-grade agent skills

TypeScript toolkit for building, validating, and shipping Agent Skills. Marketplace for skills, prompts, agents, and MCP servers.

MBDF-FLV: Multi-Book Distillation Framework with Four-Layer Verification. Distill N books (N>=3) on the same domain into executable agent skills. Pure methodology, blind-validated evaluation protocol (v1.1.7 CLOSED).

Composable Agent Skills suite for senior-level Python development: 12 single-responsibility skills (architect, coder, reviewer, security, performance, async) with handoff contracts, deterministic stdlib-only tooling, and LLM-as-judge evals for opencode, Claude Code, Codex CLI, Trae, Kilo.

Execution protocol for AI coding agents. Complexity routing, phase gates, TDD, evidence grading, verification gates, multi-persona review.