A latticework of thinking, strategy, and analysis frameworks packaged as model- and harness-agnostic agent skills (SWOT, Porter's Five Forces, OKR, Cynefin, and 50 more).

AI-first workspace bootstrapper — installs skills, packs, agents, and disciplines into .agents/. Cross-compatible with Claude Code and OpenCode.

Agent skills for the MeisterTask and MindMeister MCP servers

Custom Claude Code skills spanning UI/UX, productivity, and developer tooling

OllyGarden's opinionated AI agent skills for OpenTelemetry and observability workflows

Comprehensive skills system for Cursor IDE with mandatory expertise enforcement, automatic skill discovery, multi-agent coordination, and persistent learning. 220+ skills across 10 categories + 8 custom orchestration rules.

Personal agent skills

A specification framework for agentic development. Agents build from complete specs - not guesses.

A specification framework for agentic development. Agents build from complete specs - not guesses.

Spec-driven AI development lifecycle for Claude Code — spec-kit + AI-DLC fused, with hook-enforced human-approval gates. Installable plugin + marketplace.

Selected agent skills

full-stack development lifecycle

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

Portable, reusable instruction packages for AI coding assistants.

Vibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.

High-agency agent skills for executable specs and end-to-end shipping.

An operating system for engineering: durable, opinionated playbooks (Agent Skills) for software architecture, AI/agentic systems, product engineering, and technical leadership. Read by humans, loaded by any LLM/agent.

A coordinated library of Claude skills with explicit phase/handoff routing, shared state, and a maker/checker loop.

Custom skills and prompts for Claude Code based on my personal workflows.

SEC API agent skills for source-cited filing research with hosted API and MCP workflows

Reusable public SKILL.md workflows for AI agents

Unified dynamic-host agent collaboration policy and signed-runtime client

A comprehensive SWE workflow, encoded. Might be useful to you too.

A comprehensive SWE workflow, encoded. Might be useful to you too.

A comprehensive SWE workflow, encoded. Might be useful to you too.

AI operating system for product managers. 65 Claude Code skills, 7 multi-perspective review agents, a memory system. Battle-tested in real PM work.

システム開発・個人開発の全工程(企画〜設計〜実装〜運用〜マネタイズ)をカバーするClaude Code用スキル集

システム開発・個人開発の全工程(企画〜設計〜実装〜運用〜マネタイズ)をカバーするClaude Code用スキル集

Trust contracts for AI agent skills: JSON Schema risk tiers, tool permissions, deny-by-default egress, approval gates, prompt-injection fixtures, ~28 CI validation gates. Apache-2.0.

A reliable engineering partner for Claude Code — ship features that make the next one faster, then curate what you've built.

My Claude Code plugins, one repo, any machine: a universal coding-discipline skill and 15 foundational build-from-scratch skills behind one orchestrator.

A production-grade .claude folder for Claude Code: 40 lifecycle skills, agents, commands, and hooks — with reflexive skill routing and always-on engineering disciplines (verify, no-bloat, continuous-git, memory, ship-fast).

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

Public reusable skill hub for agent workflows

A Claude skill that decomposes an AI-built or unfamiliar project into learnable knowledge points — so you can explain it, trust it, and own it.

Five open agent skills for sharper literature reviews: question refinement, review modules, method comparison, contradiction mapping, and research gap discovery.

Portable, reusable Agent Skills library for coding workflows.