Beginner-first agent skills that turn 'I want to learn X' into a 30-day path, tutor loop, projects, and learning memory.

Skills for tracking fast-moving research without drowning in arXiv, benchmarks, and lab updates.

Skills for checking claims, auditing sources, detecting hallucinations, and labeling uncertainty.

26 repository-agnostic engineering skills for Claude Code — debugging, design, review, validation, and AI engineering as operational runbooks.

Agent evals on autopilot: find quality bugs in your AI agent, ship a targeted fix, and prove it on a held-out set. Zero-dependency Agent Skill + CLI.

Agent evals on autopilot: find quality bugs in your AI agent, ship a targeted fix, and prove it on a held-out set. Zero-dependency Agent Skill + CLI.

Agent evals on autopilot: find quality bugs in your AI agent, ship a targeted fix, and prove it on a held-out set. Zero-dependency Agent Skill + CLI.

Find broken and risky Codex or Claude Code skills locally

Find broken and risky Codex or Claude Code skills locally

Handy AI skills

Validate AI coding assistant skills against the Agent Skills specification (agentskills.io) — a dependency-free validator with fix hints, plus skills for auditing instruction quality and tuning description triggering.

31 GPU inference profiling and optimization skills for Claude Code, with a bundled MCP server

Personal plugin marketplace of Claude Code skills (slash commands)

An LLM wiki for Obsidian: a markdown knowledge base your AI agents compile and maintain under written law. 32 skills for Claude Code and Hermes, a zero-dependency Python CLI, and a vault template governed by an 11-law constitution.

Free mini-eval and scorecard for AI coding agents: Claude Code, Codex, Cursor, Copilot, Windsurf.

Remote MCP for Gemini upgrade evals, prompt regressions, output diffs, and eval receipts.

Installable agent skills (SKILL.md) for government contracting. Claude Code plugin + copyable playbooks driving the CLEATUS MCP server.

🦾 My own little curation of skills

A modular PMO & release-management platform for Claude Code: skills, governance disciplines, and a 13-stage release pipeline.

Pre-wired Claude Code workspace: Next.js 16 + AI SDK 7 + shadcn/ui + Tailwind v4 + DuckDB, with Skills & MCP servers ready on clone.

Prove whether a SKILL.md actually changes agent behavior (with/without) and which CLI harness does a task best — agent-native subagents or CLI. agentskills.io-compatible. Site: https://cskwork.github.io/skill-ab-eval/

Legible, deterministic QC/qualification for bio-AI tool outputs — named-reason contracts + agent skills that compose with NVIDIA BioNeMo.

Prompt optimizer & compiler for Claude Code — intent mining, genre-aware skeletons, multi-candidate + LLM-judge eval. Text / image / video prompts (Midjourney, Seedance, Sora, Kling). 新手友好的提示词优化套件

A standardized testing harness for MCP servers and agent workflows

Central library for AI coding context: steering files, AGENTS templates, reusable skills, scaffold scripts, and guided setup for new or existing projects.

Open agent skills for the skills.sh ecosystem — browser, docs, mail, media, security, networking, orchestration, and more.

Open agent skills for the skills.sh ecosystem — browser, docs, mail, media, security, networking, orchestration, and more.

🛒 Skill Bazaar — an all-in-one open collection of AI Agent Skills (SKILL.md), organized by category. Part of the Mega AI Bazaar.

Honest AI work evaluation for Claude Code — two-axis scoring with anti-inflation mechanisms

Neural distance heuristics + GPU/TPU beam search for the CayleyPy IHES Picture Cube and Megaminx puzzles

Claude Code skills for running models cost-effectively: security gates (secret scanner, commit-gate), model-quality tooling (eval harness, token-squeeze, compact-io, opus-workers), review/advisory (trusted-advisor, audit, skill-vet, research-brief), and a read-only reorg-proposal advisor.

ACT-Edition brain template for AI coding assistants — critical thinking, epistemic calibration, and structured reasoning

Stop Claude Code from hallucinating — Karpathy-grade discipline in 8 skills

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

A collection of AI skills created for me

OPC-Skills — AI 一人公司（One-Person Company）Claude Code 技能合集。一个人 + AI = 一支团队。战略/法务/内容/文档等虚拟部门，18 个开箱即用的 AI 技能。

ASO & app-market research skills for AI agents — Claude Code, Cursor, and any MCP client. Install: npx skills add getappniche/aso-skills

Zeoel-AI is a production-grade, multi-agent SaaS software engineering agency. Instead of single, fragile LLM prompts that lose context, Zeoel-AI coordinates a complete team of 33 specialized agents (UX designers, database architects, systems engineers, security auditors, QA engineers, etc.) to brainstorm, plan, build, and verify entire software.

Zeoel-AI is a production-grade, multi-agent SaaS software engineering agency. Instead of single, fragile LLM prompts that lose context, Zeoel-AI coordinates a complete team of 33 specialized agents (UX designers, database architects, systems engineers, security auditors, QA engineers, etc.) to brainstorm, plan, build, and verify entire software.

Zeoel-AI is a production-grade, multi-agent SaaS software engineering agency. Instead of single, fragile LLM prompts that lose context, Zeoel-AI coordinates a complete team of 33 specialized agents (UX designers, database architects, systems engineers, security auditors, QA engineers, etc.) to brainstorm, plan, build, and verify entire software.

23-agent AI development team for Claude Code, Cursor, and Gemini CLI. Multi-agent orchestration framework with strict TDD, sprint planning, 420+ skills, and automated QA/security/SEO audits. Stop vibe-coding — start shipping production-grade software.

23-agent AI development team for Claude Code, Cursor, and Gemini CLI. Multi-agent orchestration framework with strict TDD, sprint planning, 420+ skills, and automated QA/security/SEO audits. Stop vibe-coding — start shipping production-grade software.

23-agent AI development team for Claude Code, Cursor, and Gemini CLI. Multi-agent orchestration framework with strict TDD, sprint planning, 420+ skills, and automated QA/security/SEO audits. Stop vibe-coding — start shipping production-grade software.

23-agent AI development team for Claude Code, Cursor, and Gemini CLI. Multi-agent orchestration framework with strict TDD, sprint planning, 420+ skills, and automated QA/security/SEO audits. Stop vibe-coding — start shipping production-grade software.

23-agent AI development team for Claude Code, Cursor, and Gemini CLI. Multi-agent orchestration framework with strict TDD, sprint planning, 420+ skills, and automated QA/security/SEO audits. Stop vibe-coding — start shipping production-grade software.

23-agent AI development team for Claude Code, Cursor, and Gemini CLI. Multi-agent orchestration framework with strict TDD, sprint planning, 420+ skills, and automated QA/security/SEO audits. Stop vibe-coding — start shipping production-grade software.

23-agent AI development team for Claude Code, Cursor, and Gemini CLI. Multi-agent orchestration framework with strict TDD, sprint planning, 420+ skills, and automated QA/security/SEO audits. Stop vibe-coding — start shipping production-grade software.

23-agent AI development team for Claude Code, Cursor, and Gemini CLI. Multi-agent orchestration framework with strict TDD, sprint planning, 420+ skills, and automated QA/security/SEO audits. Stop vibe-coding — start shipping production-grade software.

23-agent AI development team for Claude Code, Cursor, and Gemini CLI. Multi-agent orchestration framework with strict TDD, sprint planning, 420+ skills, and automated QA/security/SEO audits. Stop vibe-coding — start shipping production-grade software.

23-agent AI development team for Claude Code, Cursor, and Gemini CLI. Multi-agent orchestration framework with strict TDD, sprint planning, 420+ skills, and automated QA/security/SEO audits. Stop vibe-coding — start shipping production-grade software.

23-agent AI development team for Claude Code, Cursor, and Gemini CLI. Multi-agent orchestration framework with strict TDD, sprint planning, 420+ skills, and automated QA/security/SEO audits. Stop vibe-coding — start shipping production-grade software.

23-agent AI development team for Claude Code, Cursor, and Gemini CLI. Multi-agent orchestration framework with strict TDD, sprint planning, 420+ skills, and automated QA/security/SEO audits. Stop vibe-coding — start shipping production-grade software.

22 production-tested Claude Code skills: code review, planning, session audits, skill builders, and more.

22 production-tested Claude Code skills: code review, planning, session audits, skill builders, and more.

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

Extend Go coding assistants with reusable skills for language, testing, security, and observability in production-ready Golang projects

my agent skills

my agent skills

my agent skills