A Claude skill that turns a production AI agent incident into a golden eval case. The loop that feeds the two gates.

A Claude Code plugin that installs the two-gate method for production AI agents: a design gate, a ship gate, and an incident-to-eval loop that turns failures into regression tests.

A curated library of production-tested skills for building reliable AI systems with Claude Code. By Hamza Malik, hamz.ai.

Portable AI agent skills built on the open SKILL.md standard — self-contained capabilities any compatible agent can discover and load on demand, usable across Claude, Codex, Gemini CLI, Cursor, and GitHub Copilot.

Portable AI agent skills built on the open SKILL.md standard — self-contained capabilities any compatible agent can discover and load on demand, usable across Claude, Codex, Gemini CLI, Cursor, and GitHub Copilot.

Concurrent-agent benchmark suite packaged as a Hermes skill. Markdown REPORT.md output

A curated library of senior grade Agent Skills and subagents for Claude Code and OpenAI Codex. 70 skills, 30 dispatchable subagents, designed for multi agent orchestration.

Codex plugin for reproducible Blender modeling, validation, animation, MCP tooling, and agent benchmarking

Public Agent Skills library exported from skill-graph. Install: npx skills add jacob-balslev/skills

Public Agent Skills library exported from skill-graph. Install: npx skills add jacob-balslev/skills

Agent Skills.

AI skills for NMTC eligibility, bank-CDFI peer benchmarking & HMDA analysis — grounded in audited PyPI tools, not hallucinated.

Portable secure code review skill for AI coding agents — OWASP/CWE coverage, structured findings, and remediation guidance. Works with Cursor, Claude Code, Kiro, and Open Agent Skills.

Operational product-management skills and a /pm router for Codex and Claude.

Agent skills and eval utilities for reward-seeking, grader-targeting, and oversight-dependent behavior.

Agent skills and eval utilities for reward-seeking, grader-targeting, and oversight-dependent behavior.

Battle-tested Agent Skills for coding agents — source-grounded, failure-driven heuristics that audit and design real surfaces. Install with npx skills.

Claude Code skills for prototype-first, autonomous AI development — skip the PRD, dogfood the prototype, run automated eval loops, ship behind flags. Anthropic's playbook as installable Agent Skills.

Evergreen, generally useful Codex skills designed to stay valuable as models improve.

The most comprehensive Claude Code setup — 29 skills, 9 plugins, 13 hooks, 8 agents, 8 commands. Self-documenting, self-improving, CLI-first. Includes self-interview prompt for personalization.

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.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

10 production Claude Skills covering the full Google Ads diagnostic lifecycle: waste, spikes, Quality Score, budgets, reporting

Cookiecutter Template for an Agent Skills Marketplace

Cloudflare Workers MCP server: ai-eval

A curated collection of specialized skills and workflows designed to enhance Claude's capabilities in specific domains. These skills provide frameworks, psychological triggers, and structured processes to deliver high-quality, professional results.

Opinionated Next.js 16 starter for building with AI agents — ship features fast while architecture and directory structure stay under control: fixed structure, enforced conventions, curated libraries, preinstalled skills, native toolchain.

Scientific research extension for apex-unified - 149 scientific skills for biology, chemistry, medicine, materials research. Powered by Scientific Agent Skills (31.4k star).

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

Agent Skill Infrastructure: quality check, behavior test runner, version awareness

This repository stores reusable agent skills, repo level benchmark workflow material, and plugin bundles for coding agents.

This repository stores reusable agent skills, repo level benchmark workflow material, and plugin bundles for coding agents.

This repository stores reusable agent skills, repo level benchmark workflow material, and plugin bundles for coding agents.

This repository stores reusable agent skills, repo level benchmark workflow material, and plugin bundles for coding agents.

This repository stores reusable agent skills, repo level benchmark workflow material, and plugin bundles for coding agents.

This repository stores reusable agent skills, repo level benchmark workflow material, and plugin bundles for coding agents.

This repository stores reusable agent skills, repo level benchmark workflow material, and plugin bundles for coding agents.

This repository stores reusable agent skills, repo level benchmark workflow material, and plugin bundles for coding agents.

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.

Merged opencode config + agents + accomplishments showcase — 217 skills, 17 agent profiles, 6 MCP servers, 78-server registry

English hub of method-neutral legal AI skills (verification core, content quality, EU law) - bundle model. Polish-jurisdiction skills live in awesome-matematic-skills-pl.

Karvey — método spec-driven development agnóstico de stack (Afán, selknam). Plugin de Claude Code. © HainTech, Apache 2.0.

Skills personales de diseño frontend (taste, brutalist, minimalist, soft, etc.) + cross-agent sync para Claude Code, Codex, Cursor, Continue, Antigravity. SKILL.md compatible.

Claude Code skill that evaluates a thesis Theoretical Framework chapter against the OL646E (Malmö University SALSU) course rubric. Companion to thesis-anchoring-map.

75 production-grade agent skills for Hermes Agent + Paperclip — research, write, organize, earn, and run an AI workforce. Every skill passes a QA gate with hard safety rails. Built by Gen AI Hub.

TypeScript DDD Clean Architecture Skills

A Claude Code plugin packaging 23 skills, 8 agents, 5 event hooks, and 7 MCP servers for full-stack development with React 19, TypeScript, Express, Prisma, Tailwind CSS v4, and shadcn/ui.