Supervised Codex and Claude Code handoff workflow packaged as a project-local Agent Skill.

一个可运行的蓝图：在 AWS 上搭建企业私有、可治理的 AI 资源注册中心 —— 基于 Amazon Bedrock AgentCore Registry + AWS CodeArtifact。

A lightweight ownership protocol for coordinating Codex, Claude Code, and other coding agents without file-scope conflicts.

A collection of elite, modular, and validated AI agent skills and system rules for Google Antigravity.

Claude Code skill for semantic congruence auditing — verifies that what an AI agent says, writes, or documents actually matches what the project does.

Production Ready Check Skill for Agent Skills standard. Automates dependency discovery, skill/MCP installation, auth handling, integration verification, and full production + security audit for any application.

agentic workflows and skills

Custom Cursor AI agent skills for mobile QA workflows — bug creation, JIRA refinement, RC revalidation, crash analysis, and build installation. Built for a large consumer mobile app (iOS/Android).

Auditable, portable agent skills that turn open-source maintenance - review, debugging, verification, handoff - into repeatable workflows for Codex, OpenCode, and Pi

Every agent leaves a paper trail. Tamper-evident JSONL audit logs for agentic workflows.

Huawei network device (USG firewall + S/CE switch) CLI skills pack for OpenClaw AI agent — also usable as a standalone cheatsheet.

Rigorous multi-agent deep-dive analysis for Claude and OpenAI Codex — audits codebases, evaluates strategies/designs, tackles open research via parallel specialists → synthesis → adversarial red-team.

Claude Code skill that delegates large, mechanical code generation to a local LM Studio model

Intent-anchored reading skill - learn a codebase another agent built, with a Feynman/plain-speech gate on every output.

A reusable control-plane pattern for using Codex to build, maintain, and verify Hermes-powered messaging-agent systems.

GenPark/OpenClaw skill: Implement OpenAI & Stripe's Agentic Commerce Protocol (ACP) for capability negotiation, cart management, and Stripe Payment Token payments.

Build & audit AI agent skills from plain English

16 agent skills to validate software ideas before you build — Mom Test interviews, JTBD, market research, pretotype tests, unit economics, and go/no-go scorecards. For Cursor, Claude Code & skills.sh.

Refine an Agent Skill via the skill-forge judge → hitl loop, in a sandboxed Docker container. npx-installable.

Render JSON slide specs into native editable PowerPoint decks through desktop PowerPoint COM automation.

Portable AI agent skills and specialist subagents for prompt enhancement, workspace resume, source-grounded research, and release readiness.

Agent skills for WhatsApp: send messages, manage channels, and monitor webhooks via AI agents.

Official MonoCloud Agent Skills repository.

A reusable codebase-orientation skill for Claude Code and Codex.

The 2muchcoffee NestJS engineering manifesto plus drop-in agent skill files for Claude Code, Cursor, and Codex.

Agent Skills for writing, reviewing, and safely executing production SRE runbooks.

Centralized manifest for AI agent skills. Synced via ai-agent-skills.

Agent governance as a skill. Stops AI agents from quietly turning local fixes into architecture debt.

Seamlessly hand off work between Claude Code and OpenAI Codex via a shared HANDOFF.md document

A Claude skill that turns a startup idea into a VC-ready strategy doc and pitch deck. Describe the idea in a sentence; it researches, stress-tests the thesis, and writes the documents.

MOVED: This skill is now maintained at https://github.com/knowingrohan/ai — see skills/refine-prompt/

Agentic, structured product discovery for AI-native delivery teams.

Parallel AI coding sessions on the same git repo, via worktrees

Personal APM marketplace — skills, prompts, agents, and instructions for AI coding agents

Reconciled Spec-Driven Development — a reasoning cascade that keeps spec and code aligned. Extends github/spec-kit with the artifact↔code reconciliation arc.

No-bullshit Harness Engineering advisor for real projects. Auto-detects gaps, knows when to shut up.

Employee-style agent skills for first-principles engineering review and multi-agent coordination.

Public agent skill for reverse engineering reusable patterns from skills, workflows, repos, and tools.

Agent Skill: draft or publish to X/Twitter through a clean Chrome profile (Kimi WebBridge), without touching your main Chrome extensions. Works in Claude Code, Codex CLI, OpenCode, Cursor.

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

My personal pi harness configuration.

a claude code skill that runs a council of models on your question. each member gets its own personality, they critique each other anonymously, and a chairman picks the best-argued answer (not a yes-man average). ported from karpathy/llm-council.

Agent skills for AI coding assistants — follows the agentskills.io format, works with Claude Code, Codex, Cursor, Copilot, and 20+ agents

Agent skill to generate Udemy Practice Test CSV files from any input (text, PDF, URLs). Real exam-like questions with proper explanations in bulk upload format. Compatible with skills.sh and skillsmp.com

Elixir content for agents to assess and improve Elixir design and implementations

iEvo — self-evolving plugin for Claude Code. Capture lessons, patch local agents and skills, replay logs on upstream updates.

GenPark skill: Automate character creation and roleplay interactions using JanitorAI.

Author and audit Agent Skills (SKILL.md) for any agent that supports the agentskills.io v1 spec

Multi-agent skill-orchestrated system for unit test training data quality assurance (BUAA SE 2026 final project)

Agent Skills repository for skills created by our AI agents.

Speed up your App Store release with the asc CLI tool

148+ curated Claude AI skills — agent orchestration, security, multi-repo PRs, design, mobile & more. One-command install.

GitHub-centered delivery workflow agent skill.

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

Claude Code plugin + npm base for AI-assisted engineering: 25 skills, 12 agents, slash commands, session-continuity hook. Also works with Copilot, Cursor, and others.

Power Automate authoring agent skill

Reusable skills for local-first agent workflows.