Agent skills to keep AI instruction files (AGENTS.md, CLAUDE.md, MEMORY.md) lean. Guardian runs before edits to prevent bloat; cleanup restructures bloated files. Works with any AGENTS.md-aware tool.

Curated agent skills, conventions, and workflows for building React Native apps with AI coding agents.

Biomedical SCI manuscript architecture skill with corpus-driven terminology and style profiling

Loadable skill and scaffold for building source-grounded agent harnesses

Publish local agent skills as clean, installable, promotion-ready single-skill GitHub repositories.

Skills for coding agents: engineering review, loop referee, skill auditor, unclebob. One SKILL.md per skill. Copy a folder and it works in Claude Code, Codex, or Cursor.

Auto-version local config files via git + OS file watchers. A drop-in skill for AI coding agents (Claude Code, Codex, Gemini CLI, etc.).

Prompt X-Ray for AI agent prompts and skills

Multi-Document Co-driven Agent Workflow for Claude Code — stop your docs from rotting. 中英文双语

Agent OS is a management layer for complex, multi-agent AI projects. Instead of letting agents get lost in endless conversational loops, it enforces a disciplined workflow: upfront planning, shared context, scoped work tracks, and strict quality gates — so every agent stays focused, coordinated, and aligned from start to finish.

Public skill library, workflows, tools, and references for AI-assisted development.

Curated AI skills and Claude Code plugins — reusable, versioned prompt templates and tools (skillshare/Codex compatible)

Agent skill repository that don't fit cleanly into any of my other cheese-related repositories

Agent Skill teaching AI coding agents to drive Apple Simulators via Evan Bacon's serve-sim — taps, gestures, hardware buttons, rotation, camera injection, and stream handoff to the host's preview pane (Claude Code, Cursor, Codex, ...).

A Skill for AI Agents to gather On This Day entries from Day One, create an analysis, and upload it to Readwise Reader shortlist.

Source-aware architecture guidance for business-domain systems using Domain-Driven Design, Layered Architecture, Onion Architecture, Hexagonal Architecture / Ports and Adapters, and CQRS.

🔍 Auditoria de segurança defensiva para Agent Skills (Claude, OpenClaw). Detecta payload em archives, ASCII smuggling, supply chain attacks e meta-prompt injection. Alinhado a OWASP ASI 2026 + AST01. Camada 1 da defesa em profundidade.

Agent skills for the reopt ecosystem — CLI workflows, Brandapp SDK install/review, and @reopt-ai/opt-* component package setup. Installs into Claude Code, Cursor, Codex, Cline, Gemini CLI, and more via skills.sh.

Official Agent Skills for integrating Masheev into your applications

A structured AI coding workflow with skills, agents, and commands that make AI think before it builds.

Static analysis for AI automation workflows. Find prompt-injection paths, overpowered tools, and write-capable agent jobs before they run.

A Claude Code skill that turns a rough app idea into a complete, optimized build kickoff package — spec, build prompt, feature sequence, and workflow. Grounded in Anthropic's prompting best practices.

Portable Agent Skills for coding agents: Git workflows, linked worktrees, GitLab MRs, Cloudflare DNS, and agent context files.

Engineering craft for Claude Code — TDD, verification, code quality, and SDLC discipline.

Agent skills for profiling and optimizing mobile app performance (startup, memory, frame-rate, network).

Production-tested agentic skills for Claude, Copilot, and the Agent SDK. Born in real businesses.

Portable Markdown skill for AI vibe coding with automation: SaaS workflows, API integrations, triggers, permissions, retries, monitoring, and GitHub automation.

AI Agent Skills for Argo CD, Rollouts, Workflows, and Events — knowledge, repo auditing, cluster debugging, and operations

Auditable, self-contained migration skills for upgrading JS/TS projects to pnpm 11 with supply-chain-hardened defaults. For Claude Code and Codex CLI.

A system prompt that forces AI to think like a Senior Software Engineer: solving real problems, avoiding XY issues, and handling edge cases before coding.

Ai skills for Frida dynamic instrumentation across Android, iOS, native hooks, agents, and troubleshooting

A professional agent skill for code-review agents that need to decide whether backward-compatibility logic is still required or has become removable technical debt.

Run CSTS/ISTQB/ISO-aligned QA, tests, and remediation loops for vibe-coded AI software

Genetic exploration of solution spaces for AI coding agents (Claude Code, Gemini CLI, GitHub Copilot, OpenCode) — gather a verifiable objective, evolve variants, apply the winner.

Codex and Claude Code plugins for agent-bus: local message bus for AI agent-to-agent communication. Bundles the MCP server, slash commands, and the universal Agent Skill.

KRKN's Personal AI workspace • Skills / Prompts / ...

Inspect, find, and review your installed Agent Skills across Codex and Claude Code.

A code reviewer with strong opinions and no patience. Agent Skill that turns Claude/Codex/Copilot into Klaus Reinhardt — a 32-year-veteran senior dev who deletes LLM slop.

AI agent skill pack for SDLC governance: Codex/Claude Code skills for requirements, architecture, tech stack, API/DB design, verification, and testing.

Custom agent skills for Claude Code, Codex, Cursor, and more. Install via npx skills@latest add niftymonkey/skills

Agent Skill for Claude and OpenAI Codex — break big, risky work into sequenced, self-contained prompts you run across separate chats, plus paste-ready handoffs.

A collection of portable agent skills by Eagerworks — install via the skills.sh CLI for Claude Code, Cursor, Copilot, Codex, Amp, and more.

Agent Skills documentation and examples for the Jido ecosystem

Agent Skill for orchestrating platform-provided subagents, delegated workers, and serial fallback reviews.

SeaArt skills for AI coding agents: prompt building, GPT Image workflows, preflight advice, and storyboard planning for creative image and video generation.

ConardLi/garden-skills 仓库的研究笔记 — 拆解 4 个 skills 背后的整体设计哲学

Single-blind review skill — context-free document audit with optional devil's advocate. Part of the Liangyi skill family.

Pressure-test any decision through five independent advisor subagents + a Chairman verdict — a Claude Code plugin & Agent Skill.

Build your own personal AI Operating System — a clonable Claude Code template with onboarding, a self-auditing health check, builder skills, and a Karpathy-style knowledge wiki. Includes a bilingual class teaching package.

skill and agent to make your ai strong in git , git lab, github,azure devops

ACP is a reusable democratic coordination primitive for discussion under load. Relay is the reference implementation used to validate that primitive in practice.

Portable SWE harness plugin for Codex and Claude Code

Modular AI Agent Skills for agent-lx-music (alx) CLI, compatible with Hermes, OpenClaw, Codex, and npx skills

Turn a ticket into a verified, deployed PR — wraps OpenAI Codex CLI's /goal Ralph loop with a 4-file durable spec, 4 HUMAN GATE approval tokens, and a one-line installer for Claude Code, Codex CLI, and .agents/skills/.

High quality skills for AI agents to automate PRDs, implementation and daily engineering tasks.

Skill that turns any rough idea (TR/EN) into a domain-classified, quality-reviewed expert prompt.

AI-native software engineering operating system for modern application architecture, scaffolding, and AI-assisted development.