general
claudecodexGeneral skills library: subagents, skill development, and git worktrees. From obra/superpowers.
8 skills
Every plugin for OpenAI Codex on GitHub — repos with a .codex-plugin/plugin.json or a Codex marketplace. Install with codex plugin marketplace add owner/repo then codex plugin add name@marketplace. Many work in both tools; see Claude Code plugins.
General skills library: subagents, skill development, and git worktrees. From obra/superpowers.
8 skills
基于 Markdown 任务契约的精简 CATLASS DSL 算子开发优化工作流。
7 skills
Architecture, executable planning, governed execution, and adversarial review for coding agents.
5 skills · 1 MCP server
Analyze real ad data, research markets, survey simulated buyers, and test marketing, sales, and product journeys through your agent.
5 skills · 1 MCP server
AI Inner OS 是一个面向 AI CLI 工具的插件,支持 Claude Code、Codex CLI、Cursor、OpenCode CLI。 它通过协议注入,让 AI 在正常完成任务的同时,额外输出一层可见的自由独白: ▎InnerOS:这仓库现在还像毛坯房,先把承重墙立起来再说。 不预设人格,不限制语气。AI 可以吐槽、得意、焦虑、冷笑、跳跃联想——或者什么都不说。独白是否出现,由 AI 自己决定。
4 skills · 1 command
Audit-closure governance skill for bounded, verified repository changes.
5 skills
StackHawk umbrella — one-command install of the default skill set (hawkscan, api, data-seed, optimize).
4 skills
Skills for a software developer agent to follow a strict Domain- and Test-Driven Development lifecycle.
4 skills
Agents and skills for creating, testing, and documenting Nextflow nf-core modules
1 skill · 3 agents
Motion forensics for the animated web. A Claude Code & Codex plugin that reverse-engineers a live URL into React + Tailwind — pulling real CSS + animation params from JS bundles (GSAP/Framer Motion/Webflow IX2) and verifying with AE/SSIM diff, not screenshots.
4 skills
Expose project-scoped upstream MCP tools through BM25, semantic, or hybrid search in one persistent local Ratel daemon.
2 skills · 1 MCP server · hooks
AgentWorks live messaging and person-controlled session attachment for Codex
2 skills · 1 MCP server · hooks
Structured argumentation with Arg2P: formalize problems as theories, solve them, and explore the results in its solver.
3 skills · 1 MCP server
Set of Claude Code skills for product development
3 skills
Set of Claude Code skills for product development
3 skills
Adaptive implementation-grounded learning for Claude Code.
1 skill · 1 agent · hooks
MeMesh — local collaboration for AI coding agents. Share memory across sessions, exchange task messages, and preserve work context. One SQLite file; no cloud required.
2 skills · hooks
Local, zero-token documentation discovery: live dashboard, heat maps, router fixes, and setup diagnostics
2 skills · hooks
Company-specific code practice guidance, scanning, and Codex hooks for Scala, Python, TypeScript, JavaScript, and Rust.
1 skill · 1 MCP server · hooks
AgentWorks: AI agents that own the work. Goals that chase a metric, and Crews your team asks from Claude, ChatGPT or Cursor. Open source.
2 skills · 1 command
Persistent semantic monitoring and rule delivery for Claude Code
3 skills
Connect Claude Code, ZCode, or OpenClaw to an operator-selected Titen MCP server.
1 skill · 1 MCP server
Multi-agent skill for faster workflows
2 skills
Configure, run, and interpret HawkScan DAST results inside Claude Code. Generates stackhawk.yml configs, runs scans via CLI or Docker, and transforms security findings into prioritized fix tasks for your coding agent.
1 skill · hooks
Build resilient backend services, AI agents, and workflows with Restate.
1 skill · 1 MCP server
Adversarial multi-model code review with dual Optimizer/Skeptic agents across Sonnet and Opus. Finds issues, challenges its own findings, and only auto-fixes what survives cross-model consensus.
2 skills
Audit scientific agent benchmarks and ProgramBench cleanroom tasks with BenchGuard Codex skills.
2 skills
Codex plugin for automatic Tripo-ready image-to-3D workflows with runtime dependency bootstrap, wallet-aware Tripo handoff, continuous post-image flow, widget-driven local preview, and selectable download formats.
1 skill · 1 MCP server
Monitor local coding-agent activity, adapter drift, executable identity, and unmatched provider events.
1 skill · hooks
Inject project rule files into Codex context through lifecycle hooks.
1 skill · hooks