Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,926 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Use Rozenite for Agents to inspect React Native DevTools data and Rozenite plugins on a live app target, either through shell-driven rozenite agent commands or programmatic @rozenite/agent-sdk usage. Trigger this skill for any task that needs live app inspection, debugging, or plugin interaction through Rozenite.
Skill Claude CodeCodex
Check a price change, stock change, order, refund or return against the merchant's margin, stock and refund policy before acting. Use before any commerce action on Walmart, Shopify, Adobe Commerce or Business Central.
xiaohuailabs/xiaohu-video-translate
Skill Claude CodeCodex
A video transcription and translation tool that turns subtitles or audio into Markdown documents. For translated videos, it transcribes the audio, translates the subtitles, and burns Chinese subtitles into the video.
Skill Codex
A Chinese-language writing workflow for producing structured academic theses, graduation projects, technical reports, and course papers. It can use real project code, school templates, sample papers, references, diagrams, screenshots, and Word documents.
Skill Claude CodeCodex
Use when the user asks for any draw.io diagram — cloud architecture (AWS, Azure, GCP, Databricks, multi-cloud, hybrid/DR, landing zone, VPC/network, serverless, data pipeline) or a business process (BPMN, swimlane, workflow with roles). Builds with the drawio-ai layout engine using real stencils, validates, and runs a…
Skill Claude CodeCodex
Generate API documentation from source code, supporting REST APIs, GraphQL, and various documentation formats.
MCP server Claude CodeCodexCursor +2
Attestix - AI agent identity and signed evidence tooling. DID-based identity, W3C Verifiable Credentials, governance evidence, delegation chains, and reputation scoring. Runs locally from the attestix Python package.
Skill Claude CodeCodex
Work in the Tura agent-runtime repository. Use for Tura architecture, Rust backend, GUI/TUI, prompts, commands, providers, sessions, documentation, tests, packaging, and release work in this directory.
Skill Claude CodeCodex
Generate CodMate slash command drafts from requirements.
Skill Claude CodeCodex
Backup and restore all OpenClaw configuration, agent memory, skills, and workspace data. Part of the MyClaw.ai (https://myclaw.ai) open skills ecosystem — the AI personal assistant platform that gives every user a full server with complete code control. Use when the user wants to create a snapshot of their OpenClaw…
Gentleman-Programming/Gentleman-Skills
Skill Claude CodeCodex needs its repo
Electron patterns for building cross-platform desktop applications. Trigger: When building desktop apps, working with Electron main/renderer processes, IPC communication, or native integrations.
Skill Claude CodeCodex
Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when…
MCP server Claude CodeCodexCursor +2 ✓ vendor
Neon's hosted MCP server: lets the agent create and manage Neon Postgres projects, branches and databases and run SQL. Remote server at mcp.neon.tech.
Skill Claude CodeCodex
Direct browser control via the Browser Use Terminal CLI. Use when the user wants to automate, scrape, test, or interact with web pages — you drive the browser yourself with Python helpers.
meleantonio/awesome-econ-ai-stuff
Skill Claude CodeCodex
Build and solve Walrasian general equilibrium models with theory derivations and Julia computation.
Skill Codex
A skill for controlling a live Nebula terminal workspace from an AI coding agent. It can work with panes, tabs, files, commands, and other Codex or Claude agents.
Skill Claude CodeCodex
Use when writing or revising scientific manuscripts, abstracts, figures, or references for journal submission and you need full-paragraph prose, scientific structure, citation-style guidance, or reporting-guideline support.
Skill Claude CodeCodex
Detect whether a passage shows AI-like writing signals and return an explainable risk estimate with confidence, caveats, and next steps.
Skill Codex
Use when the agent is running inside yolobox and needs to orient itself to the current sandbox, trust model, runtime/config, mounts, network mode, readonly/output paths, Docker access, forwarded env keys, or other environment constraints and freedoms. Also use when the user explicitly invokes /yolobox.
YuJunZhiXue/StudyAnalysis-Skills
Skill Claude CodeCodex
A Chinese-language workflow for deeply analysing links, documents, or code and turning them into teaching notes for beginners through advanced readers. It also checks claims against source material and flags possible hallucinations or outdated information.
Skill Claude CodeCodex ✓ vendor
Run and interpret SkillEvaluator for agent skills. Use for any skill benchmark or eval - validating or scoring a SKILL.md, writing evals.json test cases or evals config, explaining benchmark reports, verdicts and exit codes, or gating skills in CI.
Skill Claude CodeCodex
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers queries against the corpus, lints the graph for health, and audits in-context human feedback filed from Obsidian or the local…
Skill Claude CodeCodex
Create or update ZeptoClaw skills. Use when designing, structuring, or authoring new agent skills.
Skill Codex
Legacy compatibility entry. Use only when design-in-figma is not installed; otherwise use design-in-figma. Create or update native, editable Figma designs with TemPad Dev MCP: screens, flows, components, and requested local design-system resources, including on an empty canvas. Use when asked to create, mock up, or…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: