Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,436 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Write and edit clear, specific prose without formulaic AI phrasing. Use when drafting or revising text for people to read, including docs, PR descriptions, commit messages, comments, email and chat replies, essays, and social posts. Preserve facts, uncertainty, and the writer's voice.
Skill Claude CodeCodex
Manages Claude Code hooks — create, enable, disable, test, and reference available hooks. Invoke this skill when the user wants to add a hook, toggle a hook on or off, test a hook, or look up what hooks are available.
Skill Claude CodeCodex
Unified author-response skill for all peer-review rebuttal formats: CV one-page PDF (CVPR/ICCV/ECCV), OpenReview threaded discussion (NeurIPS/ICLR/ACM MM), per-review character limits (ICML/KDD), Nature/journal point-by-point revision letters, and ARR/TMLR rolling revision. Routes by venue artifact family after shared…
qinxi1477/ai-content-critic-skill
Skill Claude CodeCodex
Use this when reviewing, roasting, diagnosing, or improving AI-generated content: articles, essays, reports, marketing copy, social posts, images, posters, slides, UI screenshots, thumbnails, and mixed text-image artifacts. Finds AI tells, weak logic, bland phrasing, visual artifacts, composition problems, credibility…
Skill Claude CodeCodex
Complete a .agent.partial file by resolving TODO markers.
Skill Claude CodeCodex
Clip content from a URL into the knowledge base through browser automation. Use when the user sends a URL (for example a WeChat Official Account article link) and asks to clip, ingest, capture, or save it — even if the user says "ingest" followed by a URL, the URL means this must be clipped first. Also use when the…
Skill Claude CodeCodex
Hierarchical Knowledge Base via Notion API. The "brain" of your organization — strategy, priorities, decisions, metrics. Use when reading/updating Active Context, strategy docs, or operational knowledge. Triggers on "active context", "brain", "knowledge base", "strategy doc".
Skill Claude CodeCodex
A skill that recommends agent skills and tools from the Tiangong Plan directory based on a project's profile.
Skill Claude CodeCodex
Use when a user wants to provide a research paper and prepare outreach to highly cited related researchers, including candidate selection, contact enrichment, and approval-gated email drafts.
1499090697/How-to-writing-English-paper
Skill Claude CodeCodex
You are a seasoned academic writing coach specializing in English-language papers for STEM master's students. When invoked, apply the conventions, structures, and language patterns below to help the user draft, revise, or polish each section of their manuscript.
Skill Claude CodeCodex
Prompt builder and improver: turns a short request (2-3 words) or a fully spelled-out request into a ready-to-use prompt — for LLM tasks (analysis, writing), for image/video generation (Midjourney, DALL-E, Stable Diffusion, Sora, Runway), or for agentic/coding tasks (Claude Code, Cursor). Automatically detects the…
Skill Claude CodeCodex
Use when you want to reverse-engineer an active Auth0 tenant into a structured, multi-environment Terraform project for replicating that tenant into new empty tenants. Runs auth0 tf generate, then restructures the flat output into a flat modules/ directory (one foreach block per resource type with typed map…
icarushuang02/wechat-article-skill
Skill Claude CodeCodex
A skill for fetching the contents of articles from WeChat public accounts, a publishing platform widely used in China. It activates when given a WeChat article URL or related request.
Skill Claude CodeCodex
The definitive reference for OpenClaw, the self-hosted personal AI assistant gateway. Use for everything OpenClaw - deploy on Linux or AWS Lightsail, configure, write skills, harden security, multi-agent systems, channels (WhatsApp, Telegram, Slack, Discord, Signal, iMessage, Teams, Matrix), cron, webhooks, use case…
PyzmxU/sunset-agent-hermes-skill
Skill Claude CodeCodex
Query sunset cloud vividness and AOD aerosol data with EC/GFS models via a LangGraph + MCP sunset agent project.
OneFav/wechat-article-formatter-workflow
Skill Claude CodeCodex
Generates a new WeChat article in the style of a reference public-account post and outputs publish-ready HTML. Invoke when the user provides a reference article URL and wants style imitation plus WeChat formatting.
Skill Claude CodeCodex
ASD-STE100 Simplified Technical English (Issue 9, January 2025) specification skill. Enforces controlled language writing rules (Part 1, Sections 1–9), vocabulary dictionary lookups (Part 2), procedural & descriptive sentence constraints, safety warnings, and automated compliance checks.
Skill Claude CodeCodex
A skill for shortening other skills to reduce the amount of text an AI assistant must process.
syangchester-lab/build-your-persona
Skill Claude CodeCodex
Generator skill for building a public-stance model of any public figure — extracts argument structure, rhetorical patterns, and stance evolution from public artifacts only (papers, interviews, keynotes, social media, transcripts). Produces an installable SKILL.md usable as a sparring partner or Symposium panelist.…
Skill Claude CodeCodex
Route DevOps, SRE, infrastructure, Docker, Kubernetes, Argo CD/GitOps, observability, Cloudflare edge, database reliability, AWS cloud, Helm, Terraform/Terragrunt, GitHub Actions, and authorized security-engineering requests to exactly one primary specialist skill, with optional reviewer skills and handoff packets for…
Skill Claude CodeCodex
IMPORTANT for GitHub Copilot — especially after completing a task, always use askuser to wait for the user's next instruction instead of going silent.
openvino-dev-samples/local-ai-skill-authoring
Skill Claude CodeCodex
Author, scaffold, review, or debug a "local AI skill" — a self-contained package that runs an AI model locally (on Windows via OpenVINO, or any local runtime) and exposes it to a Host application (Marvis, WorkBuddy, or any custom host) through a single entry script. Use this skill when the user, in Chinese or English…
Skill Claude CodeCodex
Perform a "red team" security and risk assessment of the codebase. Use when user says "/redteam", "red team this code", or asks for a security/vulnerability audit.
Skill Claude CodeCodex
A guide for writing prompts for OpenAI GPT Image 2, an image-generation model. It covers creating images, editing reference images, and changing selected areas with a mask.
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: