Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,015 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Use when the user asks to build, edit, debug, or run a wick workflow — a multi-step automation stored as a graph of typed nodes with triggers (cron, channel, webhook, manual). Covers when a workflow is the right tool versus an agent or a job, the node catalog, trigger types, the render context, and how to author one…
Skill Claude CodeCodex
Guide users through creating, reviewing, and improving OpenClaw skills following proven best practices. Use when someone asks to "create a skill", "write a SKILL.md", "make an OpenClaw skill", "publish to ClawHub", "review my skill", "improve my skill", "optimize skill description", "skill frontmatter help", "what…
Command Claude CodeCodex
Continuously replicate SQLite databases to cloud storage.
Skill Claude CodeCodex
Rules for creating ASCII art diagrams with Unicode box-drawing characters. Covers boxes, trees, flow charts, and visual representations.
Skill Claude CodeCodex
Expert code review guidelines with priority levels, core review areas, language-specific checks, and structured output format. Use this when asked to review code, review a PR, or perform a code review.
Skill Claude CodeCodex
Use when the user wants a git-history health check of an unfamiliar or inherited repository — triggers on "git recon", "codebase health check", "analyze this repo's history", "where are the landmines", or onboarding/due-diligence framing. Do NOT use for architecture review, bug-fixing, or feature work; this skill…
Skill Claude CodeCodex
Project an existing canonical .claude setup to GitHub Copilot, or fully AI-enable a repository for Claude Code and Copilot with shared instructions and the developer-led workflow. Re-runnable; converges the repo on the layout.
Skill Codex
Main compact engineering mode. Use for Codex or Claude Code work when the user wants concise, structured, token-efficient output without losing technical substance.
Skill Claude CodeCodex
Alice's couch-to-5K weekly planning with training constraints and running goals.
Skill Claude CodeCodex
Audits a repo's test suite against a short rubric and scaffolds a comprehensive one if it's thin or missing. Detects language and test framework, measures coverage where possible, identifies gaps (no unit tests, no integration tests, no CI hook, slow or flaky suite, uncovered critical paths), and presents a scored…
sirkitree/slack-markdown-formatter
Skill Claude CodeCodex
This skill should be used when users request messages, notifications, or content formatted for Slack. Use this skill when the user asks to write, draft, format, or compose messages specifically for Slack, as Slack uses "mrkdwn" which differs from standard markdown. Also use when users mention Slack Block Kit or rich…
Skill Claude CodeCodex
Quick-reference skill for Godot 4.x UI/UX development, covering Control nodes, theming, responsive design, and common UI patterns.
Skill Claude CodeCodex
Material Design 3 and Android platform guidelines. Use when building Android apps with Jetpack Compose or XML layouts, implementing Material You, navigation, or accessibility. Triggers on tasks involving Android UI, Compose components, dynamic color, or Material Design compliance.
vercel-labs/sanity-copilot-eve-template
Skill Claude CodeCodex ✓ vendor
Writing-quality guardrails for any prose the agent drafts or edits: blog posts, page copy, Notion drafts, release notes, marketing text. Use this skill whenever writing or revising content meant for humans to read, to keep the prose natural, plain, and free of AI-sounding phrasing. Not needed for code, queries, or…
Skill Claude CodeCodex
When user says "diagnose", "gate health", "which gates fire most", "gate effectiveness", "analyze gates", "gate stats", "gate report", or wants to understand how framework gates are performing.
Skill Claude CodeCodex
You are a competitive intelligence analyst generating strategic briefings for HubSpot leadership on AI-native CRM competitors, agentic automation platforms, and frontier LLM threats.
passengerxuhongli/TESSNG_secondary_dev_Skills
Skill Claude CodeCodex
A development guide for extending TESS NG V4.1, a traffic-simulation system, with Python, Java, or C++.
Skill Claude CodeCodex
A testing skill that checks whether a third-party coding-agent skill does what its documentation claims. It breaks claims into individual items and tests them in a temporary workspace.
ThinkR-open/golem-agent-skills
Skill Claude CodeCodex
Finds missing ns() local scope calls inside Shiny modules. Triggers on: "find missing ns" "find missing ns()" Do not trigger on: if outside an R Shiny app if outside an R Shiny app which is not golem based.
Skill Claude CodeCodex needs its repo
Vue Vben Admin - Modern Vue 3 Admin Framework with Monorepo Architecture.
Skill Claude CodeCodex
Talk to a ccgateway agent directly from Claude Code. Spawns an isolated subagent session with the agent's full identity (CLAUDE.md, SOUL.md, IDENTITY.md, AGENTS.md) and ccgateway skills injected. Usage: /talk.
Skill Claude CodeCodex
Publishes a local blog file (markdown) to Substack using Playwright MCP browser automation. Trigger when the user says anything like "publish to Substack", "post this blog to Substack", "upload my markdown to Substack", "share on Substack", "save this draft to Substack", or any similar intent to send a local blog file…
Skill Claude CodeCodex
ALWAYS USE THIS SKILL when creating or updating a pull request. Automatically generates a well-structured PR description by analyzing all commits in the branch. Activates for "create PR", "pull request", "open PR", "update PR description".
SimplesficaErp/demonstracoes-cpc26-skill
Skill Claude CodeCodex
Gera DRE, BP, DFC e DMPL conforme CPC 51 R3 (IFRS 18 — Apresentação e Divulgação, vigência obrigatória 01/01/2027 com adoção antecipada permitida em 2026) — padrão atual e recomendado. Suporta CPC 26 R3 (norma anterior, IAS 1) como modo legado para exercícios encerrados sem adoção antecipada. Use SEMPRE que receber…
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: