Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 267,593 indexed, measured the same four ways as everything else here.
zarazhangrui/beautiful-feishu-whiteboard
Skill Claude CodeCodex
A library of 35 curated colour palette styles for building beautiful, editable Feishu / Lark (飞书) whiteboards from SVG. Use this whenever the user wants to create or draw a Feishu whiteboard, infographic, diagram, poster, or visual explainer and wants it to look polished, on brand, or in a particular aesthetic, or…
Skill Claude CodeCodex
Use when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.
MCP server Claude CodeCodexCursor +2
Policy-gated, audited SSH for Linux and Windows hosts: roles, approvals, and an audit log. Runs locally from the ssh-mcp npm package. Needs 4 environment variables to run.
Skill Claude CodeCodex ✓ vendor
Use when the user wants to train, validate, predict, track, export, benchmark, tune, inspect, or orchestrate YOLO-Master / Ultralytics experiments in this repository, including LoRA, MoE, multimodal inference/evaluation, and solutions workflows.
nuyoah-ai-works/nuyoah-xiezhen-prompt
Skill Claude CodeCodex
A Chinese-language prompt-writing guide for AI portrait photography, including recreating a photo series with a different person and breaking reference images into usable instructions.
MCP server Claude CodeCodexCursor +2
MCP server "xbbg-mcp" as configured in xbbg-org/xbbg. Launched with https://github.com/xbbg-org/xbbg/releases/download/v1.4.6/xbbg-mcp-v1.4.6.mcpb. Needs 6 environment variables to run.
Skill Claude CodeCodex
Implement and extend PostHog Data warehouse import sources. Use when adding a new source under products/warehousesources/backend/temporal/dataimports/sources, adding datasets/endpoints to an existing source, or adding incremental sync, resumable imports, webhook ingestion, pagination, credentials validation, and…
Skill Claude CodeCodex
A dialogue-review system for novels that studies how characters speak and whether their voices remain distinct. It can examine speech habits, sentence length, question frequency, and repeated phrases.
Skill Codex
Use when a task needs current public-web facts, comparisons, fact-checking, sources, or a multi-source synthesis and both websearch and webfetch are available.
Skill Claude CodeCodex
A Chinese-language assistant for writing articles for WeChat Official Accounts, China's platform for publishing articles to subscribers. It can write the article, prepare image prompts, and produce inline HTML for the layout.
Skill Claude CodeCodex
Taste Skill, subtitled "the anti-slop frontend framework for AI agents," adjusts layout, typography, motion, and spacing in AI-generated interfaces. The skills cover different registers, including a minimalist editorial style and an industrial brutalist style, and several generate reference images before any code is…
Skill Claude CodeCodex
Use this to build and flash custom firmware onto a Solo 2 Hacker key — including checking the lock/seal state (Secure vs Hacker, which is the PFR seal field, not secure boot), matching the build to the key's storage mode, and validating the equivalent build on an EVK first. Use it WHENEVER you are about to write…
Skill Claude CodeCodex
Prints a greeting with unnecessary confidence.
Skill Claude CodeCodex
A tool for finding trending topics and recent developments across search engines, news and community platforms.
shannhk/hermes-agent-control-room
Skill Claude CodeCodex
Use when creating a fresh Hetzner Cloud VPS with an SSH alias, local project folder, provisioning script, destroy script, and optional handoff into setup-control-room.
Skill Claude CodeCodex needs its repo
Use ONLY when calling the browserexecute tool or driving a real browser via the Chrome DevTools Protocol. Required reading before the first browserexecute call in a session. Covers the three connection methods (local Chrome with remote debugging, isolated debug-port profile, Browser Use cloud), the in-process session…
Skill Claude CodeCodex
Use the ax CLI instead of curl + throwaway parsing scripts whenever you fetch a URL, explore an unknown web page, or extract structured data from HTML. Trigger whenever you are about to write an inline script (python3 heredoc, node -e, regex over HTML) or a bare curl for one-off web fetching, scraping, or page…
Skill Claude CodeCodex
Orchestrator reference for pi-messenger Crew planning, task management, configuration, and agent coordination. Crew workers already have the pimessenger actions they need in crew-worker.md.
MCP server Claude CodeCodexCursor +2
Nova3D MCP server — structured, part-aware 3D generation for AI agents. Runs locally from the nova3d-mcp Python package. Needs 2 environment variables to run.
Skill Claude CodeCodex needs its repo
Authors deterministic and LLM rubric graders for skillgrade evaluations. Use when creating scoring scripts, writing evaluation rubrics, or combining multiple graders with weighted scoring. Don't use for setting up eval pipelines, configuring eval.yaml defaults, or general test writing.
MCP server Claude CodeCodexCursor +2
Add components to your apps. Runs locally from the shadcn npm package.
growthenginenowoslawski/coldoutboundskills
Skill Claude CodeCodex
Creates cold email copy through a stepwise confirmation process. Use when writing email campaigns, given a campaign strategy document, website, or client context. Confirms direction at each step before outputting final copy.
Skill Claude CodeCodex needs its repo
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the stepfun-37 smoke test), open code review (ocr), PR…
Skill Claude CodeCodex
How to discover, read, write, and search data in a TigerFS-mounted PostgreSQL database using file tools.
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: