Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 269,418 indexed, measured the same four ways as everything else here.
kingpanther13/Hubitat-local-MCP-server
Skill Claude CodeCodex
Guide for developing and maintaining the Hubitat MCP Rule Server — a Groovy-based MCP server running natively on Hubitat Elevation hubs, exposing 118 tools (36 on tools/list via category gateway proxy) for device control, virtual device management, room management, rule automation, hub admin, file management…
s1gmamale1/apple-design-skills
Skill Claude CodeCodex
Use when deciding HOW an Apple-style interface should BEHAVE — the functional UX/interaction logic, not the looks. Navigation-model decisions (push vs sheet vs modal vs tab vs popover vs split-view vs full-screen, back behavior, deep-linking, state restoration), state & feedback behavior (loading/skeleton timing…
MCP server Claude CodeCodexCursor +2
An MCP Server for STAC requests. Runs locally from the stac-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server for E.Leclerc Drive — search products, manage cart, and order groceries from Claude. Runs locally from the mcp-leclerc-drive npm package. Needs 4 environment variables to run.
Skill Claude CodeCodex
A debate-questioning guide based on the 《辩论筑基》 system, a framework for building arguments and handling challenges. It guides users through questioning and responses during a debate.
Skill Claude CodeCodex
A Korean patent-document checker for comparing a patent specification, drawings, and claims—the sections that describe an invention and define its legal protection.
Skill Claude CodeCodex
Create and manage dedicated Codex lane threads for either new work or existing uncommitted/committed work. Use when the user wants to split a project into parallel lanes, hand off a lane to another thread, run final-review in a separate thread, open or babysit PRs, resolve review-bot comments, ship/merge work, or set…
dacnay816y62-hub/window-scenery-skill
Skill Codex
A skill for generating photorealistic travel images seen through a vehicle window, with a consistent location label in the lower-left corner.
Skill Claude CodeCodex
Automate server O&M, execute batch commands, test network connectivity, transfer files, and manage host assets using the XOps CLI toolkit. Triggers when managing server clusters, performing concurrent tasks across multiple machines, checking network ports, or synchronizing configuration files.
Skill Codex
Run safe, high-yield codebase maintenance passes that trim dead code, vestiges, duplicate implementations, stale scripts/configs, and excessive LOC without churn. Use when the agent is asked for a maintenance pass, cleanup pass, code cleanup, slop trimming, dead-code removal, de-duplication, vestige pruning, or…
xWebt/chinese-erotic-fiction-writing
Skill Claude CodeCodex
A Chinese-language writing aid for adult fiction. It helps plan, write, expand, and revise stories, with support for outlines, chapter structure, local reference-text indexing, and learning from examples.
Skill Claude CodeCodex
Designs and writes a focused artifact another agent runs — an agent persona in agents/, a workflow skill in skills/, or a pi session harness in .pi/harnesses/. Use when authoring a reviewer or specialist persona, a repeatable process skill, or a pi extension that reshapes a session — or when rewriting one that is…
Skill Codex
An image-conversion guide that redraws photographs as simple, high-saturation, flat-color illustrations while preserving the subject's identity and layout.
MCP server Claude CodeCodexCursor +2
Dify MCP Server. Runs locally from the dify-mcp npm package.
Skill Claude CodeCodex
Execute requested Python code inside an isolated CubeSandbox MicroVM. Use when the user explicitly asks for CubeSandbox, MicroVM isolation, offline execution, or proof that code did not run on the DSH host.
skyfox3725-sdx6z/integration-partner-brief
Skill Claude CodeCodex
Write a one-page technical integration partner brief: joint value, scope, auth/data flows at high level, security pointers, success metrics, next steps. Triggers: integration partner brief, tech partner one-pager, ISV partnership brief, integration collab outline, API partner summary.…
Skill Codex
Save primary-agent context by assigning codebase research to a lower-cost scout. Use when the implementation or relevant code connections are unknown. Skip when a focused local read or a current report is sufficient.
HarrierPigeon/Solidworks-MCP-Server
MCP server Claude CodeCodexCursor +2
MCP server "solidworks" as configured in HarrierPigeon/Solidworks-MCP-Server. Runs server.py with python.
SPYfighting/my-academic-skills
Skill Claude CodeCodex
Gated protein design campaign: each expert judgement is a checkpoint a human signs off before compute is spent. Branches: de novo binder design (epitope choice, generation, co-folding ensemble ranking, ranked order sheet); structure and complex prediction with calibrated confidence; protein engineering (stability…
Skill Claude CodeCodex
Comprehensive analysis of Swift 6 ownership, concurrency safety, and systems programming foundations.
Skill Claude CodeCodex
Security audit and threat model for OpenClaw gateway hosts. Use to verify OpenClaw configuration, exposure, skills/plugins, filesystem hygiene, and to produce an OK/VULNERABLE report with evidence and fixes.
Skill Claude CodeCodex
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for…
Skill Claude CodeCodex
Use when designing, auditing, refactoring, or expanding complex repositories where the AI should first discover architecture from the codebase instead of being constrained by premature schemas, rigid YAML definitions, or hardcoded implementation assumptions.
Skill Claude CodeCodex
Build evaluation harnesses for agents and chatbots — golden sets, deterministic tool-selection checks, LLM-as-a-Judge, Bedrock RAG evaluation jobs, CI gates, and online drift monitoring. Use when an agent needs a quality gate before merge or a quality alarm in production.
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: