Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,813 indexed, measured the same four ways as everything else here.
rastian/interaction-design-skills
Skill Claude CodeCodex
Apply interaction design (IxD) principles and frameworks to product and service design work. Use this skill when designing or evaluating interaction flows, micro-interactions, feedback mechanisms, affordances, mental models, component states, response time, animation and transitions, error recovery, input validation…
Skill Claude CodeCodex
Manage what enters and stays in the context window — pruning, compaction, summary fidelity, ordering — so the agent stays coherent on long runs without inflating cost. Use when the user is hitting context limits, running long agentic loops, paying for full-history replays, or asks "how do I keep context manageable?" /…
LENKIN233/xianyu-monitor-skill
Skill Codex
Search and monitor Xianyu/Goofish listings with filters, deduplication, and optional AI ranking. Use for searches, login, item analysis, and recurring alerts on 闲鱼 / Goofish.
Skill Claude CodeCodex
A workflow for recreating small web games from a name, link, screenshot, or video, then building an original version with similar gameplay. It is intended for puzzle and casual games that can run in a browser.
Skill Claude CodeCodex
Zvec vector database development assistant. Use this skill when users need to develop vector search applications based on zvec, build RAG systems, implement semantic search, or handle vector data storage and querying. Suitable for Python and Node.js development environments, providing complete technical guidance from…
MCP server Claude CodeCodexCursor +2
MCP server "nl-supermarkt-mcp" as configured in Samvox1/nl-supermarkt-mcp. Runs locally from the nl-supermarkt-mcp Python package.
arunbalajiraju-proc/procurement-ai-assistant
Skill Claude CodeCodex
Runs structured supplier and market research, capability comparison, pricing observations, and risk checks. Use for market scans, longlists, and sourcing research.
Skill Claude CodeCodex
Authors and extracts dbt MetricFlow meta context — structured YAML meta: blocks that encode business knowledge (thresholds, investigation paths, SLAs, relationships) alongside metric definitions so AI agents answer analytical questions accurately. Use when user asks about context cards, meta context blocks, dbt metric…
Skill Claude CodeCodex
Explain something in short, chunked, ADHD-friendly steps instead of dense prose. Use whenever the user asks what was done, how something works, or why a choice was made — and ALWAYS when they say they don't understand, ask to simplify, say an explanation was too long or dense, or mention ADHD or focus. Also use…
Skill Claude CodeCodex
A skill for turning image ideas, characters, scenes, and styles into Danbooru tags, which are standardized labels used in some AI image tools.
AlterLab-IEU/AlterLab-FC-Skills
Skill Claude CodeCodex
This skill should be used when the user asks about "audio production", "ElevenLabs", "voice isolator", "audio post-production", "AI narration", "text to speech production", "voiceover studio", "audio native", "transcription", "Scribe", "multi-track audio", "audio assembly", "batch audio processing", "audio export"…
Skill Claude CodeCodex
PRISM finds entities (genes, proteins, compounds) at the INTERSECTION of two or more property sets on RDF knowledge graphs via TogoMCP — e.g. "genes common to disease X and druggable pathway Y", "targets both linked to phenotype P and modulated by existing drugs". Use whenever the user asks a set-intersection /…
Skill Claude CodeCodex
Process Granola meeting notes from inbox/ — route to correct folder, rename with consistent naming, scaffold missing person profiles, extract tasks to my-tasks/tasks.md.
Skill Claude CodeCodex
Write publication-ready papers for top security, privacy, and cryptography venues (IEEE S&P, ACM CCS, USENIX Security, NDSS, PETS, CRYPTO, Eurocrypt, TCC). Use when drafting papers from research repos in these areas, structuring threat models and security claims, writing game-based or simulation-based proofs, or…
Skill Claude CodeCodex
Kreuzberg's format detection -> extraction -> fallback orchestration for 75+ file formats.
Skill Claude CodeCodex
Use when writing or tuning ElevenLabs speech so it sounds alive, paced, and human; covers text shaping for Eleven Multilingual v2 and Eleven v3, plus API-based voice-setting updates from user feedback.
sector-b79/Malware-And-Reverse-Engineering-Skill-for-AI-Agents
Skill Claude CodeCodex
Defensive malware analysis and reverse-engineering workflow. Use for authorized lab analysis of suspicious Windows executables, DLLs, shellcode, packed samples, malicious documents, indicators of compromise, static and dynamic triage, IDA/Ghidra/debugger reasoning, anti-analysis handling, unpacking, host/network…
Skill Codex
A prompt-writing tool for turning approved storyboards and fixed production details into ready-to-copy Chinese instructions for AI video platforms.
MCP server Claude CodeCodexCursor +2
MCP server "engram" as configured in rwnalds/engram. Runs in Docker (ghcr.io/rwnalds/engram:0.1.2).
Skill Codex
A source-grounded adaptive tutor that tracks proof of mastery rather than content completion. Use it to learn a topic systematically, build a course from PDFs, webpages, transcripts or notes, practice retrieval and transfer, resume a long-running course, or verify whether the learner can recall and apply what they…
MCP server Claude CodeCodexCursor +2
MCP server for Microsoft To Do via Microsoft Graph. MSAL device code flow, no client secret needed. Runs locally from the @mag-cie/mcp-microsoft-todo npm package. Needs 2 environment variables to run.
Skill Codex
Apply a named Thinking Toolkit model or audit an argument with /logic. Use only when the user explicitly invokes the toolkit, names an included model or alias, or invokes /logic.
Q0916/community-webtoon-agent-kit
Skill Claude CodeCodex
Use when turning an online community post, forum incident, meme thread, live gallery mood, or user-supplied issue into a short Korean vertical info-gag webtoon; includes source collection, fact-mood-MSG separation, sweet-spot approval, causal storyboard packets, cast-text-reference locks, ima2-gen-first generation…
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…
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: