Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,342 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Spend against a budget below the real window, and count the tool schemas you re-send on every step — they are the floor compaction cannot reach.
MCP server Claude CodeCodexCursor +2
MCP server "dart" as configured in sabbirba/preconnect. Launched with dart mcp-server.
Skill Claude CodeCodex needs its repo
Build, test, and harden this DaloyJS REST API on Bun. Use when the user asks to add or change an endpoint, route, Zod/Standard Schema, middleware, error handling, OpenAPI spec, typed Hey API client, contract gate, auth, rate limit, background jobs, or security default. Also use for phrasing like "add GET /...", "new…
vishalmdi/india-equity-report-skill
Skill Claude CodeCodex
Generate a detailed Buy/Sell/Hold equity research report for Indian stock market (NSE/BSE listed companies). Use this skill whenever the user asks for a stock analysis, equity research, investment recommendation, target price, fundamental analysis, technical analysis, or buy/sell/hold opinion on any Indian company or…
Skill Claude CodeCodex
A Chinese AI short-drama production workflow covering scripts, storyboards, character references, images, videos, voice-over, subtitles, music, and final editing.
Skill Claude CodeCodex
Run a human-feedback loop through RambleDesk. Hard trigger: when the user invokes /ramble, $ramble, [$ramble], or says to use RambleDesk/ramble feedback, create a RambleDesk request before answering the substance unless they explicitly say not to send one. Also use when real human judgment, review, approval, or…
Skill Claude CodeCodex
A Chinese-language product-selection assistant for 1688 and Ozon, two online commerce platforms.
Skill Claude CodeCodex
A guided process for discovering a product idea and writing a PRD, or product requirements document. A PRD records what should be built, for whom, and how it should work.
MCP server Claude CodeCodexCursor +2
MCP server for Monarch Money personal finance. Runs locally from the monarch-mcp-jamiew Python package. Needs 6 environment variables to run.
Skill Claude CodeCodex
Remove AI writing tells from text. Use when a text artifact is the deliverable or a major part of one, such as documentation, PR or commit text, release notes, reports, marketing copy, code comments, or when asked to de-slop, humanize, or clean up text. Not for chat replies, status updates, or completion summaries…
Skill Claude CodeCodex
A framework for finding and addressing the reasons buyers hesitate to purchase.
Skill Claude CodeCodex
Build or debug Roblox music, spatial audio, effects, text-to-speech, and speech-to-text. Use for audio graphs, asset permissions, playback problems, or migration from Sound.
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 needs its repo
A workflow that converts a Figma design into web code and checks the rendered page against the original design. It uses saved design data, screenshots, pixel differences, and structural checks to guide repeated fixes.
Skill Codex
Orchestrate a complete MiniMax H3 music-video production from song, lyrics, and visual references through MV direction, integer-second audio segmentation, storyboard generation, official H3 prompt writing, direct local minimax-H3-GEN submission, shared RunningHub queue autofill, resumable monitoring, automated result…
Skill Claude CodeCodex
A Chinese-language prompt-writing guide for GPT-image-2, an AI model that creates images from instructions. It covers single images and batches such as icons, characters, cards, and images containing Chinese text.
Skill Claude CodeCodex
Install, diagnose, and safely use KeyShot MCP for local product visualization, scene editing, camera control, material assignment, and rendering.
Skill Claude CodeCodex
1C:Enterprise development through the AI-EDT MCP server - BSL analysis and editing, metadata, managed and ordinary forms, query validation, project diagnostics, debugging, infobase updates and unit tests. Use when the project is a 1C:EDT workspace: BSL modules, .mdo metadata, 1C queries, managed forms, Form.oform…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Route an incoming request to the VERTICAL knowledge graph (what the agent knows — a single relationship/temporal traversal), the HORIZONTAL workflow graph (how the agent acts — a decomposed multi-step process), BOTH (a workflow whose nodes query the knowledge graph and write results back), or UNROUTABLE (neither fits…
street1983nk/nextcloud-mcp-connector
MCP server Claude CodeCodexCursor +2
MCP server "nextcloud-mcp-connector" as configured in street1983nk/nextcloud-mcp-connector. Runs locally from the nextcloud-mcp-connector Python package.
ostikwhy-blip/claude-code-handoff-skill
Skill Claude CodeCodex
Use when ending or pausing a Claude Code session whose work must continue in a fresh session — user says "create a handoff", "write a handoff", "I'm ending this session", "prepare for a fresh session", "hand this off", or "/handoff" — or when starting a session in a project that already contains a HANDOFF.md at the…
majiayu000/claude-skill-registry-data
Skill Claude CodeCodex
Build a specification-first Digital FTE that orchestrates accumulated intelligence from Lessons 1-7. Learn to compose execution skills into production-ready agents, validate against specifications, and position for monetization.
Skill Claude CodeCodex
Use when installing Anthropic's Claude Science on a geo-blocked machine (e.g. China) or running it without a Claude account. Downloads the binary from the unblocked downloads.claude.ai CDN, sets up the claude-science-api-bridge local proxy to route requests to ANY OpenAI- or Anthropic-compatible API (Volcengine…
Skill Claude CodeCodex
Dedalus Rust correctness and style rules. Use when writing, reviewing, or refactoring any Rust code in the host-agent, enclave, or packages/rust workspaces. Covers return-value naming, error design, mustuse, visibility, RAII, fail-closed, and all hard limits from style.md and rust.mdx.
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: