Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 267,919 indexed, measured the same four ways as everything else here.
Use this skill to start or resume the VeriFlow RTL hardware design pipeline (architect to synth). Trigger this when the user asks to "run the RTL flow", "design hardware", or "start the pipeline". Pass the project directory path as the argument. Optional: append --benchmark to auto-generate a benchmark report after…
Implement one phase of ./specs/91-impl-plan.md end-to-end with high quality bars (correctness, elegance, performance), then run an independent code review against the relevant specs and fix every valid finding before declaring done. Use whenever the user says "build phase N", "implement the next phase", "land…
An agent for operating Feishu/Lark, a workplace platform with messaging, documents, databases, calendars, tasks, and user directories. It supports actions across those services through commands.
A tool for creating browser-based presentations as single HTML files, or converting PowerPoint files into them. It includes bilingual English and Chinese support and a library of visual styles.
Instagram MCP server — 23 tools for the Instagram Graph API. Manage posts, comments, DMs, stories, hashtags, reels, carousels, and analytics. Runs locally from the @mcpware/instagram-mcp npm package. Needs 3 environment variables to run.
★not rated 51 2mo agoA
tokens not measured
originalMIT
A tool that creates a market-breadth heatmap PNG from industry MA20 data. Market breadth shows how widely a market move is shared, and MA20 means the 20-day moving average.
Record and live-transcribe a meeting or live conversation from a Codex thread on macOS, saving streaming transcript text to the workspace with OpenAI Realtime transcription, then summarize notes in-thread. Use when the user asks to start, stop, capture, transcribe, ask questions about, or summarize a meeting recording…
Bridge Claude Code with Perplexity Comet for autonomous browsing and tab management. Runs locally from the perplexity-comet-mcp npm package. Needs 2 environment variables to run.
★not rated 51▲
+3 2mo agoA
tokens not measured
originalMIT
Create, tighten, or review runnable /goal contracts for coding agents such as Codex, Claude Code, Cursor, and similar agent tools. Use when the user asks to write, make, generate, improve, productize, or critique a goal prompt, rescue contract, GOAL.md-style task, done-when contract, verification prompt, stop-rule…
A sales-account research guide for sales, marketing, operations, and product teams. It uses provided material to examine why a customer or prospect is not moving forward.
Use this skill for a reproducible WeChat Official Account workflow with dual channels (API draft and/or Chrome browser publish) and production default draftnotifyfeishu: API draft/add then Feishu notify for human formal publish in mp admin (avoids freepublish visibility bugs on Linux/OpenClaw). Also covers browser…
Generates meeting briefings by aggregating account info, contacts, opportunities, cases, and activity history into structured prep documents with talking points and discovery questions. Use when user says "prep me for my call", "brief me on this account", "meeting prep", "I have a meeting with [company]", "account…
Alibaba Cloud Data Agent MCP skill (alibabacloud-data-agent-mcp-skill, data-agent MCP) for enterprise database/file analysis. Use when the user asks (in any language, including Chinese) to query/analyze DMS-managed databases, run SQL/data analysis, start quick-query (lite) or deep-analysis (pro/ultra) sessions…
Turn an ambiguous question about an unfamiliar or brownfield system into a bounded, read-only, evidence-backed investigation with a confirmed investigation contract, deliberate context manifest, claim ledger, ontology, owned open questions, and reviewable technical brief. Use when asked to investigate a repository…
Use when given an engineering or mathematics homework PDF and asked to solve all or selected questions, answer sketch or plot problems, redraw assignment figures, or work from noisy OCR-extracted homework text.
Query OpenSea marketplace data via the official CLI, SDK, MCP server, or shell scripts. Get floor prices, collection stats, NFT details, token data, trending collections, drops, events, search, favorites, profile and collection settings, and other wallet-scoped operations. For trading use opensea-marketplace, for…
Three.js performance optimization and best practices guidelines. Use when writing, reviewing, or optimizing Three.js code. Triggers on tasks involving 3D scenes, WebGL/WebGPU rendering, geometries, materials, textures, lighting, shaders, or TSL.
Opinionated creative skill for building stunning 3D, particle, and generative visual components. Use when building any Three.js, Canvas, WebGL, or visually complex component. Provides specific visual recipes, mathematical patterns, and creative direction — not API docs.
Produce HTML output instead of markdown for any agent task. Four levels — Static Doc, Visual Artifact, Two-Way Interactive, Throwaway Tool. Based on Thariq Shihipar's "Unreasonable Effectiveness of HTML" framework. Triggers on "/html-it", "html-it", "html this", "render as html", "build me an html", "make an html…
★not rated 51▲
+1 4mo agoA84 tokens
originalMIT
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: