Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 267,523 indexed, measured the same four ways as everything else here.
Edit videos using natural language instructions. Supports trimming, jump cuts (silence removal), captions with multiple styles, text overlays, and speed changes — all powered by ffmpeg and Whisper.
Create or run the proof behind a software-factory L3 gate and seal evidence that survives re-verification. Use when a feature needs its first gate, when a gate is red for missing or stale evidence, or when asked to prove a change actually works end to end.
A video-prompt writing skill that examines a video or a rough idea and turns it into instructions for an AI video generator. It can describe camera movement, timing, style, consistency between shots, and platform-specific settings.
Write high-converting Meta (Facebook + Instagram) ad copy — primary text, headlines, descriptions, and UGC/video ad scripts. Use this skill whenever the user asks to write, rewrite, or brainstorm Meta ads, Facebook ads, Instagram ads, ad hooks, ad captions, ad primary text, UGC scripts, video ad scripts, talking head…
A research workflow for searching the live web and extracting information from pages. It supports quick scans for short overviews and deep research for comparing several sources.
Use before adapting or debugging any PPTX template-driven deck. Parses a template into a portable spec.json contract: classified shape tree, slide roles, repeated card structures, per-slide fillplan, text style/paragraph metadata, font availability, and optional renders. This is the required first half of the…
Scaffold, implement, register, scientifically qualify, and production-check an LDM domain task in this repository. Use when adding or repairing a task adapter, task manifest, experiment.json benchmark contract, proposal-provider capabilities, metric roles, qualification evidence, official evaluation budget, campaign…
A guide for creating reusable support replies for customer-service teams that support developer tools. It covers situations, placeholders such as a customer’s name, tone, escalation wording, and rules such as not inventing response times or asking for passwords.
Requirements grilling for engineering tasks. Use before writing any code when the task's goal, boundaries, acceptance criteria, failure modes, priorities, or non-goals are not yet settled — interrogate the user across six dimensions, reach consensus, record a structured spec, and only then implement.
Use this skill for any request involving cryptocurrency market data, coin prices, trading volume, market cap, OHLC charts, historical data, exchanges, derivatives, NFTs, DeFi, on-chain token data, liquidity pools, DEX data, or anything powered by CoinGecko or GeckoTerminal APIs. Trigger this skill whenever the user…
A tool that turns customer conversations, meeting notes, and other Feishu records into structured requirement documents. BRD means business requirements document, and PRD means product requirements document.
MCP server for browsing, searching, exporting, and backing up your Cursor AI chat history. Runs locally from the cursor-history-mcp npm package.
★not rated 32 9d agoA
tokens not measured
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: