Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 282,298 indexed, measured the same four ways as everything else here.
Guide for creating logos, brand identities, and visual assets using AI tools — covers tool selection, prompt engineering, vectorization pipelines, mockups, automation, and IP safety.
Use when writing, reviewing, refactoring, or modernizing CSS/Tailwind. Apply a policy-first approach: semantic tokens, explicit cascade order, static CSS, intrinsic component layouts, accessible state, measured performance, and progressive enhancement backed by current sources.
Analyze chart screenshots or user-described market segments with an Al Brooks price-action framework. Use when the user wants the agent to infer symbol, timeframe, and range from a screenshot or text, fetch OHLC and EMA data, and produce scenario-based trading analysis with levels, invalidation, and risk notes. For…
Run your Discord server from Claude, Cursor or VS Code: messages, moderation, roles, forums, events. Runs locally from the @pasympa/discord-mcp npm package. Needs 1 environment variable to run.
★not rated 34▲
+2 2d agoA
tokens not measured
originalMIT
Alex Hormozi's complete entrepreneurship playbook from one transcript — covering fear, business ideas, leverage, hiring, content, advertising volume, hypothesis thinking, and hard work philosophy. Use for any stage challenge from 0-to-1 through $10M+. The skill asks clarifying questions, routes to the right framework…
Video understanding and transcription with intelligent multi-provider fallback. Use when: (1) Transcribing video or audio content, (2) Understanding video content including visual elements and scenes, (3) Analyzing YouTube videos by URL, (4) Extracting information from local video files, (5) Getting timestamps…
Drive the ReconBridge toolchain to reverse-engineer / recon / tamper Android apps on a rooted (KernelSU) device from the PC side. Use whenever the task involves: pulling an APK or native .so off a device, decompiling with jadx, locating classes/methods with DexKit/androguard, Ghidra native analysis, hooking or tracing…
Rules for building offline-first Progressive Web Apps that launch instantly from the home screen. Use when building, reviewing or debugging a PWA, or anything touching a service worker, a web app manifest, precaching, an in-app update prompt, iOS home screen behaviour, or safe-area/notch layout.
A planning tool for building a consistent content series, such as a YouTube channel, newsletter, or short-video programme. A series bible is a reference document covering its audience, voice, recurring topics, formats, rules, and future ideas.
Audit, clean, and when explicitly requested uninstall local Claude Code, Claude Desktop/PWA, Anthropic browser bridges/extensions, auth/config residue, CC Switch app/data/routes, Claude network signals, DNS/WebRTC leaks, browser locale/timezone/font signals, PWR fingerprint signals, environment fingerprint baseline…
Reads, searches and counts Claude Code session transcripts (the .jsonl files under /.claude/projects, subagents too) with the csift command-line tool, and ships hooks that re-inject compacted turns or record pending questions. Use when asked what a past or running session said, did, edited, spent or is doing now; when…
A drafting tool for OKRs, a planning method that pairs broad objectives with measurable key results. It is designed for small product and engineering teams, with English, Chinese, or bilingual output.
Use for any crypto market or onchain data request, even if CoinGecko isn't named: coin and token prices, market cap, volume, OHLC and historical charts, supply, categories, top gainers and losers, trending coins, new listings, global market stats; exchanges, tickers, derivatives and funding rates; NFT floor prices…
Parse, read, search, navigate, summarize, extract, crop, enhance, dewarp, or check images and documents for manipulation through xparse-cli. Use for document conversion, durable Task workflows, structured extraction, and domestic TextIn image processing or manipulation/AIGC detection of a local file or URL. Prefer it…
/neat extend is a set of six MCP surgical tools for long-tail instrumentation — three diagnostic (read-only), three operative (file-scope-restricted, idempotent, reversible, observable). The user's MCP agent reasons; NEAT operates. NEAT holds no LLM key and never auto-applies. No standalone CLI variant. Discovery is…
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
★not rated 34 5mo agoA
tokens not measured
originalBSD-3-Clause
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
A workflow for creating an interactive PRD from clarified product ideas or an existing demo. It plans and reviews sections, then produces an editable local workspace with web prototypes, notes, navigation, and linked pages.
★not rated 34▲
+1 2mo agoA107 tokens
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: