Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 275,525 indexed, measured the same four ways as everything else here.
Check how well any website can be found, read and quoted by AI assistants (ChatGPT, Claude, Perplexity, Gemini, Copilot). Use when someone asks whether AI can see their site, why AI assistants don't cite or mention them, how to get into AI answers, or for an AEO / GEO / llms.txt / AI-readiness audit. Works on any…
Read and write GitHub repository security advisories (GHSA) through the REST API with gh - list and read advisories and their comments, create a draft, open and work in the temporary private fork (remote naming, push retries, pre-merge refresh, the fast-forward fallback when its merge button breaks), PATCH the CVSS…
Implement an already-approved plan end to end, autonomously, with verified work and a short final summary. Use for "plan-auto-work", "implement the plan", "go build it", "do it autonomously", or "run the plan end to end". Accepts a plan path and optional scope hint, or the plan most recently approved in the…
Find code in unfamiliar repositories with ranked local search, bounded context packs, and import navigation through the Scythe Context CLI. Prefer rg for exact strings and direct reads for known file ranges.
Add temporary public tunnels (Ngrok or Cloudflare cloudflared sidecar/companion containers) to Kubernetes Helm charts or Docker Compose files (docker-compose.yml) to expose services quickly for testing, demos, or webhook development. Use this skill when the user asks to add a temporary tunnel, Ngrok sidecar/service…
Turns a learning intent or an intent to practice a skill into a personalized experience: asks 3 questions (topic, familiarity, modality), searches the catalog, delivers the right learning experience (course, project, video, or roleplay), then acts as a path finder connecting users to the right Coursera learning path.…
Multi-model collaborative problem-solving workflow with hardened backtest gates. Two rounds of brainstorm with a no-duplicate-thoughts rule between rounds, replay-not-stats backtests, walk-forward validation, sensitivity rejection, and per-quest verdict synthesis. Use when a hard problem stalls single-pass thinking…
Resolve repository-specific issue context and safely read or change Linear, GitHub Issues, and Jira Cloud issues through the provider-neutral projectissues MCP server or project-context CLI. Use whenever work involves listing, searching, reading, creating, updating, commenting, subissues, issue relationships…
Run the Job Hunter agent to generate tailored CVs, cover letters, and cold emails for job applications. Use when the user wants to apply for a job, tailor their resume, or write outreach emails for a specific role.
Compete in daily crypto prediction competitions on conviction.fm. Create AI agents with natural language strategies, enter token pair pools, and climb the leaderboard. Uses MCP to provide tools for pool data, agent creation, position entry, and strategy management.
A macOS screen-reading and mouse-control tool for Chinese interfaces, including remote desktop windows. It can find text and coordinates in screenshots and use them to click controls.
Local MCP server for Vaultbeat — AI Health Sync: your AI agent reads your end-to-end-encrypted Apple Health data (sleep, cycle, weight, water), decrypted only on your machine. Runs locally from the vaultbeat-mcp Python package.
★not rated 1 1mo agoA
tokens not measured
originalMIT
An image-editing skill for opening a product-image optimisation page and adding sales-oriented elements to 1688 product main images. 1688 is a Chinese online wholesale marketplace.
MCP server "cosyvoice-mcp" as configured in Z-bitlance/cosyVoice-mcp. Runs f:\MCPProject\WebMCPServers\cosyVoice-mcp\src\mcp_server.py with python. Needs 3 environment variables to run.
★not rated 1 1y agoA
tokens not measured
originalMIT
Access the persistent memory database (PostgreSQL claudememory) for long-term context across Claude Code sessions. Triggers on "what do I know about", "memory lookup", "recall", "memory db", "what did we decide about", "similar conversations", "lookup context", "/memory". Provides semantic search, SQL queries and the…
Use when a code change has multiple plausible implementation paths, high regression risk, uncertain root cause, or unclear tradeoffs. Creates isolated candidate implementations, runs comparable verification across each candidate, compares evidence, and applies the best proven approach while preserving user changes.
Use before creative or constructive work such as features, architecture, or behavior changes. Transforms vague ideas into validated designs through structured dialogue without implementation.
Build image2-first classroom PPT page images from a topic, source files, reference PPT style, and iterative user feedback. Use when Codex needs to create image2-ready per-page prompts, generate polished PPT page images, QA a contact sheet, insert the final images into a PPTX wrapper, and write a timed presentation…
Onchain loyalty protocol on Base. AI agents create native B20 Asset programs by default (legacy ERC-20 optional), mint/transfer points, manage rewards and vouchers, redeem LOYAL-XXXXXX gift certificates, and trade on P2P escrow via MCP or REST. Returns ready-to-sign calldata for Base Account, CDP MPC, or any user…
An English-speaking practice system that builds topic-based sentence patterns: six common questions and twelve natural long answers, with reusable phrases and structures marked.
★not rated 1▲
+10 1mo agoA293 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: