Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 282,343 indexed, measured the same four ways as everything else here.
Keep project documentation in sync with code changes. Identifies which docs need updating after a PR merges or code changes, drafts the updates, and manages doc site structure (mkdocs, docusaurus, vitepress). Use when: (1) a PR just merged and docs may need updating, (2) the user says "update the docs" or "sync docs"…
Local-first command wrapper for AI coding agents with compressed terminal output and privacy-safe proof metrics. Runs locally from the psycgod-sage Python package.
★not rated 11 26d agoA
tokens not measured
originalMIT
Shape output for a busy operator. Use this skill whenever responding to ANY user message including business decisions, pricing questions, tool comparisons, how-to questions, technical explanations, planning, writing feedback, research summaries, and casual conversation. Lead with the verdict or the number, keep it to…
MCP server for Cathedral — persistent memory and drift detection for AI agents. Runs locally from the cathedral-mcp Python package. Needs 3 environment variables to run.
★not rated 11 todayA
tokens not measured
originalMIT
Analyze and optimize database schemas, identify performance issues, and suggest improvements. Use when working with database structure, indexes, or query performance.
Use when searching past conversations, recalling previous solutions, understanding project history, or needing context from earlier sessions - proactive conversation history mining via ccvault MCP server.
Reconstruct a referenced website, page, interaction, or WebGL/WebGPU/Canvas effect from a URL or supplied evidence. Use for faithful site cloning, offline mirrors, responsive page replication, SPA fixture replay, visual-effect extraction, design transfer, and continued fidelity work on an existing replica. Not for…
Transform text into a personal writing style. Use when asked to "rewrite in my style", "make this sound like me", "my style", "make it mine", "transform this", "rewrite as me", "sound like me", "use my voice", or any request to match a personal tone. Works for emails, messages, professional writing, and casual texts.…
Design websites, apps, slides/PPT and forms. Use when creating or visually changing these outputs, or when requirements are confirmed and the user is ready for a design next step, even if they describe only business functions. Infer suitable layout, color and interaction from the task and existing project.…
A development guide for Vue 3, Element Plus, and Electron desktop applications. It explains where interface code, operating-system code, and the secure bridge between them should live, and how to structure and verify changes.
Share an interactive terminal session (claude / shell / any CLI) over MQTT in real time to remote devices (ESP32 / MCU, etc.). Two routes: inside Herdr, trigger the vibetty plugin share action on the focused agent pane; otherwise start vibetty in a background tmux session. Covers prerequisites, the start commands…
Use when bootstrapping, auditing, improving, or retrospecting on human-AI collaboration systems in a project, especially around context entrypoints, authority, staged scope, local drafts, verification, decision records, documentation drift, and correction loops.
Design, generate, audit, or revise minimal validation-driven AI agent packs for Codex, Claude Code, and Claude skills from project descriptions, README files, specs, existing workflows, or repository evidence. Use when creating or improving AGENTS.md, CLAUDE.md, context routers, primary workflow agents, reviewers…
Audit the shell startup chain (the rc file + every file it sources) for hardcoded credentials, persistence-suspicious patterns, duplicate or dangling aliases, and git-baseline drift. USE WHEN the user wants to review, secure, clean up, or maintain their shell aliases or startup files; check /.zshrc / /.bashrc for…
Use when a task involves X/Twitter: search posts, read a profile or timeline, post/reply/quote, upload media, send DMs, manage lists, bookmarks, communities, or scheduled posts. Spectre is the MCP server for all X work.
A testing and quality-checking toolkit for running an application, finding bugs, and creating automated tests. It supports API tests and browser-based UI tests in Python or Java.
ALWAYS use this skill when user needs ANY API functionality (AI models, image generation, video, audio, text processing, etc.). Automatically search 302.AI's 1400+ APIs and generate integration code. Use proactively whenever APIs or AI capabilities are mentioned.
Adaptive teaching skill for developers, PMs, QA, designers, AI engineers, and security engineers — calibrated to your role and codebase, SM-2 spaced repetition, gamified with achievements, hunts weak spots with The Ambush, guides career growth to Founder.
A guide for taking apart a Codex Skill and explaining its design in plain language. A Skill is a set of instructions and supporting files that guides an AI coding agent through a task.
Pre-share leak scanner for Claude Code skills (or any folder). Scans BEFORE you publish for secrets (API keys, tokens, private keys, .env values, high-entropy strings), PII (emails/phones), local machine paths (C:\Users\ , /home/ , /Users/ , UNC, internal hostnames), and client/proper-noun names from a LOCAL private…
★not rated 11 4mo agoA193 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: