Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 269,285 indexed, measured the same four ways as everything else here.
Create, revise, and audit executive-ready strategy-consulting presentations as native, editable PowerPoint files. Use when turning topics, text, Markdown, Word, PDF, spreadsheets, CSV data, URLs, research, or an existing PPTX into a board, client, strategy, transformation, market-analysis, or McKinsey-style consulting…
Lets the agent inspect a PostgreSQL database schema and run read-only SQL queries against it. Runs locally from the @modelcontextprotocol/server-postgres npm package.
Mass-publish CorpusIQ affiliate program pages in 100+ languages via Rentry.co API. Proven to drive signups (12 users acquired). No auth required - pure API POST. Use whenever pushing affiliate program worldwide.
Skill "code-refactor" from ZeroPointRepo/CRHQ-PRDs, covering code refactor skill, when to use this skill, the two modes, core principles and the seven phases (shared by both modes).
Turn a prompt or brief into a fully rendered MP4 video. Generate AI videos and social clips (TikTok, Reels, YouTube Shorts), YouTube intros, startup website hero loops, product promos, marketing videos, explainers and animated data visualizations - with AI voiceover (text-to-speech), word-synced captions/subtitles…
Automatically delegate complex, logic-intensive tasks to OpenAI Codex CLI via codex exec --full-auto. Claude Code uses this skill to invoke Codex for complex backend logic, intricate algorithms, or persistent bugs. Enables seamless AI-to-AI collaboration where Claude Code analyzes and Codex executes.
Build, compare, review, or repair a Blender model against an actual supplied image, photograph, concept, or visual reference using adaptive decomposition, measurable proportions, evidence scoring, and bounded repair. Use only when the request explicitly concerns model creation or quality against visual form criteria…
Crea automatizaciones inteligentes (agentes de IA) en la nube de Cloudflare, paso a paso, en español sencillo, sin necesidad de saber programar. Úsalo cuando alguien escriba "/crear-agente", "/crear-agente-imperio", "quiero crear un agente", "quiero hacer un agente", "quiero automatizar [X]", "quiero un sistema que me…
ShellX host-session manifest. Use only when the current prompt or runtime metadata positively identifies this session as running inside ShellX, when ShellX host tools are advertised, or when the user explicitly asks about ShellX host APIs or surfaces. Do not use merely because this skill is installed, a project…
A process for automatically recording feature-demo videos of a local web app using Playwright, a browser-automation tool, and ffmpeg, a video-processing tool. It drives the real app, then adds subtitles, labels, a simulated cursor, zooms, and faster playback for waiting periods.
A configuration-driven process for compiling ONNX or BC machine-learning models for J6 HBDK hardware. It creates a YAML configuration, waits for approval by default, then compiles and checks the output.
Audit and apply real, project-local Trellis integrations for Matt Pocock and Waza skills, with phase routing, hook injection, durable artifact handoffs, and smoke-test evidence. Use when a user wants to strengthen, compare, modernize, integrate, or debug Trellis with Matt/Waza workflows, especially when skills are…
Guia prático da API Pública do DataJud (CNJ) — consulta de metadados e movimentações de processos judiciais brasileiros via Elasticsearch em api-publica.datajud.cnj.jus.br. Vai além da documentação oficial: registra conhecimento de produção como a consulta obrigatória pelo alias do tribunal (o curinga apipublica…
Adversarial cross-model verification of work produced by an AI agent — code, documents, data, config, anything. A different model attacks the work against its brief, Claude arbitrates. Triggers on /verify-agent — or natural language like "verifica il lavoro che ha fatto l'agente", "è corretto quello che ha fatto…
A shared command-line foundation for Yandex Mail, Calendar, and Disk. A command-line tool is a program operated by typing commands, and this one returns machine-readable JSON by default.
Secure filesystem MCP server for reading, writing, searching, diffing, and patching files. Runs locally from the @j0hanz/filesystem-mcp npm package. Needs 1 environment variable to run.
★not rated 22▲
+2 3d agoA
tokens not measured
originalMIT
A stdio MCP server that exposes Bash-like SSH execution, sessions, and remote file read/edit/search. Runs locally from the slepp-ssh-mcp Python package.
★not rated 22 2mo 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: