Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,730 indexed, measured the same four ways as everything else here.
Turn a book, paper, document, documentation site, or code repository into an agent skill, and keep it honest afterwards — grade a skill's load cost and routability, test it against the source it came from, and rebuild it when the source moves. Use when the user wants to make a skill from a PDF, EPUB, DOCX, a URL, a…
A document-assembly skill that combines completed chapters and exercises into one Markdown textbook, with a cover, contents page, consistent formatting, and optional learning roadmap.
A planning step for creating or improving a presentation, report, pitch, training deck, or technical talk. It prepares the audience, goal, timing, story, slide structure, evidence, notes, risks, and visual direction before the slides are designed.
A conversion tool for turning HTML, React, or Vue demo pages into native WeChat Mini Program projects. WeChat Mini Programs are small apps that run inside WeChat.
Create schema-validated HTML survey pages from natural-language requirements using the admin designer references. Use this skill whenever the user asks to create, design, prototype, render, or generate a survey/questionnaire HTML page, especially when they want free-form UI style but need the question structure…
Wire Patter as the voice layer on top of an OpenClaw brain — the "brain on the line" pattern. Use when the user runs OpenClaw (or any OpenAI-compatible agent gateway) and wants a phone number that answers any caller, talks with low latency, and consults a specific OpenClaw receptionist agent for real data/actions…
Turn a rough idea, scene, story, creature, building, environment, or visual reference into a professional colossal-scale concept and a production-ready English image-generation prompt, then recommend suitable image models and concrete settings. Use for…
Spec-driven feature work in 4 phases — Specify, Design, Tasks, Execute — sized by complexity; atomic tasks and commits, Execute delegated to workers in waves plus an independent Verifier. Triggers on "specify/discuss feature", "design", "tasks", "implement", "validate", "verify work", "UAT", "record decision"…
Create or redesign Instagram posts in a retro playful editorial aesthetic: 4:5 aspect ratio, clean magazine-style layout, nostalgic objects such as vintage phone, toys, and everyday items, balanced image and structured typography overlay, horizontal color blocks, label-style sections, subtle UI-like information layout…
Create a study cheatsheet by extracting and synthesizing key concepts from lecture materials, homework, and past exams. Use this skill whenever a user asks for help making a cheatsheet, study sheet, formula sheet, exam reference sheet, or "one-pager" — especially when they upload lecture slides (PDF/PPTX/DOCX)…
Use the agent-rollback MCP server or ar CLI to snapshot the workspace, list/show/diff checkpoints, and roll back unwanted changes. Use this skill whenever the user mentions checkpoints, rollback, undo, revert, restore, "go back to", "what changed", "I broke something", "this isn't working", or asks to inspect or…
Full operational Kubernetes surface via the container-manager-mcp MCP server — workloads (pods/rollouts/StatefulSets/DaemonSets/ReplicaSets/Jobs/CronJobs), config (ConfigMaps/Secrets/Namespaces/CRDs/patch), networking (Ingress/native Services/NetworkPolicy/DNS), storage (PV/PVC/StorageClass/snapshots/CSI), RBAC…
Use the user's Omni-Context long-term memory when it is connected over MCP. Trigger this whenever you need to recall what the user has done, decided, or prefers across past conversations, or when a conversation reaches something worth remembering. Omni-Context is a local knowledge graph — NOT the standard…
The "poke" workflow: an episode (or movie) that should already be out wasn't grabbed automatically. Confirm it aired, run an interactive search, pick the best release by seeders, grab it, and verify it entered the queue. TRIGGER THIS SKILL WHEN: - "A new episode of should be out but nothing downloaded" …
Use when the user asks to fact-check, verify, or score the citations/sources/references in a document from a chat (no terminal) — extracts citations with bundled code, fetches and judges each source with web tools, then scores through paper-verify's standard 100-point rubric via --from-evidence.
Initialize Symbiote for the current project. Scans the codebase and extracts developer DNA (coding preferences), project constraints, and architectural decisions from the current context. Use when the developer runs /symbiote-init, asks to "initialize symbiote", "set up symbiote", or "scan my project". Requires…
Use when operating an Air Jam project through its first-party MCP tools for inspection, development, semantic game sessions, logs, quality gates, and releases.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Gemini CLI's capabilities with specialized knowledge, workflows, or tool integrations.
Use TakeoffLens to count and audit supported building-system symbols in engineering DWG/DXF/PDF drawings by preferring CAD metadata, using vector geometry for vector PDFs, and using high-resolution vision only for raster PDFs. Electrical and ELV systems are the first active disciplines. Use when an agent must count…
Write git commit messages that follow the Conventional Commits standard. Use when the user asks for a commit message, or gives a change summary or diff and wants it written up for git.
MCP server "clojure-android" as configured in xlisp/clojure-android-demo. Runs mcp_server.py with python3.
★not rated 6 4mo agoA
tokens not measured
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: