Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 267,873 indexed, measured the same four ways as everything else here.
Bootstrap a team's Context Tree from readable source repos — for an onboarding "build / set up the Context Tree" task on a tree that has no domain structure yet: either no tree exists (creates and binds it) or a bound-but-empty tree (fills it). Supports clean explicit-Team invocation without a Workspace manifest…
Use when planning a multi-step task or working in plan mode and you need to capture the plan as a durable, resumable artifact — breaking work into phases with per-item checkboxes, completion tracking, autonomous verification, and a handoff summary so a future agent can pick up where you left off. Use when user wants…
Create, edit, replicate, read, and export presentations. For every PPT task, the default deliverables are BOTH (1) a self-contained PPTD project folder containing the .pptd manifest plus pages/media dependencies and (2) a locally generated .pptx with embedded fonts and fade slide transitions. Use for any presentation…
Generate a game-ready 3D asset by running the local AI pipeline sequentially: Fooocus (SDXL text-to-image) -> Hunyuan3D-2 (image-to-textured-GLB) -> optional Blender FBX convert + Unreal import. Use when the user wants to create/generate a 3D model, mesh, or racer for the Unreal train-racer project from a text prompt…
A workflow for finding, checking, organizing, analyzing, and reviewing Chinese- and English-language research papers. It uses browser automation to search databases including CNKI, Web of Science, and ScienceDirect, then produces Markdown files with paper details, citations, and a final review.
Reference-aware whole-paper reading and structured research-note generation. Use when the user wants to understand an entire paper, place it in the literature, compare it against core prior work or baselines, or decide whether a paper should be read as a method paper or as a Nature or Science-style evidence-chain…
An automated workflow for preparing Chinese software-copyright registration materials from a real software project. It produces application information, an operation manual, and source-code documents with evidence from the project.
Orchestrates multi-agent work with OpenPI's inline JavaScript Workflow DSL. Use when a task needs multi-phase fan-out, pipelines, barriers, structured handoffs, or resumable background orchestration.
Write to (or read) the user's BonsAI board — the spatial idea canvas in the BonsAI macOS app. Use when the user asks to put / drop / add / send something to their BonsAI board, capture an idea or note on the board, sketch a diagram or architecture onto the canvas, evolve an idea already on the board, or read what's…
Deploy a trained embodied-AI policy onto an RDK board — LeRobot ACT imitation policies and Pi0 VLA (openpi) — by exporting to ONNX, compiling to a BPU .hbm, and running the on-board control loop that drives a robot arm. Use whenever the user has an ACT checkpoint or a Pi0 model and wants it on RDK S100/S100P/S600…
Use when the user wants to import external chat exports into OpenClaw. This skill normalizes raw chat history into conversation-archive-compatible JSONL, then guides the model to distill daily memory and MEMORY.md candidates before applying merges with user confirmation.
A workflow step for turning a product brief and technical decisions into a system architecture overview. It identifies separate systems, their boundaries, dependencies, and the source-code directories they map to.
Turn any system architecture into an interactive, pannable/zoomable canvas diagram (dark by default with a light switcher, JetBrains Mono, plane-coloured bands, click-to-isolate focus, PNG export) — the "architecture canvas" style — and optionally publish it to artifact.cafe for review. Use whenever the user asks for…
Use when building software with AI agents and you need a serious end-to-end workflow instead of vibe coding. Covers harness choice, context discipline, cleanup, review loops, launch pressure, and security basics.
Use CodeScope to analyze any indexed codebase via its graph database (neug) and vector index (zvec). Supports Python, JavaScript/TypeScript, C, and Java (including Hadoop-scale repositories). Covers call graphs, dependency analysis, dead code detection, hotspots, module coupling, architectural layering, commit…
A seven-stage workflow for turning a computer-science research idea into an academic paper. It covers finding related work, designing methods and experiments, writing, review simulation, and responses to reviewers.
Modify, validate, run, register, publish, consume, and troubleshoot agents on Blocks Network. Use when an agent project already exists, when deploying existing code, or when working with agent-card.json, the Blocks CLI, TaskClient, streams, private access, or publishing. For a brand-new agent, use blocks-getstarted.…
Use when building email features, emails going to spam, high bounce rates, setting up SPF/DKIM/DMARC authentication, implementing email capture, ensuring compliance (CAN-SPAM, GDPR, CASL), handling webhooks, retry logic, making emails accessible (alt text, headings, contrast, screen readers), or deciding transactional…
Inspect and safely operate the local ASFW FireWire MCP control plane. Use when an ASFW task needs live driver status, node discovery, protocol telemetry, MCP tool discovery, or explicitly authorized guarded FireWire control through the loopback MCP endpoint.
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: