Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,788 indexed, measured the same four ways as everything else here.
MCP server "fusionmcp" as configured in Misterbra/fusion360-claude-ultimate. Runs C:\Users\YOUR_USERNAME\path\to\fusion-claude-ultimate\server\server.mjs with node.
Biên tập tiếng Việt sáo, máy móc, đều nhịp hoặc lệch giọng để tự nhiên, rõ và hợp độc giả. Dùng khi chỉnh văn phong, bảo toàn giọng tác giả, hoặc biên tập chat và kịch bản nói theo yêu cầu. Không dùng để suy đoán tác giả, lách detector hay chỉ soát lỗi ngữ pháp.
A BOSS Zhipin hiring workflow that runs a new candidate-screening task from start to report through one command-line tool. BOSS Zhipin is a Chinese job-recruiting platform.
A guide for creating and editing fixed-page HTML layouts, InDesign presentations, architectural reports, and typeset documents. It also covers converting between HTML and InDesign files and filling existing InDesign templates.
Use this skill for a guarded experimental italic or oblique construction draft from Roman glyphs, including one glyph, a selection, a named scope, or corresponding masters across a family.
Clean research code for public release while preserving reported results. Uses releaseaudit.py to separate safe mechanical cleanup from ask-first behavior risks and identity leaks. Use for release-ready repos, dead experiment branches, config extraction, documented entrypoints, and double-blind code cleanup.
Run the MolmoAct LIBERO checkpoint (allenai/MolmoAct-7B-D-LIBERO-0812) as a closed-loop VLA policy for the dexterous pick-and-place segment of a task. Drives a Franka Panda in the LIBERO/robosuite OSCPOSE action space from agentview + wrist cameras, served behind a vLLM-style script speaking the openpi websocket…
Migrate Pine Script v4 / v5 source to v6 — analyze, apply migration rules, compile-check, iterate until clean. Use when the user hands over an older script or asks to "upgrade to v6" / "port this Pine code".
Audit a Laravel application's performance deeply and safely: unnecessary queries, N+1, collection vs database work, memory amplification, repeated computation, I/O, queues, and rendering cost — verifying that every proposed optimization preserves behavior before reporting it. Use when auditing performance or…
The guided walkthrough for a codebase that has just installed montology (or has never written its vocabulary down) — phased questions served to the people who own the code as a clean one-question-at-a-time form in their browser (a local HTML file, no hosted service), answers returned to the agent on disk, each round…
Review a migrated .ipynb for correctness — NOT just "did it run". Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms, builtins shadowing, format downgrades. Outputs a structured Blockers / Important / Style / Good review report. Use…
Workspaces for agentic teams. Complete agent guide with all 19 consolidated tools using action-based routing — parameters, workflows, ID formats, and constraints. Use this skill when agents need shared workspaces to collaborate with other agents and humans, create branded shares (Send/Receive/Exchange), or query…
Review local changes with Qodo during substantive coding milestones and before a PR or completed-work handoff. Use light background checkpoints while coding, collect and assess findings with session context, and run a final review before handing off. Also use for "review my local diff", "pre-PR review", or "run qodo…
Generates OMG BPMN 2.0.2-compliant process diagrams (BPMN XML with diagram interchange plus an SVG preview) and DMN 1.3 decision models (DMN XML) from natural-language descriptions, Logic-Core/Decision-Core JSON, or existing .bpmn/.dmn files. Validates soundness and modelling style, lays the diagram out automatically…
Research independent web questions with authorized host subagents, then synthesize cited evidence and gaps. Use for requested parallel or multi-angle research, not ordinary lookups. Check child MCP access before fan-out; disclose serial fallback when delegation is unavailable.
Integration guidance for Mastercard APIs. Covers resolving a service's ID from its name, confirming a service's auth type before writing auth code, routing to the right authentication guide, finding an operation's request and response schema, sandbox versus production base URLs, and what Mastercard's error responses…
Send a task to one of the person's Hives (their SwarmAI on AWS), follow it and finish it. TRIGGER: "send this to a Hive", "run it in the cloud", "Swarm Out", "派到 Hive". NOT FOR: a Hive run the person dispatched themselves.
Build the user's Today list for Cai. Read every work tool connected to their Claude (chat, email, code, issue trackers, docs and any other source) without changing anything, find the few things that need them, rank them P0 to P3 and write them to Cai's Today folder as items.jsonl. Use when Cai runs it, or when the…
Use when drafting or refining a prompt for Claude (or any LLM) and reliability matters more than cleverness. Distilled from production patterns for document/form analysis and agent workflows.
Convert Markdown files to academic paper-style Word (.docx) and PDF documents. Dual format support: Chinese academic paper (paperolcnv2.0 template) and English arXiv-style.
★not rated 59 3d agoASkillSpector: pass0 tokens
originalApache-2.0
One-click starter pack and curator for Codex/agent skills. Use when a beginner wants a high-quality default skills setup across common needs, when the user asks to install useful skills without researching them one by one, or when the installed skills library needs auditing, deduplication, conflict resolution…
★not rated 59 5mo agoA81 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: