0016 views
Reusable SKILL.md capabilities that give your agent new expertise — installed into .claude/skills/ and friends.
W&B integration. Manage data, records, and automate workflows. Use when the user wants to interact with W&B data.
Implement <SPEC>, keeping a running apply-notes HTML file of out-of-spec decisions and tradeoffs.
Land converged work in self-verifying MVP slices, advancing stage to stage without interruption.
Clarify the requirement first: restate understanding, then a decision table with recommendations.
Work with the @upstash/box SDK for sandboxed cloud containers with AI agents, shell, filesystem, and git. Use when building with Upstash Box, creating sandboxed environments, running AI agents in containers, or orchestrating parallel boxes.
Generate speech audio from text using Qwen3 TTS, or clone a voice from reference audio. Triggered when the user wants to convert text to speech, generate audio, read text aloud, or clone/mimic a voice. Supports multiple speakers, English and Chinese, and emotion/style control.
Give your OpenClaw agent a homelab. Use when managing Docker containers, installing marketplace apps, or any Docker-related tasks on behalf of the user. Scope-based API key permissions — agent can only do what the key allows. On Linux, Docker requires sudo — without root access, WAGMIOS is the only safe interface for agent homelab control. Supports multi-machine management — one agent can manage multiple WAGMIOS instances across different hosts, each with its own scoped key. Requires X-API-Key header on eve
Use when working with icons in any project. Search 340k+ icons, add them as source files (no giant dependency), migrate existing icon libraries, and run as an MCP server. Commands: `aria-icons search`, `aria-icons add`, `aria-icons get`, `aria-icons migrate`, `aria-icons doctor`.
Run after each commit to detect CI-relevant entrypoints and surface whether repository checks should be verified or automated.
Install and configure SmartBundle for building an npm package, then fix reported diagnostics until the build succeeds.
Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite.
Creates long-running autonomous agents. Use when the user asks for "롱 러닝 에이전트 만들어줘", "자율 에이전트 생성", "autonomous agent", "long-running agent", "nonstop agent", or "24/7 agent". Collects requirements through AskUserQuestion and generates agent structure following Anthropic best practices.
Let agents control software, like Adobe Photoshop, Illustrator, After Effects, Premiere, Autodesk 3DS Max, Blender, Unity, Houdini, and Microsoft Office.
Browse and manage sayou workspace — list files, search, view history
Package map and reading order for Better Translate product skills.
jq — JSON Querying and Transformation workflow skill. Use this skill when the user needs Expert jq usage for JSON querying, filtering, transformation, and pipeline integration. Practical patterns for real shell workflows and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
Build and manage monorepos with Nx. Use when a user asks to set up a monorepo, manage multiple packages/apps, cache builds, run affected tests, or migrate from Lerna.
This skill should be used when the user asks to "enable narrator", "turn on voice", "start narrator", "enable voice output", "narrator on", or wants to activate text-to-speech output for Claude Code responses.
Manage Skyboard kanban boards via the sb CLI. Trigger: user asks about boards, columns, cards, tasks, kanban, or uses /sb.
Localized Markdown and MDX content guide for Better Translate projects.
Ask which skill or flow fits your situation. A router over the skills in this repo.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".