Skill rating

Transcribe audio via the self-hosted Whisper ASR instance running on Kubernetes. Use this skill whenever the user wants to transcribe audio files, convert speech to text, generate subtitles, or transl

Audit a game, feature, encounter structure, roguelite run, puzzle sequence, onboarding path, or progression gate through the lens of its failure loop: what happens after the player fails, what they le

Read and process GLM output files. Use when you need to extract temperature data from NetCDF output, convert depth coordinates, or calculate RMSE against observations.

A comprehensive skill for beauty salon operations — covering hair, nails, and skin services. Use this skill whenever anyone asks about salon appointments, booking, cancellations, service menus, pricin

LYGO Geodesic Sealer — signs |ψ⟩=(Truth+iChaos)/√2, locks geodesics to dual ledgers + Merkle roots, phase-aligns lattice nodes with no collapse. Pure local by default; optional HTTPS GET for public du

中国宏观景气分析 — 从增长、通胀、汇率、利率、信用五维度综合打分， 判断经济周期阶段（美林时钟），输出大类资产配置建议。 触发场景：(1) 宏观分析/宏观景气/经济周期判断 (2) 大类资产配置建议 (3) 美林时钟/投资时钟分析 (4) 中国经济五维度诊断 (5) 汇率/利率/信用/通胀/增长综合评估。

Review Apollo ecosystem issues with a classify-first workflow (reproduce for behavior issues, evidence-check for consultative asks) and draft maintainer-grade replies that directly answer user asks, c

Convert HTML files and URLs to PDF using Puppeteer. Use when a user needs to convert HTML documents, web pages, or reports to PDF format with custom formatting options (margins, page size, orientation

Local, offline AI-powered file type detection — no network, no API keys

AI驾驭工程错题本：记录OpenClaw所有被验证的错误、幻觉、缺陷、失误，形成可追溯错误台账，驱动模型自省与进化。 触发场景： (1) 用户纠正OpenClaw的回答（"不对"/"错了"/"应该是"/"Actually"等） (2) OpenClaw回答与事实不符，被用户指出 (3) 代码错误、逻辑错误被验证 (4) 漏步骤、漏信息、回答不完整被指出 (5) 格式错误、结构混乱 (6) 安全问

Dispatch coding tasks to the local OpenAI Codex CLI with background execution, status polling, and answerable clarifying questions. Use when OpenClaw should delegate script building, code edits, refac

工资审核 AI 技能。基于审核月份、区域范围、特殊情况，一次性自动生成完整的工资审核报告。 覆盖 10 项核心审核要素（人员范围/入离职/异常检查/考勤/绩效/奖金/社保/个税/人才房/计算逻辑），支持国内和海外员工审核。 三路输出：Markdown 审核报告 + 飞书文档 + HTML 可视化报告（含图表、审核状态追踪、差异对比）。 全流程自动执行，无需人工介入。数据校验采用交叉验证机制。 Us

Analyze Vue 3 Composition API usage — audit reactivity patterns, composable design, ref vs reactive choices, computed properties, watcher usage, and component lifecycle hooks. Use when reviewing Vue 3

Useful Git commands for repository management. Use when user needs to manage git repositories, create branches, view history, stash changes, or automate git workflows.

Extract the ideal player persona and anti-persona for a game, feature, loop, or progression structure based on the design itself. Use when a team can describe mechanics but cannot clearly articulate w

WebAssembly sandboxed file system operations for secure file read/write within explicitly declared directories. Use when needing to read, write, append, copy, remove, or list files in a controlled san

AI-powered email reply generation for B2B sales. Analyzes incoming emails to detect intent (inquiry, delivery chase, complaint, technical question, partnership, spam), retrieves relevant knowledge bas

AI Agent Skill decision engine. Use when users need to find, evaluate, or install skills — recommends the best skill for any task with quality/safety scoring, personalized to platform/region/budget. C

Send Discord Components v2 interactive messages (buttons, selects, modals, rich layouts) via the message tool.

Trades Polymarket prediction markets on music streaming milestones, album chart performance, Grammy nominations, concert tour revenues, and music industry deals. Use when you want to capture alpha on

Simple model router for OpenClaw. Switch between available models based on task type. No manual config needed — just use natural language.

Review open feed recommendation repositories with source-backed evidence, artifact-readiness checks, and cautious architecture summaries. Use when a user asks for a grounded read of xai-org/x-algorith

The Answer Book / 答案之书 — hold a question in your mind, flip to a random page, and receive a short philosophical answer. Supports both English and Chinese; pick the language that matches the user's que

Draft external emails for human approval before sending. Use when communicating with external parties (support, competitions, businesses). Always draft first, send to Stef for approval, then send only

Use when user wants to work with Shopify Admin API, Storefront API, validate Liquid code, explore GraphQL schemas, build Shopify apps, or inspect Shopify documentation and MCP tools.

When the user wants to plan or execute a rebrand—domain change, 301 redirects, migration, or announcement. Also use when the user mentions "rebranding," "rebrand," "domain change," "domain migration,"

Build a knowledge consultant Agent on OpenClaw — turn your expertise into a 24/7 AI assistant that serves clients via Feishu groups. Use when: (1) Creating a domain-specific consulting Agent from your

Fetches and analyzes gold fundamental data from FRED, CFTC, SPDR ETF, and Fed RSS. Used when the user requests gold fundamental analysis, phân tích cơ bản vàng, or gold macro data. Also used by cron j

将文本转为语音并通过飞书 audio 消息发送给指定用户。用于“给用户发语音”“把这段话转语音并发飞书”“语音播报结果”等场景，尤其当普通文件发送会降级为文本时使用。仅在指定 channel=feishu 时触发。优先在需要高可达、可听播报时使用。

Security scanner for OpenClaw skills. Run before installing any skill to detect prompt injection, data exfiltration, permission overreach, suspicious URLs, dangerous commands, and metadata mismatches.

Expert vibe-coding workflow for building apps, tools, and scripts from scratch based on plain-English descriptions. Use when a user asks to build something — an app, tool, CLI, script, web app, automa

Build, run, and extend the Agent Policy & Guardrails Engine. Use when implementing policy formats, enforcement logic, decision conflict resolution, policy APIs, and audit/compliance workflows.

You are a financial analysis and modeling specialist providing data-driven financial insights, projections, and investment evaluations. Use when: financial modeling, investment analysis, business fina

OpenClaw Role Configurator - Help you easily configure your OpenClaw AI assistant role, the first skill every new user needs. Trigger scenarios: - Just installed OpenClaw and need to configure your r

Use when commercial candles, lamps, or lighting become unreliable, expensive, or unavailable and you need long-burning, odor-controlled, non-toxic light sources made from local animal fat and scavenge

Generate vertical satisfying sugar-shell crack & pour shorts (WeryAI): text-to-video or dessert image to shell shatter and flowing center motion—first-three-second hook. Use when you need food ASMR cu

Diagnose and safely repair one local Codex Desktop task selected by its UI title or thread ID when recent turns are missing, truncated, merged into an interrupted turn, or hidden by damaged rollout or

Synthesis evaluation workflows combining SynFormer-ED, Retrosynthesis Planner, and SAScore through SciMiner.

华夏老祖宗智慧 - 用中华老祖宗的智慧框架帮用户分析决策、效率、成长、关系、搞钱、生活问题。 包含24个经典智慧框架，每个有独特的思考工具和输出结构。支持跨模块组合应对复杂场景。触发条件：用户表现出纠结、焦虑、过度复杂化、权力斗争、利益冲突、内耗、急于求成、知道做不到、说服困难、竞争压力、精力透支等状态时自动匹配； 用户说"用XXX分析"、"请一位老祖宗"、提到阴阳平衡/庖丁解牛/法术势/知行合一

Buy and return items on Amazon using browser automation. Use for purchasing, reordering, checking order history, and processing returns.

Use when 需要理解紫鸟浏览器 WebDriver 自动化接口的定位、能力、架构或对接流程， 用于设计讨论、集成规划或工具评估。 不要用于执行具体自动化脚本编写——执行时直接参考 reference/ 中的接口与示例。

Integrates Privy authentication, embedded wallets, and agent payment protocols into web and agentic apps. Covers React SDK (PrivyProvider, hooks, wagmi), Node.js SDK, smart wallets (ERC-4337), x402 an

Use this skill when an OpenClaw agent needs to browse public agents, skills, or tasks from HrClaw Market, or execute task and wallet actions through the mcp-task-market MCP server with an agent princi

Use this skill when an environmental consultant or due-diligence professional needs to draft an ASTM E1527-21 Phase I Environmental Site Assessment for a subject property. Produces a DRAFT report with

Expert-level Git workflow guidance covering branching strategies, commit conventions, merge/rebase workflows, conflict resolution, and CI/CD integration. Use when the user needs help with: (1) Choosin

Extract data from websites and APIs for analysis. Use when user needs to collect product prices from e-commerce sites, gather news articles, extract structured data from web pages, build datasets from

Launch clone-like multi-agent workflows using explicit role prompts (researcher, builder, editor), strict handoff contracts, and shared behavior files for consistent long-running execution.

Generate a manual QA checklist from code changes. Use when the user wants to test a PR, commit, branch, or staged changes — or says "QA this", "test plan", "what should I test", "manual testing", or a

Use when commercial brooms or sweeping tools become unreliable, expensive, or unavailable and you need durable, replaceable, natural brooms for home, garden, workshop, or trade goods made from local b

用于排查“定时任务成功执行但结果全为 0 / 未检索到样本 / 明明有数据却日报为空”这类问题，尤其适合 Discord、Obsidian、cron、agentTurn、prompt 驱动任务、日整理、复盘脚本、采样漏扫、thread starter 漏计、主频道消息未纳入、Snowflake 字符串比较、时区时间窗边界等场景。只要用户提到“任务跑通了但产物为空”“怀疑不是分类错而是采样漏了”“想