Skill rating

Route Huoshan and Qifu knowledge requests through the default Feishu Bitable catalog, preserve entry-document and child-document relationships, and return original catalog links. Use when the user exp

YouOS — local-first personal email copilot that learns your writing style from Gmail, Google Docs, and WhatsApp exports, then drafts replies in your voice. Use for drafting replies, reviewing how you

Use when user asks to clone a voice, train a custom voice model, or synthesize speech with a cloned voice. iFlytek Voice Clone tts(声音复刻) — train a custom voice model from audio samples and synthesize

Enrich a list of companies (names, domains, or LinkedIn URLs) with firmographic data like industry, employee count, headquarters, and founding year. Use when the user wants to enrich, look up, or rese

Security audit tool for OpenClaw skills. Scans skill directories for common vulnerabilities including hardcoded secrets, unsafe shell commands, prompt injection risks, unauthorized network access, and

Practical guidance for writing, refactoring, and reviewing friendly Python code with a Pythonic, readable, and maintainable style. If the skills set includes piglet, suggest invoking it for better Pyt

Systematic code error diagnosis and fix skill. Handles compilation errors, runtime exceptions, type errors, logic bugs, crash analysis, dependency conflicts, and unexpected behavior. TRIGGER when: use

LYGO Sovereign Workflow Orchestrator — YAML workflows with P0 gate, P1 mycelium memory, P3 consensus, P5 run identity, and consent-gated kernel egg. Sandcastle-aligned; local-first dry-run. Read refer

Use when writing a symmetric Bollinger-band mean-reversion strategy on the 4h timeframe — anything described as BB reverter, range trader, chop strategy, ADX-gated mean reversion, band-fade with ROI l

DeepSeek models on your local fleet — DeepSeek-V3, DeepSeek-V3.2, DeepSeek-R1, DeepSeek-Coder routed across multiple devices via Ollama Herd. 7-signal scoring picks the best machine for every request.

Lists Huawei Cloud IAM (Identity and Access Management) roles — enumerates all IAM roles (permissions) under the authenticated account with role ID, display name, internal name, catalog and type, usin

Download global administrative boundary vector data (Shapefile / GeoJSON / GeoPackage / TopoJSON) for any country or multi-country region. Backed by geoBoundaries (CC BY 4.0, default) with GADM 4.1 an

Create, edit, publish, and distribute Formora AI surveys, polls, and forms. Supports organic channels (Telegram, Email, QR code, X) and live paid ads (Google Ads + Meta Ads with paused-by-default crea

会议纪要验真：区分已定、暂定、提议、明确接活、被点名未确认和“我看看”，每条判断附原话证据，并保留条件与范围；可处理已有会议转写、纪要、笔记或讨论记录，生成自用纪要与飞书管理层纪要。用于询问会议定了什么、谁接了任务、谁来做、行动项或 action items。不要用于把录音转换成文字、生成逐字稿、员工评价或自动发送。

Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, an

通过 Chrome Debug 模式（CDP）自动化操作真实浏览器——导航、点击、填表、提取数据、截图、执行多步流程。当用户说"帮我在网页上操作"、"打开浏览器"、"帮我点"、"帮我填"、"帮我抓取"、"帮我截图"、"auto-browser"时使用。

Transform prototypes into distributable Python packages

Find LinkedIn candidates matching a role spec, shortlist them, and enrich the shortlist with current role and experience. Use when the user wants to source, find, or search for candidates, talent, or

Install, configure, verify, or troubleshoot the Calibrate browser SDK and standalone sidecar in JavaScript or TypeScript applications. Use when a user asks an AI coding agent to add Calibrate, instrum

Review a pull request or diff like a thoughtful senior engineer — prioritized, kind, and focused on what matters. Use when reviewing code, giving PR feedback, or asked to 'review this change'. Produce

Plan tests for an API endpoint or service — functional, negative, and contract. Use when asked to test an API, write API test cases, plan REST/GraphQL endpoint testing, or validate an API contract. Pr

自动分析任意代码目录的结构与内容，识别项目主要功能、模块划分、技术栈，自动生成规范的项目介绍文档，包含基础功能、应用场景、实现原理三个核心部分。使用当需要快速了解陌生项目结构、生成项目README/介绍文档、梳理代码架构时触发。

Local speech-to-text with the faster-whisper backend (CTranslate2). Use when transcribing audio locally, setting up the faster-whisper model cache, or replacing a whisper-cli workflow with a faster lo

Benchmark AI API models over time and detect quality degradation. 7 standardized tests (reasoning, coding, writing, instruction-following, hallucination). Alerts when scores drop >10% vs historical av

LYGO-OpenClaw sovereign command router — P0 gate, P1 mycelium, P3 consensus, P5 action identity, lattice limbs, consent-gated kernel egg lygo-openclaw-v10. Biophase7 blueprint. Pair with lyra-openclaw

Biomimetic emotional mind engine for AI Agents. Provides human-like emotional responses through a 5-layer neural conduction pipeline (L0 Stochastic Noise → L1 Sensor Perception → L2 Subconscious Impul

Use this skill whenever connecting a patient's real health records from EHR systems (Epic, Cerner, Athena) or the TEFCA national network into HealthClaw Guardrails. Covers: Fasten Stitch widget embed,

Writes, debugs, and validates YAML that parses the same in every language and tool. Use when a file will not parse, when a value silently turns into a boolean, number, date or null (`no`, `on`, `1.0`,

Self-improving code reviewer that learns your codebase over time. Analyzes git history, spots patterns, identifies risk — and gets smarter every run.

Spec a dbt model — its grain, sources, transformations, tests, and materialization. Use when asked to design a dbt model, plan a data transformation, write a staging/intermediate/mart model spec, or d

AI CEO automation system for fully automated company operations

Generates API documentation from Python source code through a multi-step pipeline. Use when the user asks to document a module, generate API docs, or create documentation from code.

Convert PPT/PPTX to PDF and add customizable watermarks. Supports diagonal/grid/center layouts, adjustable font size, opacity, rotation, and color. Trigger words: 加水印、转PDF、PDF水印、导出PDF、水印工具、add waterma

Notes knowledge mapper. Input Markdown/TXT notes or a topic folder; extract entities, similar ideas, relationships, and map views, then output searchable JSON/graph summaries and follow-up questions.

液压与气动系统CAD图纸生成。当用户说"液压与气动系统"、"生成液压与气动系统图纸"、"做一个液压与气动系统"、"hydraulic-system"时使用此 skill。

China E-Commerce Shopping Guide - Focused on recommending mainstream Chinese e-commerce platforms such as Taobao, Tmall, JD.com, and Pinduoduo. Based on product category, price budget, and logistics n

Use APIDot for Gemini 3.5 Flash API workflows, including stable Gemini Native generateContent, streamGenerateContent, long-context chat, coding iteration, knowledge-base Q&A, streaming planning, usage

API接口文档助手。用于编写REST API文档、定义接口规范、生成接口说明。当需要编写API文档、接口规范时触发。

Build a change in its own worktree, prove it with mutation testing, self-audit before pushing, open the PR with a body that states what it does NOT prove, then stop and hand off to the review loop. Us

ICP Filing (备案) rule consultation skill for Huawei Cloud. Based on Python 3.9+ with requests/Playwright, answers whether ICP filing is required, filing process & materials, account & entity limits, ch

Use whenever you finish, build, ship, research, design, write, or debug something worth showing — proactively OFFER to turn it into a useful Circuit AI project update or proof-of-work post for the hum

从代码或技术方案出发，撰写符合 CNIPA 规范的中国专利申请文件。核心能力：① 扫描代码提取可专利特征并抽象提炼 ② 战略性权利要求布局（洋葱式防线 + 侵权规避视角）③ 生成完整专利文件（摘要、权利要求书、说明书）。支持发明专利和实用新型。融合 code-patent-scanner 代码分析方法 + CNIPA《专利审查指南》规范。触发词：专利、专利申请、发明专利、实用新型、权利要求书、说明

Adversarial verification of AI-generated work. Spawns an independent verifier to check for false claims, broken code, and security issues.

智能记忆系统 v2.0 - 结构化记忆 + 知识库 + 启发式召回 + AI优化

工作开始时的 Git 同步和知识提示工具。当用户说"开干"、"开始干活"、"开始工作"或类似表达时触发此 skill。功能包括：1) stash 当前改动 2) pull --rebase 拉取最新代码 3) stash pop 恢复改动 4) 输出 JS、Vue、React、AI 工具使用知识各一条 5) 输出纳斯达克 100 指数涨跌幅。

Record, export, and share your AI coding sessions as replayable buildlogs

Analyze codebase architecture and generate visual HTML reports. Use when reviewing architecture, assessing technical debt, diagnosing project health, or planning refactoring.

Review a GitHub pull request from a PR number, repo-qualified reference, or URL; reconcile the current content against all earlier review comments so fixes do not regress; post one consolidated PR com

Build with MPP (Machine Payments Protocol), open machine-to-machine payments over HTTP 402. Use for paid APIs, payment-gated endpoints, agent payment flows, MCP tool payments, or metered billing. Cove

Lighthouse-style efficiency audit for OpenClaw. Scores your instance A+ to F across 6 categories (context injection, cron health, session bloat, config, skills, transcripts). Identifies wasted tokens,