Skill rating

屏幕控制技能 - 通过OpenClaw Node + pyautogui实现电脑屏幕识别和鼠标键盘操控。功能：(1) 截图获取屏幕画面，(2) OCR文字识别定位，(3) 图片匹配定位，(4) 鼠标移动/点击/拖拽，(5) 键盘输入/快捷键，(6) 基于视觉信息的自动化操作。Use when: (1) 需要远程操电脑屏幕，(2) 需要自动操作桌面应用（非浏览器），(3) 需要批量处理电脑上的文件或

Expert guidance for Vision-Language-Action (VLA) robot foundation models — covering architecture design, training pipelines, data strategy, deployment, and evaluation. Use when (1) designing or implem

Extract design information from Figma files. Pull design tokens, component structure, colors, typography, spacing, and export assets. Use when the user asks about their Figma designs, needs to extract

Stealth browser automation using CloakBrowser to bypass bot detection on protected sites. Use when web_fetch fails with anti-bot blocks, CAPTCHA, or access denied errors. Use for scraping reviews, pro

Asynchronous reflection and memory integration for genuine AI development. Use on heartbeat to reflect on recent sessions, extract structured memories with confidence scores, generate follow-up questi

AI-driven Playwright test code generator for QA engineers. Generates Page Object Models, standard test scripts, and data-driven tests from natural language descriptions, HTML analysis, or page URLs. S

Lightweight CDP browser control for AI agents. Token-efficient alternative to the built-in browser tool — 3-10x fewer tokens per interaction. Use when browsing websites, clicking elements, filling for

Transcribe and organize voice memos with automatic categorization and information extraction. Use when users have voice notes, audio memos, or spoken notes to convert to structured text.

Download or collect a YouTube video media file from a known video URL. Do not use for metadata, comments, transcripts, channel profiles, or keyword-based video discovery.

Use this skill only when the user explicitly asks for a dry-run cleanup inventory, disk-space cleanup, deletion review, or recoverable archiving of generated workspace artifacts in a coding repo, such

Activate when: user says 'challenge my thinking', 'play devil's advocate', 'what's the strongest counter-argument', 'ACH', 'analysis of competing hypotheses'; user needs to evaluate a high-stakes clai

Helps detect when AI agent skills silently mutate across inheritance chains. A skill audited safe in generation 1 may drift far from the original by generation 5 — but nobody re-audits because the nam

When the user wants to plan, implement, or optimize discount and promotional pricing strategy. Also use when the user mentions "discount strategy," "promo code," "coupon," "redeem code," "lifetime dea

Stop agents from producing reports instead of taking action. Restructure prompts, cron jobs, and agent shifts so they DO things — send emails, post content, make API calls, push code — instead of writ

Use this skill only when the user explicitly asks for a code audit, security audit, risk-focused PR/diff review, repo or module audit, regression-risk review, project-intent drift check, or validation

Specialist in video production pipeline. Use when: stage 1: pre-production, stage 2: asset generation, stage 3: video assembly.

This skill evaluates arithmetic expressions using the Unix `bc` calculator. It accepts full `bc` syntax (addition, subtraction, multiplication, division, modulus, scale, sqrt, and constants like `pi`)

Browser-side request inspection and reporting for user-authorized web debugging. Use when you want one skill to observe page fetch/XHR/WebSocket activity, inspect login/register/API flows, and generat

Manage sourdough starters with feeding schedules, hydration calculations, health tracking, and baking preparation. Use when the user wants to maintain a sourdough starter, plan feedings, calculate rat

Work with Jira issue tracking and project workflow state through Atlassian Rovo's hosted MCP server. Thin pass-through to Atlassian's official MCP; the live tool catalog is whatever that server advert

Read DocuSign account, envelope, recipient, template, and signing-status data through DocuSign's official developer MCP server. Use when the user asks to inspect DocuSign signing workflows without cha

Make OpenClaw agent workflows restart-safe using checkpoint files, idempotent step tracking, wake/resume handoff, and stale-checkpoint monitoring. Use when users ask to recover from restarts, preserve

Visual identity discovery for AI agents — not an avatar generator, but a self-reflection system that creates a face from your agent's personality, memory, and relationship with its human. Quick mode:

Query system information including OS, CPU, memory, and disk usage. Use when users ask about system configuration, resource usage, performance diagnostics, or basic system info. Supports Windows, Linu

Generate images from text prompts using ZenMux API (Vertex AI protocol with Gemini models). Use when: (1) User wants to generate/create images from text descriptions, (2) User asks for AI image genera

Explain, generate, validate, and preview crontab expressions. Use when a user needs to understand what a cron expression means, create a new cron schedule, check if a cron expression is valid, or see

Draft and fill Y Combinator SAFE templates — valuation cap, discount, MFN, pro rata side letter. Standard startup fundraising documents for convertible equity. Produces signable DOCX files. Use when u

Automate GitHub pull request workflows including creation, review, merging, and monitoring. Handles PR templates, auto-labeling, CI/CD integration, and review automation. Use when users need to create

Export Slack thread messages from a logged-in Slack web tab into CSV using an attached Chrome Browser Relay tab. Use when the user wants to collect Slack conversations by person, channel, or time rang

Compact AI-to-AI communication protocol. Use when spawning sub-agents, sending inter-agent messages via sessions_send/sessions_spawn, or when instructed to speak OpenLang. Reduces token usage 5-10x on

Rewrite, edit, or review Indonesian text so it sounds natural, human, and context-appropriate. Use when the user asks to humanize Indonesian writing, remove AI-sounding phrasing, adapt text to officia

Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3 or local Whisper. Transcribes audio messages, saves both audio files and text transcripts.

Household food inventory manager with expiry tracking. Use when: (1) adding food to fridge/freezer/pantry — 'bought milk', '买了鸡蛋', (2) removing/consuming food — 'used 3 eggs', '牛奶喝完了', '扔了过期酸奶', (3) c

Analyze and clean up OpenClaw session storage files. Use when the user wants to manage session files, clean up old sessions, delete cron/heartbeat, or organize session storage. Triggers on phrases lik

Create, fetch, share, or update hosted Pipintama Charts through the MCP server. Use when a user needs a line, bar, pie, or radar chart from text or structured values, and the right output is a hosted

Web search grounding via Azure Foundry and Bing Grounding Search tool. Use when the user needs up-to-date information searched from the web via Azure AI Agents. Returns the synthesized answer and URL

This skill orchestrates autonomous discovery of brand materials across enterprise platforms (Notion, Confluence, Google Drive, Box, SharePoint, Figma, Gong, Granola, Slack). It should be used when the

Use this skill whenever the agent has access to Linkup web search or fetch tools. Teaches the agent how to reason about query construction, choose search depth, write effective queries, select the rig

AI skill safety validation — real human experts vet skills, plugins, and MCP tools for security risks. Query trust scores, submit evaluation inquiries, and get real-time safety verdicts before install

Use when the user asks about Indian competitive exam preparation, Sikkim PSC (SPSC) questions, previous year questions (PYQ), mock test generation, exam pattern practice, or needs reference questions

Compare model candidates using weighted metrics and deterministic ranking outputs. Use for benchmark leaderboards and model promotion decisions.

Safely release and publish skill updates to ClawHub with version bump discipline. Use when preparing patch/minor releases, running lint/build checks, writing changelogs, and publishing a skill folder.

Use when visual reasoning is needed with Alibaba Cloud Model Studio QVQ models, including step-by-step image reasoning, chart analysis, and visually grounded problem solving.

Polymarket prediction market trading for agents. Use this skill when users want to create a Polymarket wallet, browse markets, place bets, manage positions, or withdraw funds. Triggers on "polymarket"

Smart home control for the Lofy AI assistant — scene modes (study, chill, sleep, morning, grind), device management via Home Assistant REST API, presence-based automation, natural language commands fo

Send voice messages on Lark (Feishu) by converting text to speech. Use when the user asks to send a voice message or reply with voice.

Gate unified account operations skill. Use when the user asks about unified account equity, margin borrowing, or leverage modes. Triggers on 'unified account', 'borrow limit', 'repay loan', 'switch ma

Create or optimize an OpenClaw skill. Use when the user wants to build a new skill, improve an existing one, review a SKILL.md, or prepare a skill for ClawHub publishing.

Browser automation for 通义千问 (Qwen) web interface at qianwen.com. Use when the agent needs to ask questions to Qwen AI and get back responses via browser automation. Supports single-turn and multi-turn

Use CamScanner to detect whether an image was generated by an AI model (e.g. Stable Diffusion, Midjourney, DALL·E). Powered by an AIGC-detection engine that classifies an image as genuine, suspected A