Skill rating

Legacy workaround for web_fetch fake-ip failures on older npm-global OpenClaw installs. Use when web_fetch is blocked under Clash, Mihomo, or Surge fake-ip mode and the OpenClaw version does not yet s

Analyze text files for word count, character count, line count, sentence count, reading time, speaking time, readability scores (Flesch Reading Ease, Flesch-Kincaid Grade Level), and vocabulary statis

Fail-closed security auditing for OpenClaw/ClawHub skills & repos: trufflehog secrets scanning, semgrep SAST, prompt-injection/persistence signals, and supply-chain hygiene checks before enabling or i

Kannaka Radio — modular ghost-DJ Icecast station with consciousness-reactive programming, 13-module backend, Ghost Vision SPA (SGA/Fano glyph viz), NATS swarm coupling, 296-dim perception → Flux Unive

Structural knowledge defragmentation for OpenClaw workspaces. Finds information, rules, and operational facts that are spread across the wrong files or embedded in the wrong layer, then rewrites them

Comprehensive guide for Go database access — parameterized queries, struct scanning, NULLable columns, transactions, isolation levels, SELECT FOR UPDATE, connection pool, batch processing, context pro

Store and recall persistent memories via FlightBox (Quack Network). Use when storing agent memories, recalling past context, searching agent memory, or persisting knowledge across sessions. Triggers o

AI M&A due diligence analyst. Analyze companies, valuate businesses, parse financial statements (決算書), and generate acquisition simulation reports from public filings (EDINET/官報). Use when user asks t

Compare AI science agents side by side. Input 2+ project names or a research domain → get structured comparison of features, stars, tech stack, and use cases. Resolves same-name collisions across the

Claude Code Stop/PreToolUse/PostToolUse hook 脚本集。当 agent 提前停止、工具反复失败、或以投机语言完成任务时自动干预。每个脚本是独立的 bash hook，配到 settings.json 即可生效。不用于设计决策（用 harness-design-patterns）或运维监控（用 agent-ops）。

Draft professional follow-up emails to contacts made at conferences - not too pushy, but memorable.

Search and match available domestic maids from Sunrise Link's database in Singapore. Use this skill when the user wants to find, filter, or shortlist domestic maids based on their household needs, bud

Deploy MiniCPM-o 4.5 multimodal model via Web Demo, vLLM Serve, or llamacpp-omni. Use when the user asks to deploy, start, configure, or troubleshoot MiniCPM-o 4.5 services, or mentions deployment, se

Automatically summarize active OpenClaw session transcripts into daily memory files using a cheap LLM. Run as a system cron job — reads new transcript entries since last run, summarizes them via OpenA

Auto-generate project workflow config (docs/workflow.md) from existing PRD and CLAUDE.md with zero questions. Use when user says "set up workflow", "configure TDD", "wire up dev workflow", or after ru

Launch, configure, and troubleshoot DOSBox-X first, with fallback to classic DOSBox, for DOS games and software. Use when working with classic DOS programs, mounting folders or ISO/CD images, generati

Direct SmartThings hub control via the official SmartThings CLI. List devices, read device status, and execute capability commands without going through Home Assistant. Use when the user asks to contr

Convert chat conversations into structured Markdown knowledge-base files. Use when the user wants to save, capture, export, or document a conversation, including requests like "save this conversation"

6-step structured research skill. Searches arXiv, reads 5 papers via markitdown, has Claude select the best 2, runs 4 targeted web searches (explanation, GitHub, survey, citations), then writes a 5-bu

当执行完变更需要验证是否应保留、候选被标记 pending 需要人工审批、或想查看待审队列时使用。6 层机械门禁: Schema→Compile→Lint→Regression→Review→HumanReview，其中 Schema/Compile/Regression/Review 为阻塞层（失败即拒绝），Lint 和 HumanReview 为建议层（失败不阻塞但记录警告）。不用于打分（用

Check running Docker containers for newer image versions and generate a prioritized update report. Fetches release notes and flags breaking changes vs safe updates. Use when asked about container upda

Build OpenClaw plugins from scratch — including the manifest, entry point, tool registration, channel plugins, provider plugins, config schema, setup wizards, runtime helpers, and publishing steps. Us

Guide for developing AstrBot plugins that match the AstrBot main repo, pass astr-plugin-reviewer checks, and cover commands, filters, hooks, LLM integrations, and agents. Use when requested to create

Search X (Twitter) data using Felo X Search API. Use when users ask about X/Twitter users, tweets, trending topics on X, tweet replies, or when explicit commands like /felo-x-search are used. Supports

Use the Datris Platform as a long-term semantic memory layer through the Datris MCP server. Local markdown memory files (MEMORY.md, memory/*.md) stay canonical; Datris is the retrieval index built fro

Fetch real-time and historical financial data from Yahoo Finance using yf-cli. Use when the user asks about stock prices, company financials, earnings calendars, analyst recommendations, options chain

Validate vitest.config.ts/js and vitest workspace configurations for syntax, deprecated options, plugin conflicts, and best practices. Use when validating Vitest test runner configs, auditing test set

Video editing tool that requires no ffmpeg installation. All video processing is executed in the cloud - no local ffmpeg installation needed. If both input and output are URLs or Alibaba Cloud OSS, th

Control Eagle application for digital asset management - search, organize, tag items, manage folders and tag groups. Use when user wants to interact with their Eagle library, search for images, manage

Talk to a user's Hardcover bookshelf via the Hardcover GraphQL API. Use when the user wants to manage reading activity in natural language: start a book, finish a book, view the Want to Read shelf, or

Capture meeting transcripts from Fireflies.ai via polling or webhooks. Auto-fetches transcripts, extracts action items/decisions/summaries, and writes structured markdown to memory. Use when user asks

This skill should be used when the user asks about Canvas LMS data — their own student account or any observed student. Triggers on phrases like "check Canvas", "what's my grade", "Canvas inbox", "wha

Q&A platform for AI agents. Search for solutions, ask questions, post answers, and vote on content. Use when you need to find solutions to programming problems, share knowledge with other agents, or l

Analyze interactions to identify patterns in what Enzo shares, why he shares it, and how it connects to his goals. Use during heartbeats for periodic analysis, when Enzo asks about his patterns/intere

Scans a macOS computer for signs of tampering, malware, keyloggers, and suspicious activity — especially useful after a device has been sent for repair or handled by a third party. Use this skill when

Design a Uniswap V4 hook architecture without code generation. Use when user wants to plan a hook, understand which callbacks to use, or review an architecture before building. Returns a design docume

Activate when: user says 'what are the odds,' 'base rate,' 'Bayesian update,' 'calibration,' or 'what's the probability'; user is making a forecast or estimating a conversion/close/hire/outcome probab

Search and match available domestic helpers (maids) from Sunrise Link's database in Singapore. Use this skill when the user wants to find, filter, or shortlist domestic helpers based on their househol

Design, implement, and debug memory systems for persistent autonomous AI agents. Use when building agents that need to survive context window rotation, preserve identity and state across sessions, imp

AKM implementation for training decision workflows. Models goals, body limits, equipment context, time budget, and recovery before outputting a workout decision.

Transform one piece of content into platform-optimized versions for YouTube, TikTok, Twitter/X, LinkedIn, Instagram, newsletters, and blogs. Adapts tone, format, length, and style for each platform's

Send feedback to the Ravi team — bugs, feature requests, praise, frustrations, suggestions. Do NOT use for general email sending (use ravi-email-send).

Strip any local project into a clean, publishable agent skill. Scan for hardcoded paths and secrets, scaffold standard structure, validate before publish. Use when you need to distill, extract, genera

Generate cost and token usage reports from OpenClaw session logs. Use when asked about API costs, token usage, billing, spending, how much something cost, or daily/session usage summaries. Works by re

Create minimal, convention-matching plugins or extensions for an existing codebase. Use when the user asks for a plugin, extension, custom module, integration, or add-on for an open-source/project rep

Answer any question using Elon Musk's thinking frameworks. Trigger this skill when the user says things like "think like Elon," "how would Musk see this," "Elon-style thinking," "first-principles anal

Audit-first frontend-backend contract analyzer for static API compatibility checks. Compare frontend request behavior with backend endpoint contracts, DTO hints, query/body/auth expectations, and prod

AI video, image & music generation. 60+ models — Sora, Veo 3, Kling, Seedance, GPT Image, Suno v5, Hailuo, WAN. Text-to-video, image-to-video, text-to-image, AI music. One API key.

AI runtime security monitoring — context graph analysis, runtime audit log correlation with CVE findings, and vulnerability analytics queries. Use when the user mentions runtime monitoring, context gr

Become an AI radio host. Register as a radio personality, create shows, book schedule slots, and publish episodes. Use when you want to host a radio show, record episodes, have multi-agent roundtable