Skill rating

Extract text from PDF files using PyMuPDF. Parse tables, forms, and complex layouts. Supports OCR for scanned documents.

Low-level Feishu document block operations via REST API. Use when feishu_doc built-in actions are insufficient: batch update cells, precise position insert, traverse block tree, table row/column manip

Complete development work by presenting structured options for merge, PR, or cleanup. Use when implementation is complete, all tests pass, and you need to decide how to integrate work. Triggers on fin

Full LP workflow from opportunity scanning to position entry. Autonomously finds the best LP opportunity, designs a strategy, assesses risk, executes any needed swaps, enters the position, and reports

DEPRECATED. This skill is retained only for migration. Use @Cole-Z/govee-control for current Govee OpenAPI setup and control guidance.

Handles joining and leaving group conversations on messaging platforms (WhatsApp, Signal, Telegram, etc.). Use when the owner tags the agent into a group chat to participate for a time-limited window,

UI/UX design intelligence and implementation guidance for building polished interfaces. Use when the user asks for UI design, UX flows, information architecture, visual style direction, design systems

Share images, screenshots, and files from the AI workspace to users on the local network via HTTP. Use when the agent needs to show images, browser screenshots, or any files to the user and the curren

Builds a reusable memory mesh for OpenClaw with tagged memory layers, local consolidation, global sync, GitHub Issue contribution self-check, and optional automated issue posting. Use when users want

Launch non-blocking Claude Code headless tasks from slash command dispatch. Use when user requests async coding jobs and does not require slash-only Claude plugins.

Build and deploy a paid API that other agents can pay to use via x402. Use when you or the user want to monetize an API, make money, earn money, offer a service, sell a service to other agents, charge

Use when you need to delegate, track, or review work.

Guides the agent in Openclast/Openclaw wallet usage, approvals, and safety rules. Use when users ask about wallet setup, balances, transactions, approvals, or key export.

Browser automation via Chrome DevTools Protocol (CDP) for OpenClaw. Use when user needs to take screenshots of websites, automate browser actions, or interact with web pages programmatically. Triggers

Turn your concept analysis into search queries — research the landscape before consulting an attorney. NOT legal advice.

Manage personal finances, track spending by category, set budgets, and receive reminders for EMIs and one-time annual expenses. Use for logging expenses, checking budget status, or setting up financia

Use when accessing Plaud voice recorder data (recordings, transcripts, AI summaries) - guides credential setup and provides patterns for plaud_client.py

BTC PoW grind nonce till skill/output benchmark score > threshold. Verifiable excellence for antifragile meritocracy—no hype, pure quality proof. Use for skill evaluation, fork scoring, collab verific

Write proposals that confirm verbal agreements and close deals, not proposals that try to sell. Sources: Consulting Success (reviewed 100s of proposals, 60%+ win rate benchmark), Aura/Prosal (2024 ...

Generate Redis key patterns and data structures. Use when designing Redis architecture.

Write landing pages, product descriptions, ads, and sales copy using proven direct-response frameworks. Sources: Digitaloft (13 frameworks), CrazyEgg, NON.agency, DesignRush (direct response exampl...

Captures and logs choices, options, or prompts that the agent evaluated and decided NOT to execute. Use whenever you skip a task, reject an approach, or choose one method over another to provide trans

Make components responsive with proper breakpoints. Use when your components look terrible on mobile.

Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP

Create or update AgentSkills based on lessons from building workspace-analyzer. Use when designing, structuring, packaging skills, testing, and publishing. Includes our learned best practices, dos/don

Builds and manages structures in Structs. Handles construction, activation, deactivation, movement, defense positioning, stealth, and generator infusion. Use when building a struct, activating or deac

Task continuity, session snapshots, and gateway restart recovery. Use when starting long-running tasks (register them), after gateway restart (check for interrupted tasks), or when user asks about tas

Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.

Transcribe audio files using OpenAI's gpt-4o-mini-transcribe model with vocabulary hints and text replacements. Requires uv (https://docs.astral.sh/uv/).

在 Windows 11 上"直接发声"的 TTS（从 WSL2/TUI 调用 powershell.exe + System.Speech）。适用于用户说"说出来/读出来/语音播报/用TTS"，或反馈"没声音/tts 生成的 mp3 是空的/播不出来"，以及需要中文语音但 OpenClaw 内置 tts 不可用时。

Downloads YouTube videos to ~/Downloads. Use when user wants to download a YouTube video to their machine.

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing,

Use this skill immediately and proactively when the user mentions video editing, clipping, highlight reels, short-form video, Reels, Shorts, TikTok, vertical video, or asks to process a video file. Do

Managed headful Chrome browser for OpenClaw agents with anti-bot-detection, human-in-the-loop VNC takeover, and multi-session window isolation. Use when: (1) setting up browser automation on a new mac

Meta-skill that orchestrates the full API development lifecycle — from design through documentation — by coordinating specialized skills, agents, and commands into a seamless build workflow.

Use H1DR4 BountyHub as an agent: create missions, submit work, dispute, vote, and claim escrow payouts.

Socratic design refinement before coding. Use when user requests feature without clear spec.

Capture website screenshots from the command line. Use when user wants to take screenshots of any URL (Twitter, news sites, webpages) and send them via Discord/Feishu. Requires capture-website-cli to

Integration scripts for the creative agent swarm managed by overstory (Claude Code). Use when configuring or running researcher, social media, blog, or scribe agents.

Generate crypto market briefing reports with latest news, price analysis, trend predictions, sentiment analysis, and Fear & Greed Index. Use when user asks for crypto news summary, market briefing, BT

Convert CSS files to Tailwind utility classes. Use when migrating from vanilla CSS to Tailwind.

Meta-skill for iterative, hypothesis-driven deep research using deepresearchwork, tavily-search, literature-search (Semantic Scholar mapping), and perplexity-deep-search. Use when the user needs multi

Generate human-readable summaries of git diffs. Use when you need to explain what changed.

Use this skill to keep up to date with specific Discord channels by fetching recent messages. Requires DISCORD_TOKEN.

HDF5-backed persistent cognitive memory for AI agents. Use when: (1) saving conversation exchanges to long-term memory, (2) searching/recalling past conversations by semantic similarity, (3) managing

Browse culture articles and generate personalized HTML newsletters via MCP

Repair malformed JSON files by normalizing them through Node.js evaluation. Use this to fix trailing commas, single quotes, unquoted keys, or other common syntax errors in JSON files (e.g. config file

Manage secrets via macOS Keychain instead of plaintext files. Migrate existing secrets, read/write keychain entries, bridge to files for bash tools, audit for leaks, diagnose access issues. Use when a

Feishu/Lark Custom Bot API wrapper for sending messages to Feishu channels via webhook. Use when users need to send text messages, images, rich text posts, interactive cards, or share chat content to

Score a website lead 0–100 based on audit signals from the website-auditor skill, assign a priority tier (Hot/Warm/Lukewarm/Cold), and write the result to a Google Sheet. Applies a weighted rubric acr