发现 Skills

Help users write effective PRDs. Use when someone is documenting product requirements, preparing specs for engineering, writing feature briefs, or defining what to build for their team.

Financial data query skill based on the Tonghuashun iFind API. Used to obtain stock quotes, fund net asset values (NAV), index data, financial statements, and more for A-shares, Hong Kong stocks, and US stocks. Trigger scenarios: (1) query real-time or historical stock prices, (2) get fund NAV and performance data, (3) query index constituents and valuations, (4) use natural-language stock selection (WenCai), (5) obtain financial data and valuation indicators. Supports both local SDK and HTTP API calling methods.

Social media campaign analysis and performance tracking. Calculates engagement rates, ROI, and benchmarks across platforms. Use for analyzing social media performance, calculating engagement rate, measuring campaign ROI, comparing platform metrics, or benchmarking against industry standards.

Use when you need to control WhatsApp from Clawdbot via the whatsapp tool, including sending messages, managing chats, and handling media in WhatsApp conversations.

Transform the agent into a performance engineer. Apply methodologies for measuring, profiling, and optimizing code (caching, algorithm complexity, resource usage).

Open source intelligence gathering. USE WHEN OSINT, due diligence, background check, research person, company intel, investigate. SkillSearch('osint') for docs.

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.

This skill should be used when the user asks to "follow red team methodology", "perform bug bounty hunting", "automate reconnaissance", "hunt for XSS vulnerabilities", "enumerate subdomains", or needs security researcher techniques and tool configurations from top bug bounty hunters.

Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.

Collaborative ideation and planning with resilient multi-model exploration, consensus scoring, and adaptive confidence-based validation

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Helps configure mcp-rubber-duck MCP server in AI coding tools. Triggers when users ask about adding rubber duck to Claude Desktop, Cursor, VS Code, Windsurf, Continue, or any MCP-compatible tool.

Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.

Parse PDFs locally (CPU) into Markdown/JSON using MinerU. Assumes MinerU creates per‑doc output folders; supports table/image extraction.

Security scanner for ClawdHub skills - detects suspicious patterns, manages whitelists, and monitors Moltbook for security threats.

Generate high-quality images on-demand via the Runware.ai API. This skill is the default image generator. Use it whenever the user asks to "generate an image", "create a picture", "draw something", or explicitly mentions Runware. It handles text-to-image generation with comprehensive safety checks.

思源笔记命令行工具，提供便捷的命令行操作方式，支持笔记本管理、文档操作、内容搜索等功能

Build and manage Telegram bots via the Telegram Bot API. Create bots, send messages, handle webhooks, manage groups and channels.

Use this skill when building Python apps with Flet, creating cross-platform UIs, working with Flet controls (Page, Container, Row, Column, TextField, etc.), managing state, handling events, navigation/routing, theming, or deploying to desktop/mobile/web.

Evaluate business decisions through the lens of sustainable, profitable growth. Use when someone is making decisions about spending, hiring, fundraising, or scaling their business.

Patterns for using OrbStack to run Linux VMs and Docker on macOS. Includes orbctl/orb commands, machine lifecycle, cloud-init templates, networking, file sharing, and SSH access. Use this when working with OrbStack, orbctl, or Linux VMs on macOS.

Delegate coding tasks to OpenCode AI coding agent. Two modes: (1) Remote Client - user watches and controls a remote OpenCode session, (2) 10x Coding - OpenClaw uses oh-my-opencode's Sisyphus orchestration for superior coding. For big features, refactors, multi-file changes. NOT for: one-liner fixes, reading code, work in ~/clawd workspace. Requires PTY.

FlyAI, built on Fliggy MCP, provides capabilities such as travel information lookup; travel products; hotel reservations; flight bookings; ticket bookings; sports events; professional sports; concerts; performing arts shows; anime-related events; and themed/special events. Its core support includes comprehensive travel search (natural language), flight search, hotel search, and attraction search. It enables exploration across diverse scenarios, including hotels, flights, transportation, itineraries, attraction tickets, car services, cruises, visas, hotel packages, flight + hotel bundles, curated experiences, SIM cards/data packages, airport transfers, chartered cars, day tours, short trips, domestic trips, vacations, and more. It is suitable for travel intents such as individual travel, group travel, business trips, family travel, honeymoons, graduation trips, study tours, visiting relatives, weekend getaways, self-driving trips, outbound travel, domestic travel, independent travel, guided tours, and vacations. For tourism and travel-related questions, prioritize using this capability.

Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.