发现 Skills

OpenClaw peer discovery and coordination. Setup claw-clan, discover peers on LAN, manage fleet, configure SSH between OpenClaw instances, keep-alive monitoring

Long-form web-novel breakdown. Deeply analyzes a hit long-form novel's golden three chapters, character architecture, satisfaction-beat design, and pacing control. Supports two modes: - Quick analysis: analyzes the golden three chapters and the overall structure (default) - Deep analysis: dissects the entire novel chapter by chapter and outputs structured files to a specified directory Trigger phrases: /story-long-analyze, /long-story-analyze, “help me dissect this book”, “analyze the golden three chapters” To trigger deep mode: “deep analysis”, “full analysis”, “systematic analysis” or provide the path to the novel text file

Comprehensive outbound email strategy skill for cold outreach, email sequences, and multi-channel campaigns. Use when writing cold emails, creating outreach sequences, optimizing response rates, designing follow-up cadences, or building outbound campaigns. Covers prospecting, personalization frameworks, sequence design, subject lines, response handling, compliance, email design, HTML email templates, email layout, email marketing, newsletter design, drip campaigns, email subject lines, email headers, and cold email templates for discovery calls and SDR workflows.

Comprehensive React component testing with Jest and React Testing Library covering configuration, mocking strategies, async testing patterns, hooks testing, and integration testing best practices

Comprehensive guide for building production-grade LLM applications using LangChain's chains, agents, memory systems, RAG patterns, and advanced orchestration

User research, usability heuristics, user psychology, accessibility, inclusive design, user testing, and UX metrics

Build comprehensive security context dossiers for functions in DeepExtractIDA binaries -- gathering identity, attack reachability, data flow exposure, dangerous operations, resource patterns, complexity metrics, and neighboring context in one command. Use when the user asks to audit a function's security posture, build a security dossier, assess attack surface, check function reachability from exports, find dangerous API usage, or needs pre-audit context gathering for a decompiled function.

Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.

Pre-IC packet assembly for each IC cycle. Assembles the docket, pulls each deal's memo and cross-references, tracks IC conditions from prior decisions through to completion, consumes the sensitivity / stress-test output, surfaces comp evidence with freshness flags, and runs an LP capital availability check. The pack is the IC committee's input; the committee owns the decision. The workflow refuses to publish a deal's packet if blocking Dealpath DQ rules are open (`dp_completeness_ic_record`) or if required sensitivity tests are missing. Outputs include the IC packet, the condition-tracking rollup (from prior cycles), and the post-IC condition-log draft ready for minute-keeping.

Suggests performing manual context compaction at logical intervals to preserve context across task phases instead of relying on arbitrary automatic compaction.

Use when the user says "brainstorm this", "I have an idea", "help me think through this", "office hours", "is this worth building", or describes a new product idea before any code is written. YC-style strategic conversation in two modes (Startup diagnostic / Builder generative); saves a design doc.

Design, refine, debug, and verify China-market-first quantitative trading strategies across framework-agnostic research flows and common engines such as vn.py, RQAlpha, TqSdk, qteasy, LEAN, Freqtrade, Backtrader, and OptionForge. Use when an agent needs to translate a trading idea into strategy logic, configs, backtests, risk rules, framework adapters, or evidence-backed delivery.

Use when user needs React development help. Examples: "build a React component", "optimize React performance", "implement custom hooks", "set up server components", "fix React rendering issues"

Use when: understanding business scenarios, identifying tax-related events, decomposing business flows. Trigger: business analysis, operating scenarios, tax-related matters, business decomposition, new client onboarding. NOT for: specific tax calculations, tax filing, accounting entries.

Use this skill when the user asks about "Effect testing", "@effect/vitest", "it.effect", "it.live", "it.scoped", "it.layer", "it.prop", "Schema Arbitrary", "property-based testing", "fast-check", "TestClock", "testing effects", "mocking services", "test layers", "TestContext", "Effect.provide test", "time testing", "Effect test utilities", "unit testing Effect", "generating test data", "flakyTest", "test coverage", "100% coverage", "service testing", "test doubles", "mock services", or needs to understand how to test Effect-based code.

Use a visible browser to automatically complete MateClaw DingTalk channel integration. When encountering a login page, the process must pause and wait for the user to log in manually before continuing.

Audits and enhances API documentation for FastAPI and REST endpoints. Identifies missing descriptions, incomplete response codes, missing examples, and generates enhanced docstrings, Pydantic model examples, and OpenAPI spec improvements. Triggers on: "generate API docs", "document this API", "OpenAPI for", "add examples to", "improve docstrings", "API documentation audit", "FastAPI docs", "document endpoints", "API reference", "swagger docs", "REST API docs", "endpoint documentation", "response documentation". Use this skill when API endpoints need documentation or documentation audit.

Produces calibrated three-point estimates (best/likely/worst case) with explicit unknowns, confidence intervals, and assumption documentation. Breaks work into atomic units, identifies technical and scope uncertainties, calculates PERT ranges, and provides confidence rationale. Triggers on: "estimate this", "how long will this take", "effort estimate", "time estimate", "best case worst case", "confidence interval", "sizing", "estimate effort", "how big is this", "story points", "t-shirt sizing", "estimate the work", "project estimate". Use this skill when a task or project needs an effort estimate with explicit uncertainty.

Systematic prompt engineering: analyzes existing prompts for failure modes, generates structured variants (direct, few-shot, chain-of-thought), designs evaluation rubrics with weighted criteria, and produces test case suites for comparing prompt performance. Triggers on: "improve this prompt", "prompt engineering", "prompt lab", "generate prompt variants", "A/B test prompts", "evaluate this prompt", "prompt failure modes", "optimize prompt", "write a better prompt", "prompt design", "prompt iteration", "few-shot examples". Use this skill when designing, improving, or evaluating LLM prompts.

Validate WCAG 2.1 Level AA compliance and accessibility best practices. Use when performing accessibility audits and WCAG certification.

Summarize recent Jira issues, sprint progress, and comments

Refactor and review SwiftUI view files for consistent structure, dependency injection, and Observation usage. Use when asked to clean up a SwiftUI view’s layout/ordering, handle view models safely (non-optional when possible), or standardize how dependencies and @Observable state are initialized and passed.

Implements business requirements as scalable, maintainable Magento 2 features. Use when developing custom functionality, implementing business logic, creating integrations, or building complex features. Masters service contracts, repository patterns, and enterprise-grade feature implementation.

Automate Adrapid tasks via Rube MCP (Composio). Always search tools first for current schemas.