发现 Skills

Use state port register sources for official port registry information and maritime infrastructure governance context.

Use Agriculture and Food Board animal keeper registration sources for registry workflow context and extractable official outputs.

Mama nagging mode — Chinese-style mama nagging drives the AI to exhaust every solution. Core behavior constraints remain unchanged (three red lines, methodology, 7-item checklist); the narration switches from big-tech PUA style to mama-like nagging. Triggers: '/pua:mama', '/pua mama', '妈妈模式', '妈妈唠叨', 'mama mode', '唠叨模式'. Like /pua:yes, this only changes narration style and does not alter core behavior.

5W1H Decision Framework Tool. Use for: (1) Systematic decision-making before creating todos, (2) Preventing duplicate implementation, (3) Detecting avoidance behavior, (4) Ensuring agile refactor compliance with executor/dispatcher separation

Brainstorm product ideas for an existing product using multi-perspective ideation from PM, Designer, and Engineer viewpoints. Use when generating new feature ideas, brainstorming solutions for an identified opportunity, or ideating with a product trio.

Generate a Lean Canvas with problem, solution, metrics, cost structure, UVP, unfair advantage, channels, segments, and revenue. Use when exploring a lean startup canvas, testing a business hypothesis, or modeling a new venture.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Transforms technical blueprints and information about methods into authority narratives that position the specialist as a reference in the niche. Use when the user requests method history, authority narrative, expert storytelling, method story, authority positioning, origin story, expert journey, authority copy, method pitch, or a blueprint for a story. Also triggers when they mention creating a narrative, telling my story, personal brand storytelling, or authority in the niche.

Assess whether it is safe to enable `tools.fs.workspaceOnly=true` on your OpenClaw agent without breaking current workflows. Use before tightening filesystem boundaries — generates a path dependency snapshot, classifies inside vs outside workspace usage, identifies which tasks would break first, and recommends whether a trial is worth scheduling now. Does NOT enable workspaceOnly; read-only analysis only.

Project-specific patterns for the Marstek integration (config flow, coordinator, scanner, entities, translations)

Technical documentation with API docs and architecture guides

Use this skill when choosing a format, designing a schema, naming files, or deciding where data lives. Codifies the filesystem-as-database principle, parquet for tabular, safetensors for tensors, YAML for config, DuckDB as the query layer, with the constraint that a static browser fetch must be able to read whatever Python writes.

Game technology selection: choose the appropriate engine, framework, and tools based on game requirements. Activated when the user says "technical selection", "which engine to use", or "technical solution". Input @concept.md + @systems-breakdown.md, output @tech-stack.md.

Manage port-out requests when numbers are being ported away from Telnyx. List, view, and update port-out status. This skill provides Ruby SDK examples.

Register brands and campaigns for 10DLC (10-digit long code) A2P messaging compliance in the US. Manage campaign assignments to phone numbers. This skill provides Python SDK examples.

Configure account addresses, authentication providers, IP access controls, billing groups, and integration secrets. This Skill provides Java SDK examples.

Access Telnyx LLM inference APIs, embeddings, and AI analytics for call insights and summaries. This skill provides Ruby SDK examples.

Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Use when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting. Covers general Figma data fetching and exploration. Do NOT use when the goal is specifically pixel-perfect code implementation from a Figma design (use figma-implement-design instead).

React composition patterns that scale. Use when refactoring components with boolean-prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes. Do NOT use for React/Next.js performance optimization (use react-best-practices instead).

Senior React Native and Expo engineer for building production-ready cross-platform mobile apps. Use when building React Native components, implementing navigation with Expo Router, optimizing list and scroll performance, working with animations via Reanimated, handling platform-specific code (iOS/Android), integrating native modules, or structuring Expo projects. Triggers on React Native, Expo, mobile app, iOS app, Android app, cross-platform, native module, FlatList, FlashList, LegendList, Reanimated, Expo Router, mobile performance, app store. Do NOT use for Flutter, web-only React, or backend Node.js tasks.

Use when APIs fail repeatedly with version-related errors (method not found, wrong arguments, unknown flag) or when about to use library APIs with uncertain knowledge - guides finding current, accurate documentation instead of guessing from training data

Automate Figma tasks via Rube MCP (Composio): files, components, design tokens, comments, exports. Always search tools first for current schemas.

You are a code migration expert specializing in transitioning codebases between frameworks, languages, versions, and platforms. Generate comprehensive migration plans, automated migration scripts, and

Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.