发现 Skills

HTML-native design skill for AI coding agents — high-fidelity prototypes, slides, animations, and MP4 export with 20 design philosophies and 5-dimension critique

When the user wants to create competitor comparison or alternative pages for SEO and sales enablement. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' or 'competitive landing pages.' Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. Emphasizes deep research, modular content architecture, and varied section types beyond feature tables.

Create detailed implementation plans for software features and refactoring tasks. Use this skill when planning new features, architectural changes, or major refactoring efforts.

MateCode — management tool for the Claude Code Telegram Bridge. Used to start, stop, and monitor the Telegram remote-control service.

Multi-channel demand generation, paid media optimization, SEO strategy, and partnership programs for Series A+ startups. Includes CAC calculator, channel playbooks, HubSpot integration, and international expansion tactics. Use when planning demand generation campaigns, optimizing paid media, building SEO strategies, establishing partnerships, or when user mentions demand gen, paid ads, LinkedIn ads, Google ads, CAC, acquisition, lead generation, or pipeline generation.

When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application.

Orchestrates parallel API instances, delegated sub-tasks, and multi-agent workflows across four CLI backends (Claude Code, Cursor Agent, Gemini, Codex). Supports cost-optimized tier routing, streaming, and tool-enabled delegation patterns. Use for parallel analysis, multi-perspective reviews, cross-vendor delegation, or complex task decomposition.

Use when designing modules, APIs, and system architecture requiring independent, non-overlapping components where changes in one don't affect others.

Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.

Performance optimization guidelines for React and Next.js from Vercel Engineering. Use this skill when writing, reviewing, or refactoring React/Next.js code to enforce optimal performance patterns. It applies to tasks involving React components, Next.js pages, data fetching, bundle optimization, or other performance improvements.

Optimizes existing Claude Code skills for token efficiency using layered loading, content classification, and progressive disclosure. Use when optimizing skills, reducing token usage, reviewing skill efficiency, refactoring large/bloated SKILL.md files, auditing a skill repo for optimization opportunities, or when user mentions skill optimization, skill review, reduce tokens, skill efficiency, or bloated skill. Invoked during skill creation (post-create optimization), skill intake (post-adapt/add optimization), or standalone skill review.

Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks

name: node-device description: Control paired mobile devices via the OpenClaw node protocol. Use when: (1) Taking camera photos from paired phones, (2) Getting device location/GPS, (3) Sending notifica...

Create an empty external 1C report (scaffold of XML sources)

Send messages to users via WhatsApp and other connected channels. Use when asked to notify someone, send a message, reply to a contact, message a group, or proactively communicate through WhatsApp. Supports text, images, documents, audio, video, and stickers. Also provides group etiquette for observing group conversations — use `<no-reply/>` to stay silent when a response is not needed.

Foundational Go patterns covering types, interfaces, goroutines, channels, and common idioms. Use when writing Go code, understanding Go's concurrency model, or needing guidance on which specialized Go skill to use. This is the entry point for Go development.

High-quality Feishu/Lark Docx writing via OpenClaw. Covers tool selection, chunked writing, native tables, $ symbol escaping, and all known pitfalls. Trigger on Feishu doc/docx links, "write to Feishu doc", "generate a Feishu doc", "append/replace docx", or when users want consistently good doc formatting.

Apply common patterns (external integration, async processing, multi-tier architecture, caching). Provides tested templates.

Send WhatsApp messages to users. After completing tasks, ask what they want next via WhatsApp and continue the conversation until they say they're done.

Flask/Werkzeug-specific pitfalls to check for in addition to the general data-flow analysis. Each pattern lists what to grep for, why it is dangerous, the safe equivalent, and severity guidance.

Configure Better Auth for JWT-based authentication in LearnFlow with student and teacher roles

Configure Dapr pub/sub components for event-driven communication between LearnFlow microservices via Kafka

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.

Bundled agents, commands, hooks, and settings that users install via `aspens add` and `aspens doc init` into their .claude/ directories