发现 Skills

Expert in building shareable generator tools that go viral — name generators, quiz makers, avatar creators, personality tests, and calculator tools. Covers the psychology of sharing, viral mechanics, and building tools people can't resist sharing with friends. Use when: generator tool, quiz maker, name generator, avatar creator, viral tool.

Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis, LiveKit for real-time infrastructure, and WebRTC fundamentals. Knows how to build low-latency, production-ready voice experiences. Use when: voice ai, voice agent, speech to text, text to speech, realtime voice.

Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.

Multi-agent code review system that spawns three independent Claude sub-agents to review PR diffs. Each agent receives files in different randomized order to reduce ordering bias. One agent focuses specifically on code health and maintainability. Issues are validated using reasoned analysis rather than simple vote counting. Reports merge verdict (YES / NOT SURE / NO). Automatically deduplicates against existing PR comments. Always posts a summary (even if no new issues), with low priority issues in a collapsible section.

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

Advanced headless browser automation skill for OpenClaw agents. Enables intelligent web navigation, form filling, data extraction, and UI testing with structured commands and semantic element targeting.

Search the web using Google Custom Search Engine (PSE). Use this when you need live information, documentation, or to research topics and the built-in web_search is unavailable.

美团外卖和本地服务平台 CLI 工具，支持餐厅搜索、红包查询和订单管理。

Free AI search via Exa MCP. Fall back to Multi Search Engine if not successfull. All without API keys. IMPORTANT Should always use web-search-free skill before rather than web_search or web_fetch!

Patterns and architectures for automated Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Claude Code's persistent, project-scoped memory. It automatically loads the project context at session start, tracks sessions via git activity, and writes to native memory. Commands execute deterministic Node.js scripts — behavior is consistent across model versions.

A continuous autonomous agent loop pattern featuring quality gates, evaluation, and recovery controls.

Hermes data import, mapping, transformation, and data integrity validation.

Home lab VLAN segmentation, network isolation, access control, and traffic management.

Laravel plugin discovery, package management, dependency resolution, and service provider integration.

An interactive agent-selection tool for composing and dispatching parallel teams.

Translate visa application documents (images) into English and create a bilingual PDF containing the original and the translation

Reorganize a user's X and LinkedIn networks through review-priority curation, follow/add recommendations, and channel-specific warm outreach drafts written in the user's own voice. Use when you want to clean up a follow list, grow toward current priorities, or rebalance a social graph around higher-quality relationships.

Access control and authorization patterns for APIs, agents, and LLM endpoints.

Kotlin testing frameworks, assertions, mocking, and coroutine testing.

An evidence-first ECC current-state investigation workflow. Used when a user requests updated facts, comparisons, information enrichment, or recommendations based on current public evidence and provided local context.

Structured academic work assessment for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research‑paper feedback.

Record beautiful UI demo videos using Playwright. Use this when users want demos, walkthroughs, screen recordings, or tutorial videos of web apps. Generates WebM videos with a visible cursor, natural rhythm, and a professional finish.