Analyze repository structure, patterns, conventions, and documentation for understanding a new codebase
Meta-skill for creating and managing Claude Code skills
Configure HUD display options (layout, presets, display elements)
|
Activate multi-agent orchestration mode
Drive development using delegated agent workflows. Coordinates multi-agent task execution with proper supervision and result integration.
Save notes to notepad.md for compaction resilience
Run Codex CLI for deep code analysis and second-opinion reviews. Use when the user explicitly asks for Codex analysis, Codex help, or wants a second opinion from Codex on code, architecture, or...
Orchestrate parallel scientist agents for comprehensive research with AUTO mode
Run and create evals for testing agent behavior. Use when the user wants to create or run an eval.
QA cycling workflow - test, verify, fix, repeat until goal met
Use when completing tasks, implementing major features, or before merging
Use when user asks to search the web, look something up online, find current/recent/latest information, or needs cited answers. Triggers on "search", "look up", "find out about", "what is the...
基于预设 URL 列表抓取内容,筛选高质量技术信息并生成每日 Markdown 报告。
基于预设 URL 列表抓取内容,筛选高质量技术信息并生成每日 Markdown 报告。
基于预设 URL 列表抓取内容,筛选高质量技术信息并生成每日 Markdown 报告。
Full autonomous execution from idea to working code
Comprehensive DeepResearch methodology for conducting rigorous, traceable research projects with quality gates, structured analysis, and decision-ready deliverables. Use when (1) Conducting deep...
|
Agentic memory system for writers - track characters, relationships, scenes, and themes