Review kpiee-designs design docs in GitHub pull requests. Use when asked to review a PR like "https://github.com/f-scratch/kpiee-designs/pull/301", "設計書レビューして", or "PRの設計書をチェックしてコメントして". The...
Enables Claude to create, manage, and analyze Microsoft Forms surveys and quizzes via Playwright MCP
Project setup. Explore the codebase, ask about strategy and aims, write persistent context to AGENTS.md. Run when starting or when aims shift.
Sequential subagent execution with two-stage review gates for implementation plans. Use when executing multi-task plans in current session, when tasks need fresh subagent context to avoid...
|
将原始研究问题细化为结构化的深度研究任务。通过提问澄清需求，生成符合 OpenAI/Google Deep Research 标准的结构化提示词。当用户提出研究问题、需要帮助定义研究范围、或想要生成结构化研究提示词时使用此技能。
Help users build relationships with mentors and sponsors for career growth. Use when someone is looking for career guidance, wants to find a mentor, needs an advocate at work, is trying to build...
This skill should be used when the user asks to "fine-tune a DSPy model", "distill a program into weights", "use BootstrapFinetune", "create a student model", "reduce inference costs with...
Conducts thorough landscape research, competitive analysis, best practices evaluation, and evidence-based recommendations. Expert in market research and trend analysis.
Chain multiple operations together in pipelines. Use for multi-step workflows, combining research with analysis, and complex automated tasks.
|
Quaker-grounded spiritual framework for AI agents seeking grounding beyond optimization
AI agent patterns with Trigger.dev - orchestration, parallelization, routing, evaluator-optimizer, and human-in-the-loop. Use when building LLM-powered tasks that need parallel workers, approval...
Lead generation system using quiz/assessment funnels (Scorecard Marketing). Use when creating landing pages for lead generation, quiz funnels, online assessments, questionnaires that qualify...
Explains difficult concepts using master teaching methodologies (Feynman, Socratic, Cognitive Load, Dual Coding). Use when user asks to explain a concept, "I don't understand X", ELI5 requests,...
Find opportunities to add metrics and estimate numbers when exact data unavailable
This skill should be used when the user asks to "debug DSPy programs", "trace LLM calls", "monitor production DSPy", "use MLflow with DSPy", mentions "inspect_history", "custom callbacks",...
Creates, updates, or optimizes CLAUDE.md files following Anthropic best practices. Use when user requests creating, updating, improving, or optimizing CLAUDE.md files for project context, coding...
Deep research expert for comprehensive technical investigations. Use when conducting technology evaluations, comparing solutions, analyzing papers, or exploring technical trends.
Reviews LangGraph code for bugs, anti-patterns, and improvements. Use when reviewing code that uses StateGraph, nodes, edges, checkpointing, or other LangGraph features. Catches common mistakes in...