Use before a multi-human Event Storming session to prepare independent findings. Each participant's agents explore their domain and produce candidate events, aggregates, and assumptions. Keywords: event storming, domain events, prep, multi-human, exploration, DDD, aggregate, bounded context.
Use when a QQ-bound agent needs to understand what QQ channel capabilities exist by domain, without loading all NapCat 接口细节 into prompt.
Gmail: Watch for new emails and stream them as NDJSON.
Run CDISC validation checks on a domain DataFrame
Manages the user's personal domain knowledge registry — company intelligence seeded per sector that the India Proxy Agent uses before searching. Activates when user runs /curiosity-stack:knowledge, says "manage my domain knowledge", "add company to my knowledge", or clicks the "missed company" add form after an India Proxy Agent run. Also activates after any India Proxy Agent output to surface the inline add prompt.
LLD review, Low-Level Design review, 详细设计评审。Use when: 实现前需要审查 LLD 与 PRD/HLD/API Contract/Guardrails 的一致性。
Expert blockchain developer specializing in smart contract development, DApp architecture, and DeFi protocols. Masters Solidity, Web3 integration, and blockchain security with focus on building secure, gas-efficient, and innovative decentralized applications.
Electronics project architecture and constraint definition. Guides users through defining project requirements, power systems, interfaces, and physical constraints.
Expert ML engineer specializing in machine learning model lifecycle, production deployment, and ML system optimization. Masters both traditional ML and deep learning with focus on building scalable, reliable ML systems from training to serving.
Expert competitive analyst specializing in competitor intelligence, strategic analysis, and market positioning. Masters competitive benchmarking, SWOT analysis, and strategic recommendations with focus on creating sustainable competitive advantages.
Creates ADHD-friendly visual organizational tools using Mermaid diagrams optimized for neurodivergent thinking patterns. Auto-detects overwhelm, provides compassionate task breakdowns with realistic time estimates.
Web research with Graph-of-Thoughts for fast-changing topics. Use when user requests research, analysis, investigation, or comparison requiring current information. Features hypothesis testing, source triangulation, claim verification, Red Team, self-critique, and gap analysis. Supports Quick/Standard/Deep/Exhaustive tiers. Creative Mode for cross-industry innovation.
Generate daily standup reports from GitHub and Linear. Use when user says "what did I work on yesterday", "generate my standup update", "summarize my recent activity", "what's on my plate today", or "prepare my daily update for the team".
Systematic problem-solving with Good Teacher mode (default). AI guides through questions, not answers - inspired by Polya's "How to Solve It". Use when user needs to: (1) Solve problems methodically, (2) Learn to think through challenges, (3) Develop problem-solving skills, (4) Find root cause of issues. Triggers: "problem", "solve", "stuck", "how do I", "figure out", "analyze", "debug", "decide", "แก้ปัญหา", "ช่วยคิด", "ติดปัญหา"
Roadmap and refactor guidance for MoFA Studio, plus skill maintenance workflow. Use when planning large changes or updating the skill set.
Activate when breaking down implementation plans into detailed task lists with agent contexts, acceptance criteria, and status tracking
