Loading...
Loading...
Found 126 Skills
Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.
Expert software architecture covering system design, distributed systems, microservices, scalability patterns, and technical decision-making.
Guide product managers in choosing the right prioritization framework by asking adaptive questions about product stage, team context, decision-making needs, and stakeholder dynamics. Use this to avoid
Create, configure, and use Frontic blocks, listings, and pages for e-commerce data. Use when working with Frontic configuration, building product/category pages, creating data sources, or integrating the Frontic client. Covers resource decision-making, block/listing creation guidelines, and client usage patterns.
Write technical specifications that give agents enough context to implement features while leaving room for autonomous research and decision-making. Use when planning features, documenting architecture decisions, or creating implementation guides.
Optimize decision-making speed by managing choice quantity. Use when designing navigation, menus, feature sets, onboarding flows, or any interface where users must choose between options.
Analyzes Claude Code session transcripts (JSONL files) to reveal context window content, token usage patterns, and decision-making processes using view_session_context.py tool. Use when debugging Claude behavior, investigating token patterns, tracking agent delegation, or analyzing context exhaustion. Triggers on "why did Claude do X", "analyze session", "check session logs", "context window exhaustion", or "track agent delegation".
Business strategy expertise for strategic planning, competitive analysis, market entry, M&A strategy, portfolio management, and strategic decision-making. Use when analyzing competitive positioning, planning growth strategies, or making strategic decisions.
Intelligent skill retrieval and recommendation system for Claude Code. Uses semantic search, intent analysis, and confidence scoring to recommend the most appropriate skills. Features: (1) Smart skill matching via bilingual embeddings (Chinese/English), (2) Prudent decision-making with three confidence tiers, (3) Historical learning from usage patterns, (4) Automatic health checking and lifecycle management, (5) Intelligent cache cleanup. Use when: User asks to find/recommend a skill, multiple skills might match a request, or skill selection requires intelligent analysis.
Q-learning, DQN, PPO, A3C, policy gradient methods, multi-agent systems, and Gym environments. Use for training agents, game AI, robotics, or decision-making systems.
Daily Review Assistant - An AI-assisted decision-making tool for cleaning up knowledge inboxes. The Agent provides "Keep/Delete" suggestions with reasons, and users manually execute after confirmation. Following the principle of "Collect without judging, make decisions during daily review", complete daily knowledge organization in 5-10 minutes. Triggers: /daily-review, /日清, /review
Implement ReasoningBank adaptive learning with AgentDBs 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.