Explore skills

Autonomous work execution across all Swarm projects. Reads last session summary, picks highest-priority work, executes it, then loops to the next item. Only stops when blocked on the operator or nothing remains. Trigger on: "what's the status", "project status", "what needs work", "prioritize", "what's next", "plan work", "coordinate", "which projects", "phase status", "roadmap", "backlog", "sessi

Provides guidance for property-based testing across multiple languages and smart contracts. Use when writing tests, reviewing code with serialization/validation/parsing patterns, designing features, or when property-based testing would provide stronger coverage than example-based tests.

Intelligent model routing for Claude Code sessions. Recommends optimal model (Opus/Sonnet/Haiku) and effort level based on task complexity. Delegates mechanical work to cheaper subagents. Maximizes quality-per-dollar across the entire session. Trigger on: any new session, "save tokens", "cheaper model", "delegate this", "use sonnet", "effort level", "cost", or automatically when task complexity is

Self-assessment and auto-update for Claude Code's installed skills, CLAUDE.md files, and reference data. Audits for staleness, gaps, overlaps, and freshness. Triggers on: "update your skills", "skill audit", "skill assessment", "refresh skills", "are your skills up to date", "check your skills", "review your context", "tune yourself up", "make yourself better".

Identifies dependencies at heightened risk of exploitation or takeover. Use when assessing supply chain attack surface, evaluating dependency health, or scoping security engagements.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Minimize Claude token and cost waste across ALL surfaces — Claude Code subagents, API calls in code, and artifacts. Routes subagent model selection via the Agent tool's model parameter. Recommends /model switches when the current model is overkill or underpowered. Applies to any code importing anthropic or calling /v1/messages. Trigger on: "API call", "artifact", "pipeline", "multi-agent", "LangGr

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Full project scaffolding. Create ops file, repo, CLAUDE.md, hooks, GitHub, repo-map entry.

数仓性能优化流程，适用于分析 ETL SQL 执行计划、分区裁剪、JOIN 策略、数据倾斜和资源瓶颈。直接调用命令：/dw-performance-optimization。

数仓自测流程，适用于通过 data-quality-checker subagent 执行 23 项标准自测并只返回摘要。直接调用命令：/dw-self-test。