Explorar skills

Auto-activate for msgspec imports, msgspec.Struct, msgspec.Meta, msgspec.json, msgspec.msgpack, tagged unions, enc_hook, dec_hook, or convert(). Use when defining msgspec models, serialization codecs, validation constraints, discriminated unions, or Litestar DTO data shapes. Not for Pydantic, dataclasses, attrs, or ORM models unless converting at a boundary.

Structured teardown of AI products (ChatGPT, Claude, Gemini, Perplexity, Copilot, etc.). Analyzes product decisions, UX patterns, technical architecture, business model, and competitive positioning.

Use when user invokes /docgen to generate or update documentation. Also triggers on "generate docs", "update the README", "write the changelog". Accepts a doc type (readme, api, architecture, changelog) and optional scope. Always outputs to conversation first and asks before writing to disk. Do NOT use for explaining code behavior — use /explain instead.

Template for structured sub-agent invocation using 4-part prompting (GOAL/CONSTRAINTS/CONTEXT/OUTPUT) and F# pipeline notation. Use when orchestrating sub-agents or designing multi-agent workflows.

Role-based brainstorming with dual modes: --scoped (sequential Task tool, 5 roles) and --exploratory (Agent Teams peer debate, 4 roles). Use for feasibility assessment and idea validation.

Template for structured sub-agent output including YAML log format, task completion reports (WHY/WHAT/TRADE-OFFS/RISKS), and summary constraints. Use when defining how sub-agents should report results.

创建 PRD 文档（自动化生成 + 自检 + handoff）

Use when you want to sweep all open pull requests across all repos, triage their status, run code reviews on unreviewed PRs, merge what's ready, fix quick blockers, and produce a full status report. Trigger when the user says "check my PRs", "close out open PRs", "what's the status of my PRs", "sweep my PRs", "PR sweep", "pull request sweep", or wants a cross-repo PR status report. Future: pairs w

Use when user invokes /harness-sync or wants to sync AI tool configurations across Claude Code, Cursor, and GitHub Copilot. Inventories installed skills, instruction blocks, and MCP configs on all detected platforms, reports divergence, and lets the user push or pull changes. Push path reuses harness-compile logic. Pull path updates harness.yaml and recompiles. Never overwrites without explicit co

Plan a new feature from concept to approved implementation plan. Activates Product Council for strategic evaluation, then Feature Council for technical planning. Produces a documented decision and scoped task breakdown. Use when starting any new feature work.

<!-- @include templates/prompts/iron-law.md --> 对指定的服务或应用进行? ?面的代码评审。 须执行，不可跳过） 从用户输? ?中提取功能名称? ?键词 检查实现代码是否存在：在 backend/ 和 frontend/ 下搜索与该功能相? ?的源代码文件（非测试文件） 检查测试是否通过：找到对应的测试代码并运行，确认测试处于绿灯状态（? ?部通过） 未找到实现代码 →…

Get detailed information about a specific research finding or observation. Use when injected research mentions "[/research-detail ID]" for more sources and context.