domain-modeling
Build or revise domain vocabulary in GLOSSARY.md and record approved architectural decisions. Use when terms or domain boundaries need resolving, or the user requests a glossary or ADR.
- License 许可
- MIT
- 最近更新
- 2026-10-17
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- domain-modeling
- description
- Build or revise domain vocabulary in GLOSSARY.md and record approved architectural decisions. Use when terms or domain boundaries need resolving, or the user requests a glossary or ADR.
02 资源文件 3
- 参考文档ADR-FORMAT.md2.7 KB
- 参考文档agents/openai.yaml101 B
- 参考文档GLOSSARY-FORMAT.md2.7 KB
03 SKILL.md 正文
Domain modeling
Read docs/agents/domain.md for the existing context layout and ADRs. This profile keeps its vocabulary in GLOSSARY.md, or in context-specific glossaries named by GLOSSARY-MAP.md.
- Challenge terms that conflict with the existing glossary. Ask which meaning the user intends.
- Resolve overloaded language through concrete scenarios and code evidence. Propose one canonical term per concept.
- When the user requested domain documentation, record resolved terms in
GLOSSARY.mdas they settle. Preserve existing entries. Use GLOSSARY-FORMAT.md for the domain title, description, language entries, and context layout. Create a missing glossary only once there is a resolved term to record. - During a discussion without a documentation request, present proposed entries in conversation and ask before creating durable files.
- Offer an ADR only for a costly-to-reverse decision, surprising without context, that follows a real tradeoff. Write it after approval using ADR-FORMAT.md.
Keep the glossary free of implementation details, specifications, scratch notes, and decisions. Record approved decisions in ADRs. Create glossary files and ADR directories only when an authorized deliverable needs them. Report conflicts with existing ADRs rather than silently replacing their decisions.
04 同仓库更多 Skills
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
wizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
wait-what
Stop. That last message did not land: re-pitch it.
visual-spec
Turn the grilled conversation into a spec, optionally confirming risky decisions as a visual HTML explainer first, then publish it to the issue tracker.
triage
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.