본문으로 건너뛰기
cccskills
무료GitHub에 공개

domain-modeling

Use when pinning down domain terminology, maintaining the domain model, or when a term conflicts or needs sharpening.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(3)

  • SKILL.md5.6 KB
  • agents/openai.yaml186 B
  • references/CONTEXT-FORMAT.md1.5 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Domain modeling

Contract

FieldBound contract
TriggerPinning down domain terminology, maintaining the domain model, or a term conflict/sharpening need
AuthorityReversible local: writes only the named glossary artifacts, CONTEXT.md at the repository root, CONTEXT-MAP.md, and per-context CONTEXT.md files beside their context source; rollback is version control or undo. No remote mutation.
Side effectLazily creates or updates CONTEXT.md / CONTEXT-MAP.md glossaries and per-context CONTEXT.md files; no other file, VCS, credential, or remote change.
DoneEach resolved term recorded in CONTEXT.md with rejected synonyms; glossary stays canonical and implementation-free.

Inputs

Required: the term, conflict, or fuzzy usage to resolve from the current design conversation, plus the human ruling when a conflict needs one. Optional: an existing CONTEXT.md or CONTEXT-MAP.md (absence is normal; files are created lazily) and the implementation source behind a term (when absent or unreadable, skip and report the code cross-check). Scope is limited to terms in the current design work unless the invocation requests a repository-wide glossary sweep.

Procedure

  1. Load the layout. Check the repository root for CONTEXT.md and CONTEXT-MAP.md. CONTEXT.md at the root means one context and one glossary. CONTEXT-MAP.md at the root means several contexts: each context's CONTEXT.md sits beside that context's source, and CONTEXT-MAP.md maps them. Read the applicable glossary before judging any term. If neither exists, create nothing yet. Done when: the layout is determined and the applicable glossary is read (or confirmed absent).
  2. Challenge conflicting terms. Compare each term used in the current design work against the glossary. The moment a use contradicts a glossary entry, state both meanings and ask which one is correct before continuing, for example, a glossary that defines cancellation as ending an Order versus a use that changes one Line Item. Done when: every conflicting term is surfaced with both meanings and the human ruling is requested.
  3. Sharpen fuzzy terms. When a name is vague or overloaded, pick the single domain term that owns the rule; every other name becomes a rejected synonym. Done when: each fuzzy term has one canonical owner and its rejected synonyms are named.
  4. Stress-test relationships. Construct an edge case that exposes a relationship boundary. For example, if one Order is split across two shipments, when may Billing issue the invoice? Resolve which term owns each side of the boundary. Done when: each relationship boundary is resolved with an edge case that exposes it.
  5. Check claims against code. Read the implementation behind each term under resolution. Surface any contradiction between the model and the code, then rule which is authoritative. When the code wins, correct the model term. This skill never edits code. If the implementation is unreadable or absent, skip the cross-check and mark it not performed. Done when: each term's code cross-check is completed or marked not performed with any contradiction surfaced and ruled.
  6. Record each resolution immediately. The moment a term resolves, write an entry to the applicable glossary file with exactly three parts: the canonical term, a one-line definition, and its rejected synonyms. Create CONTEXT.md (one context) or CONTEXT-MAP.md plus the per-context CONTEXT.md (several contexts) only at this first write: never before there is something to record. Done when: each resolved term has a glossary entry with canonical term, one-line definition, and rejected synonyms.
  7. Keep the glossary pure. Entries contain definitions and rejected synonyms only. Refuse implementation details, specification content, and scratch notes in glossary files; put them in their own artifacts or drop them. Done when: every glossary entry contains only definitions and rejected synonyms.

Failure and recovery

  • Unresolvable conflict. Neither the design conversation, the human ruling, nor the code settles which meaning owns the rule: record nothing, leave the glossary unchanged, and report the term as unresolved. Do not pick a winner to force closure.
  • Implementation unavailable. Step 5 cannot run: record the term only if the design conversation resolved it, mark its code cross-check as not performed, and say so in the report. Never claim code agreement that was not observed.
  • Purity pressure. A resolution only makes sense together with implementation detail or specification content: write the glossary entry without that content and route it to its own artifact.
  • Partial results. A session may resolve some terms and not others; only resolved terms are written, and unresolved terms stay out of the files.
  • Rollback. Revert the glossary edit; delete a lazily created file that ended the session with no surviving entry.
  • Blocked result. The terminal failure output names each unresolved or unrecorded term with its reason. Never present Done while a resolved term lacks its entry or its rejected synonyms.

Output

Updated or newly created glossary files in the layout chosen at step 1, with every resolved term appearing once with a one-line definition and its rejected synonyms, plus a terminal report listing terms resolved and recorded, conflicts surfaced, model-versus-code contradictions with the ruling, entries whose code cross-check was not performed, and terms left unresolved with reasons.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Use when explaining System V AMD64, ARM AAPCS, RISC-V psABI, stack frames, variadic calls, or FFI register rules. Not for the Rust FFI binding layer: use rust-ffi.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

Use when configuring ADC sampling time, DMA-driven ADC, calibration, or DAC channel setup on bare-metal MCUs. Not for the DMA stream itself: use dma-baremetal.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

af-xdp

무료

Use when creating AF_XDP sockets, configuring UMEM and XSK rings, writing an XDP redirect program, or choosing copy versus zero-copy mode. Not for full kernel bypass: use dpdk.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

Use when a redacted, trimmed agent transcript must be appended to a GitHub PR or issue body, with human approval and preview. Not for automated or model-initiated insertion.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

agents-md

무료

Use when a repo needs agent setup, AGENTS.md added or made lean, CLAUDE.md audited, or agent instructions scored or pruned. Not for remote, credential, publish, deploy, or irreversible changes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

OutlineDriven의 스킬 모두 보기

이 스킬의 문제 신고