원클릭으로
knowledge-layers
Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when grilling should be grounded primarily in project artifacts. Loads `/grill`, checks project vocabulary and prior decisions first, and spawns bounded explorers when the answer should come from docs.
Load for large human-facing outputs: reports, docs, multi-section explanations, artifacts. Choose the right form for each beat (prose, diagram, table, mockup) and put the answer first, depth behind it. If the medium allows, use progressive disclosure.
Anchor work in a work item: artifacts on disk, not in context.
Investigate and engage concurrently: don't block on evidence before surfacing your read.
Use when exploring or changing the codebase: read AGENTS.md first, use .context/CONTEXT.md for detail, keep intent docs succinct.
Use when recovering decisions or context from conversation history: session log navigation, transcript delegation.
| name | knowledge-layers |
| type | reference |
| description | Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories. |
| model-invocable | true |
Load /qi-layer when writing or editing AGENTS.md or .context/ files: it
owns the craft (four principles, contents guidelines, what doesn't belong).
Load /information-hierarchy if not already loaded for disclosure tiers.
Load /llm-writing if not already loaded.
| Layer | What it holds | When to use it |
|---|---|---|
AGENTS.md | Intent and mental model for a directory | First thing agents read on entry; what to understand before working here |
.context/CONTEXT.md | Contracts, architecture, rationale | Reference depth, co-located with the code it describes |
| KB | Cross-cutting decisions, domain concepts, patterns | Spans directories; outlives sessions; no single directory owns it |
docs/ | User-facing documentation | Different audience, different update cadence |
| Work directory | Temporary design decisions and scratch | Not colocated with durable content; scoped to an active work item |
If knowledge is scoped to one directory → .context/.
If it's intent/mental-model for a directory → AGENTS.md.
If it spans directories or isn't anchored to code → KB.
If it's for end users → docs/.
If it's a temporary work artifact → work directory.
When in doubt, colocate. Knowledge that lives far from what it describes rots faster: changes to the code don't trigger awareness that a distant doc needs updating.
Every layer holds the best current understanding. When content is
superseded, delete it or (for KB pages) move it to archive/
(.kgignore'd, excluded from the knowledge graph). Live content never
references archived content. Pages read as current truth, never narrate
their own evolution.
Deletion needs no replacement. A page whose subject is gone, or that describes behavior the system no longer has, gets deleted on sight — even with nothing new to write in its place. Stale knowledge is worse than a gap: agents load it and reason from it.
Git history is the archive. Commit untracked files before deleting them so the removal lands in history, and say what was removed and why in the commit message. Deletion is cheap because nothing tracked is ever truly lost.
Decision records are the exception: preserve superseded decisions in place when they explain why the system changed. Mark the old decision as superseded and link to the replacement.
Read the KB's own AGENTS.md before writing. Each KB defines its local
structure, naming, validation commands, and governance. Treat this skill as the
cross-project default; the local KB guide wins for that KB. See
resources/bootstrap.md for a suggested starting layout.
Follow /information-hierarchy. One concept per document; name files by
what they describe (token-validation.md), not when (auth-redesign-notes.md).
Cross-reference instead of re-explaining. Load /shared-dao for vocabulary
methodology. Use mermaid for anything spatial; capture what code can't
easily tell you.
Ingest: new information enters the KB. Read the source, extract key knowledge, write or update wiki pages, and update indexes/cross-links touched by the change.
Maintain: keep the wiki current per Current Truth Over History above.
Lint: health-check the wiki. Look for contradictions, stale claims,
orphan pages, missing cross-references. Use /md-validation for link
checking and diagram validation.
Flag content needing human attention with > [!FLAG] **Needs human review**.