knowledge-layers
Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
Skill by FiredMosquito831
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/firedmosquito831-knowledge-layers
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
knowledge-layers- Description
- Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
- License
- Apache-2.0
- Instructions
- 105 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- bootstrap.md · resources/
SKILL.md (first lines)
# Knowledge Layers 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. ## The Five Layers | 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/` | Contracts, architecture, rationale (`CONTEXT.md`); deferred work (`TODO`, `FUTURE`) | Reference depth and tracked deferrals, co-located with the code they describe | | 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 | ## Placement Rules If it's intent/mental-model for a directory → `AGENTS.md`. If it's directory-scoped depth an agent looks up → `.context/`. If it's deferred work scoped to this directory → `.context/TODO` (must-do) or `.context/FUTURE` (nice-to-have). Flat markdown lists — each entry names the affected path and concrete follow-up. Cross-cutting items or items needing external visibility get filed in the project's issue tracker instead. If it's big picture — cross-cutting decisions, domain concepts, higher-level system architecture → KB. If it's for end users → `docs/`. If it's a temporary work artifact → work directory. When in doubt, colocate. Knowledge that depends on one subsystem belongs in that subsystem's AGENTS.md or .context/ even when it reads like a concept; the KB stays code-agnostic, holding what survives implementation change. Knowledge that lives far from what it describes rots faster: changes to the code don't trigger awareness that a distant doc needs updating. ## Current Truth Over History Every durable layer — AGENTS.md, `.context/`, KB, `docs/` — holds the best current understanding; work directories may keep intermediate reasoning while their work item is active. When durable 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. Deletion is the content-truth owner's call; structural roles flag instead. **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. **Truth is anchored per layer.** AGENTS.md and `.context/` describe the checkout that contains them: update them in the same branch as the code change and let the merge carry both — with parallel PRs in flight, each branch documents itself. The KB is code-agnostic: it records the current settled intent — what the system *should be* — and a settled decision is KB truth the moment it's made, merged or not. Unsettled intent isn't KB material; it stays in the work directory. `docs/` describes shipped behavior. 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. ## KB Conventions ### Structure The KB is a directory tree like any other: it carries its own AGENTS.md and `.context/` pair, written per `/qi-layer` — intent in AGENTS.md, governance depth (writing conventions, structure, validation) in `.context/`. Read the KB's own `AGENTS.md` before writing. 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. ### Wiki Page Conventions 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. ## Operations **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**`.
From FiredMosquito831/my-writing-companion, Apache-2.0.
More from FiredMosquito831/my-writing-companion
- 0.557score
demolition
FiredMosquito831
Load when the author invokes demolition on a chapter draft, or when muse offers it before marking a chapter final.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
qi-layer
FiredMosquito831
Use when writing or maintaining AGENTS.md, .context/CONTEXT.md, or CLAUDE.md mirrors: keep intent docs minimal and load-bearing.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
cold-read
FiredMosquito831
Load for /vellum:cold-read, after every major editorial program, and before export.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
gates
FiredMosquito831
Load when muse accepts a pivotal chapter, before export, or for any scoring task.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
kb-integrity
FiredMosquito831
Load when a vellum check failed, or when muse routes integrity work.
SkillBFreshness: B★ 2Claude Code +9 - 0.553score
export
FiredMosquito831
Load for /vellum:export.
SkillBFreshness: B★ 2Claude Code +9 - 0.550score
project-setup
FiredMosquito831
One-time project setup for creative writing.
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 9, 2026 (1 month ago)
- Last release
- Sep 11, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Website
- vellum.danubelabs.net
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from FiredMosquito831
- 0.560score
config
FiredMosquito831
Configure prompt-cache warming (keep-alive pings for idle Claude Code sessions) per scope - global, CLI, desktop app, project folder or single session -…
SkillAFreshness: AClaude Code +9 - 0.557score
cold-read
FiredMosquito831
Load for /vellum:cold-read, after every major editorial program, and before export.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
gates
FiredMosquito831
Load when muse accepts a pivotal chapter, before export, or for any scoring task.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
demolition
FiredMosquito831
Load when the author invokes demolition on a chapter draft, or when muse offers it before marking a chapter final.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
qi-layer
FiredMosquito831
Use when writing or maintaining AGENTS.md, .context/CONTEXT.md, or CLAUDE.md mirrors: keep intent docs minimal and load-bearing.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
kb-integrity
FiredMosquito831
Load when a vellum check failed, or when muse routes integrity work.
SkillBFreshness: B★ 2Claude Code +9
Cite this page
knowledge-layers skill. Agent Mart. https://agentmart.dev/skills/firedmosquito831-knowledge-layers (last updated 2026-10-24)