Intent Documentation Layer
Qi layer

Use when writing or maintaining AGENTS.md, .context/CONTEXT.md, or CLAUDE.md mirrors: keep intent docs minimal and load-bearing.
--- name: qi-layer description: 'Use when writing or maintaining AGENTS.md, .context/CONTEXT.md, or CLAUDE.md mirrors: keep intent docs minimal and load-bearing.' --- # qi-layer `/qi-maintenance` owns when colocated knowledge must move with source changes. This skill owns how to write and structure that knowledge. Load `/knowledge-layers` for where each layer lives and what it holds. Load `/llm-writing` if it isn't already loaded. This skill is about **how to write and maintain** the directory-local pair: AGENTS.md and `.context/CONTEXT.md`. The pair governs any tree agents work in — code, the KB, docs, work directories. AGENTS.md loads into an agent's bounded context as standing instructions: write it like a prompt, minimal, every line load-bearing.
Overview
/qi-maintenance owns when colocated knowledge must move with source changes. This skill owns how to write and structure that knowledge.
Manual install (npx, ZIP)
npx skills add haowjy/creative-writing-skills --skill qi-layer -g -a claude-codenpx degit haowjy/creative-writing-skills/cw/skills/qi-layer#main ~/.claude/skills/qi-layerConnects with Agent Alley MCP · agentalley.io/mcp
Files included
SKILL.md5.3 KB
Read SKILL.md here
Show the full text118 lines
qi-layer
/qi-maintenance owns when colocated knowledge must move with source changes.
This skill owns how to write and structure that knowledge.
Load /knowledge-layers for where each layer lives and what it holds.
Load /llm-writing if it isn't already loaded.
This skill is about how to write and maintain the directory-local pair:
AGENTS.md and .context/CONTEXT.md. The pair governs any tree agents work
in — code, the KB, docs, work directories. AGENTS.md loads into an agent's
bounded context as standing instructions: write it like a prompt, minimal,
every line load-bearing.
The Four Principles
- Fractal Compression: leaf AGENTS.md summarizes its directory's content; parent AGENTS.md summarizes its children. Each level is a compression of the level below.
- Hierarchical Summarization: root provides broad architectural frame. Leaves provide local working knowledge. Agents accumulate understanding as they descend.
- LCA Deduplication: shared knowledge appears once at the shallowest node covering all relevant paths. Never duplicate between siblings.
- Progressive Disclosure: give just enough to work correctly at this
level. Link to
.context/CONTEXT.mdfor depth.
Writing AGENTS.md
Agents read AGENTS.md before opening anything else in the tree — write for that moment. Ask: what must someone understand before working here? That's what AGENTS.md captures.
Keep AGENTS.md as short as the directory allows, rarely past 200 lines. Include only what has substance:
- Purpose: what this area IS and what it ISN'T (1–3 sentences)
- Mental model: how to think about this area, key abstractions
- Key rules: constraints, what breaks if you get it wrong
- Anti-patterns: what NOT to do here
- Downlinks: to
.context/for depth, to related areas
An agent that only reads AGENTS.md should be able to work correctly here. An agent that also reads .context/ should be able to change things safely.
Writing .context/CONTEXT.md
Reference depth, co-located with the code it describes. Where an agent goes when it needs contracts, architecture, or rationale in detail.
Sections (use only those with substance):
- Contracts: interfaces, invariants, what breaks if violated
- Architecture: component relationships, data flow, dependency direction
- Rationale: why X over Y, rejected alternatives
- Patterns: how to work here, concrete pitfalls
The .context/ directory is extensible: additional files alongside
CONTEXT.md for specialized concerns.
What Does NOT Belong in AGENTS.md
Apply the every-session test: root AGENTS.md loads on every session. If knowledge is only relevant when working in a specific domain, it belongs in that domain's AGENTS.md or .context/, not root.
Apply the think-vs-lookup test: text whose removal would cause a wrong decision belongs in AGENTS.md. Text an agent would merely have to look up belongs in .context/. Text that changes no behavior gets deleted — agents already know how to code and follow common conventions.
Specific failure modes:
- Session bleed: LLM working notes that calcified into the instruction file. Tells: status-update language ("deleted", "shipped", "deferred"), implementation terms packed without framing, history narration.
- Reference material posing as intent: tables, command blocks, full scheme vocabularies, implementation specifics.
- Redundant guards: prose warnings for invariants already enforced by tests or types. The code is the real guard; prose rots faster.
- Duplicated knowledge: restating what lives in a skill, a domain .context/, or a KB page. Point, don't duplicate.
- Domain-specific detail at root: URI scheme tables, gateway pricing internals, auth implementation details. These belong in their domain's AGENTS.md, not root.
Structural Rules
- Relative paths for all links
- AGENTS.md and .context/ at the same directory level (siblings)
- Link to files, not headings (headings change more often)
- Lateral links between
.context/directories with contracts between them - LCA deduplication: if two siblings share context, put it in the parent
CLAUDE.md Mirrors
Claude harnesses read CLAUDE.md, not AGENTS.md. Give every AGENTS.md a
sibling CLAUDE.md whose first line is @AGENTS.md — normally the whole
file. Run meridian qi claude-md-fix <target-root> on the containing tree
after creating or moving AGENTS.md files: it creates missing mirrors, skips
exact ones, and reports anything else as a conflict.
Never write shared instructions into CLAUDE.md. Claude-only knowledge is
rare; when it exists, put it below the @AGENTS.md import and expect
claude-md-fix to keep flagging the file, so the divergence stays visible.
Loading differs by level. At the root, each harness auto-loads its own file every session: Claude reads CLAUDE.md, others read AGENTS.md. In subdirectories, Claude auto-injects CLAUDE.md when it touches files there; other agents see nested AGENTS.md only by reading it on entry. Don't lean on Claude's auto-injection: a nested AGENTS.md carries the local additions an agent needs on entry, with everything else inherited from ancestors.
| 1 | |
| 2 | name qi-layer |
| 3 | description 'Use when writing or maintaining AGENTS.md, .context/CONTEXT.md, or CLAUDE.md mirrors: keep intent docs minimal and load-bearing.' |
| 4 | |
| 5 | |
| 6 | # qi-layer |
| 7 | |
| 8 | `/qi-maintenance` owns when colocated knowledge must move with source changes. |
| 9 | This skill owns how to write and structure that knowledge. |
| 10 | |
| 11 | Load `/knowledge-layers` for where each layer lives and what it holds. |
| 12 | Load `/llm-writing` if it isn't already loaded. |
| 13 | |
| 14 | This skill is about **how to write and maintain** the directory-local pair: |
| 15 | AGENTS.md and `.context/CONTEXT.md`. The pair governs any tree agents work |
| 16 | in — code, the KB, docs, work directories. AGENTS.md loads into an agent's |
| 17 | bounded context as standing instructions: write it like a prompt, minimal, |
| 18 | every line load-bearing. |
| 19 | |
| 20 | ## The Four Principles |
| 21 | |
| 22 | **Fractal Compression**: leaf AGENTS.md summarizes its directory's |
| 23 | content; parent AGENTS.md summarizes its children. Each level is a |
| 24 | compression of the level below. |
| 25 | **Hierarchical Summarization**: root provides broad architectural |
| 26 | frame. Leaves provide local working knowledge. Agents accumulate |
| 27 | understanding as they descend. |
| 28 | **LCA Deduplication**: shared knowledge appears once at the shallowest |
| 29 | node covering all relevant paths. Never duplicate between siblings. |
| 30 | **Progressive Disclosure**: give just enough to work correctly at this |
| 31 | level. Link to `.context/CONTEXT.md` for depth. |
| 32 | |
| 33 | ## Writing AGENTS.md |
| 34 | |
| 35 | Agents read AGENTS.md before opening anything else in the tree — write for |
| 36 | that moment. Ask: **what must someone understand before working here?** |
| 37 | That's what AGENTS.md captures. |
| 38 | |
| 39 | Keep AGENTS.md as short as the directory allows, rarely past 200 lines. |
| 40 | Include only what has substance: |
| 41 | |
| 42 | **Purpose**: what this area IS and what it ISN'T (1–3 sentences) |
| 43 | **Mental model**: how to think about this area, key abstractions |
| 44 | **Key rules**: constraints, what breaks if you get it wrong |
| 45 | **Anti-patterns**: what NOT to do here |
| 46 | **Downlinks**: to `.context/` for depth, to related areas |
| 47 | |
| 48 | An agent that only reads AGENTS.md should be able to work correctly here. |
| 49 | An agent that also reads .context/ should be able to change things safely. |
| 50 | |
| 51 | ## Writing .context/CONTEXT.md |
| 52 | |
| 53 | Reference depth, co-located with the code it describes. Where an agent |
| 54 | goes when it needs contracts, architecture, or rationale in detail. |
| 55 | |
| 56 | Sections (use only those with substance): |
| 57 | |
| 58 | **Contracts**: interfaces, invariants, what breaks if violated |
| 59 | **Architecture**: component relationships, data flow, dependency direction |
| 60 | **Rationale**: why X over Y, rejected alternatives |
| 61 | **Patterns**: how to work here, concrete pitfalls |
| 62 | |
| 63 | The `.context/` directory is extensible: additional files alongside |
| 64 | CONTEXT.md for specialized concerns. |
| 65 | |
| 66 | ## What Does NOT Belong in AGENTS.md |
| 67 | |
| 68 | Apply the **every-session test**: root AGENTS.md loads on every session. |
| 69 | If knowledge is only relevant when working in a specific domain, it belongs |
| 70 | in that domain's AGENTS.md or .context/, not root. |
| 71 | |
| 72 | Apply the **think-vs-lookup test**: text whose removal would cause a |
| 73 | *wrong decision* belongs in AGENTS.md. Text an agent would merely have to |
| 74 | *look up* belongs in .context/. Text that changes no behavior gets |
| 75 | deleted — agents already know how to code and follow common conventions. |
| 76 | |
| 77 | Specific failure modes: |
| 78 | |
| 79 | **Session bleed**: LLM working notes that calcified into the instruction |
| 80 | file. Tells: status-update language ("**deleted**", "shipped", "deferred"), |
| 81 | implementation terms packed without framing, history narration. |
| 82 | **Reference material posing as intent**: tables, command blocks, full |
| 83 | scheme vocabularies, implementation specifics. |
| 84 | **Redundant guards**: prose warnings for invariants already enforced by |
| 85 | tests or types. The code is the real guard; prose rots faster. |
| 86 | **Duplicated knowledge**: restating what lives in a skill, a domain |
| 87 | .context/, or a KB page. Point, don't duplicate. |
| 88 | **Domain-specific detail at root**: URI scheme tables, gateway pricing |
| 89 | internals, auth implementation details. These belong in their domain's |
| 90 | AGENTS.md, not root. |
| 91 | |
| 92 | ## Structural Rules |
| 93 | |
| 94 | Relative paths for all links |
| 95 | AGENTS.md and .context/ at the same directory level (siblings) |
| 96 | Link to files, not headings (headings change more often) |
| 97 | Lateral links between `.context/` directories with contracts between them |
| 98 | LCA deduplication: if two siblings share context, put it in the parent |
| 99 | |
| 100 | ## CLAUDE.md Mirrors |
| 101 | |
| 102 | Claude harnesses read CLAUDE.md, not AGENTS.md. Give every AGENTS.md a |
| 103 | sibling CLAUDE.md whose first line is `@AGENTS.md` — normally the whole |
| 104 | file. Run `meridian qi claude-md-fix <target-root>` on the containing tree |
| 105 | after creating or moving AGENTS.md files: it creates missing mirrors, skips |
| 106 | exact ones, and reports anything else as a conflict. |
| 107 | |
| 108 | Never write shared instructions into CLAUDE.md. Claude-only knowledge is |
| 109 | rare; when it exists, put it below the `@AGENTS.md` import and expect |
| 110 | `claude-md-fix` to keep flagging the file, so the divergence stays visible. |
| 111 | |
| 112 | Loading differs by level. At the root, each harness auto-loads its own |
| 113 | file every session: Claude reads CLAUDE.md, others read AGENTS.md. In |
| 114 | subdirectories, Claude auto-injects CLAUDE.md when it touches files there; |
| 115 | other agents see nested AGENTS.md only by reading it on entry. Don't lean |
| 116 | on Claude's auto-injection: a nested AGENTS.md carries the local additions |
| 117 | an agent needs on entry, with everything else inherited from ancestors. |
| 118 |
Details
- License
- Apache-2.0
- Stars on the repo
- ★ 506
- Checked
- Source
- haowjy/creative-writing-skills ↗
- Creator
- haowjy · 22 listings
Similar skills
See all →
Browser Testing Suite
Everything MCP
Web Content Fetcher
Filesystem Operations
Library Reference Tool
Chrome DevTools DebuggerMore from haowjy
Character Voice Simulator
Story Research Assistant
Fiction Writing Craft Guide
Writing Mode Guide
Multi-Mode Writing Studio
Output Information Hierarchy