living-doc-k
This skill should be used when the user asks about "living documents", "living doc", "update MOC", "MOC maintenance", "how do MOCs work", "keep docs updated", "project brief", or needs to understand or apply the living document pattern.
What this skill does
> **Knowledge skill** — Living document patterns: MOCs, project briefs, what makes docs "living", update signals.
# Living Documents
Living docs evolve as understanding shifts. They synthesize — not just list. Two types exist in the vault: **MOCs** and **Project Briefs**.
## Types of Living Documents
### MOC (Map of Content)
**Purpose**: Synthesize an area's knowledge into navigable structure.
**Not an index.** A MOC tells you what you know about a topic and how it fits together.
```markdown
---
type: moc
level: 0
created: YYYY-MM-DD
---
# Area Name
{Thesis paragraph: current understanding. Updated when understanding shifts.}
## Section Name
- [[note-name]] — what it covers, why it matters
- [[other-note]] — key insight from this note
## Another Section
- [[yet-another]] — brief annotation
## Open Questions
- What you don't know yet
- Gaps in understanding
---
Sources cross-linked from: [[00_related-area]], [[00_another-area]]
```
**What makes it living:**
- Thesis paragraph evolves as understanding deepens
- Sections reorganize as the area's structure becomes clearer
- Annotations get refined (not "see this" but "key insight: X")
- Open Questions get resolved, new ones added
- Cross-links grow as connections are discovered
**L0 vs L1:**
- `00_area-name.md` (L0) — one per area, always exists, synthesizes broadly
- `01_subtopic.md` (L1) — only when 15+ notes cluster. L0 references L1; L1 goes deep.
- Never L2. If L1 needs splitting, scope is wrong.
### Project Brief
**Purpose**: Track a project's state, resources, decisions, and next actions.
```markdown
---
type: project
status: active
created: YYYY-MM-DD
goal: "One-sentence objective"
deadline: YYYY-MM-DD
---
# Project Name
{Current status paragraph: what's done, what's in progress, what's blocked.}
## Resources
- [[00_area-moc]] — area knowledge feeding this project
- [[resource-note]] — specific reference material
## Backlog
- [ ] Concrete task
- [ ] Another task
## Decisions
- Decision made and why
- Another decision with rationale
```
**What makes it living:**
- Status paragraph reflects current reality, not aspirational state
- Backlog is actual next steps, maintained as items complete
- Resources grow as relevant notes and references are discovered
- Decisions capture rationale so future-you understands past choices
## Signals a Living Doc Needs Updating
- New notes filed in the area/project that aren't linked yet
- An Open Question now has an answer in a recent note
- Thesis paragraph no longer reflects what the notes actually say
- Project status paragraph is stale (work happened but brief wasn't updated)
- Sections don't match actual note clustering (structural drift)
- Cross-links missing to areas that have grown relevant
## When to Create vs Update
| Situation | Action |
|-----------|--------|
| Filing a new note | Update parent MOC — add link with annotation |
| Understanding shifted | Update MOC thesis paragraph |
| New notes cluster on subtopic (15+) | Create L1 sub-MOC |
| Starting a new project | Create project brief |
| Project milestone hit | Update project brief status + decisions |
| Area has no MOC | Create L0 MOC |
## Anti-Patterns
- Flat bullet list of links with no annotations → not synthesized
- Thesis unchanged in months → probably stale
- No Open Questions → either perfect understanding (unlikely) or not used for thinking
- Project brief with aspirational backlog → not reflecting reality
- Sections that don't match note clustering → structural drift
## Updating a Living Doc
When invoked with an area name or file path:
### 1. Read the Target
Read the MOC or project brief.
### 2. Scan the Area/Project
List all notes. Read frontmatter and first few paragraphs of each.
### 3. Identify Gaps
- **Unlinked notes**: Notes not referenced in the living doc
- **Outdated sections**: Don't reflect current notes
- **Stale Open Questions**: Now answered by existing notes
- **Missing cross-links**: Related area MOCs that should be referenced
- **Annotation gaps**: Links with vague or missing annotations
### 4. Propose Updates
Present specific edits:
```
## Proposed Updates to 00_ai-dev-ecosystem.md
1. ADD to "Agent Architecture" section:
- [[2025-02-05_agent-note]] — multi-agent orchestration patterns
2. UPDATE thesis paragraph:
Add sentence about multi-agent patterns emerging as dominant architecture
3. RESOLVE Open Question:
"How does memory continuity work?" → answered in [[2025-02-01_memory-patterns]]
```
### 5. Execute on Confirmation
Apply edits. Only modify the living doc — never the notes themselves.
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.