skills/doc-standards/SKILL.md
Documentation standards for the LLM Wiki project. Reference skill loaded when creating or updating markdown docs. Ensures consistent structure, mermaid diagrams, and formatting.
npx skillsauth add RonanCodes/ronan-skills doc-standardsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Reference skill for creating and updating docs in the llm-wiki project. Claude should follow these conventions when writing any .md file in docs/.
Every doc should have:
# Clear Title## sectionsEvery doc that describes a flow, process, or architecture MUST include at least one mermaid diagram.
| Content | Diagram type | Example |
|---------|-------------|---------|
| Process flow (step by step) | graph TD (top-down) | Ingest pipeline, Ralph loop |
| Data flow (A sends to B) | graph LR (left-right) | Sources → Engine → Vault → Obsidian |
| Architecture layers | graph TB (top-bottom) | Three-layer pattern |
| Timeline / phases | graph LR with subgraphs | Roadmap phases |
| Comparisons | Tables (not mermaid) | RAG vs Wiki |
| Decision trees | graph TD with diamonds | Vault-create interview |
Amber (#e0af40) — user actions, sources, starting points
Cyan (#5bbcd6) — Claude/engine actions, skills, commands
Green (#7dcea0) — outputs, results, Obsidian, success states
Rose (#d4726a) — warnings, errors, required items
Grey (#94a3b8) — future/planned items
Apply with: style NodeName fill:#e0af40,color:#000
subgraph to group related nodes-.-> for optional/conditional flows, --> for required flowsbash), configs (yaml, json)[doc name](other-doc.md)dataview-queries.md — code examples are the contentdependencies.md — tables are sufficientdecisions.md — prose reasoning is the contentkarpathy-research.md — reference/quote compilationtesting
--- name: linear-pipeline description: The Fable orchestrator for a single dispatched Linear ticket. Holds almost no context itself; it receives `--issue <ID> --detached`, decides the stage sequence, and fans out a sub-agent per stage, passing forward only each stage's artifact (never re-derived, never inlined into its own context). Step zero, before any planning or stage routing, is a boundary triage against `canon/security-boundary.md` (#199): a match tags Ronan Connolly and stops the run, no
development
--- name: in-your-face description: Capture a chat-only answer into a durable artifact (markdown + HTML, PDF when cheap) and launch it automatically so the user cannot miss it. Use when user says "in your face", "don't let me lose this", "save that answer", "make that durable", or right after answering a substantive side question (a recipe, comparison, how-to, or generated prompt) that would otherwise die with the context. category: workflow argument-hint: [--no-open] [--vault <short>] [hint of
tools
One-shot headless OpenAI Codex CLI calls for background/admin AI tasks — summaries, classification, extraction, admin glue. The default engine for anything that runs AI constantly in the background (daemon-driven, per-event), because it bills the flat ChatGPT subscription instead of Claude usage or per-token API spend, and it keeps working while Claude is rate-limited. NEVER for coding — coding stays Claude. Use when a skill or daemon needs a cheap always-on AI call, when the user says "use codex", "ask codex", "codex as backup", or when building a background summarizer/classifier into a listener or loop. Reads auth from ~/.codex/auth.json (ChatGPT account, no API key).
research
Turn a warranty rejection, repair quote, or RMA email into a cited decision brief — legal read (NL/EU consumer law), is the part user-serviceable, live part and new-unit prices, repair-vs-DIY-vs-new economics, before-you-send-it checklist, deadlines. Use when the user pastes or screenshots a repair quote, warranty rejection, "not covered" email, onderzoekskosten fee, or asks "should I repair or replace this".