geronimo-iia/llm-wiki-skills/frontmatter
Claude Code and agent skill by geronimo-iia/llm-wiki-skills
- community
Checking that the SKILL.md file is still in the repository.
Reference for writing correct wiki frontmatter — required fields, field conventions, type-specific validation, and the accumulation contract.
Install
npx vskill@latest install geronimo-iia/llm-wiki-skills/frontmatterSKILL.md
Frontmatter Reference
Background knowledge for writing correct frontmatter in wiki pages. This skill is loaded automatically when writing wiki pages.
For type system management (listing, adding, removing types), see the schema skill. For the full type taxonomy, see references/type-taxonomy.md.
Quick template
Get the exact frontmatter scaffold for any type:
Required fields
Every wiki page must have:
| Field | Rule | |
|---|---|---|
title | Concise, specific, unambiguous | |
type | Page type from the type registry |
Additional required fields depend on the type:
| Type | Extra required fields | |
|---|---|---|
concept, query-result | read_when | |
skill | name, description (instead of title, summary) |
Field conventions
title
| Type | Convention | Example | |
|---|---|---|---|
concept | The concept name | "Mixture of Experts" | |
paper | "Paper Title (Year)" | "Switch Transformer (2021)" | |
article | "Article Title" | "Why MoE Models Are the Future" | |
documentation | "Product — Topic" | "vLLM — MoE Configuration" | |
transcript | "Event — Topic (Date)" | "Team Standup — MoE Decision (2025-07-15)" | |
note | Descriptive title | "Quick Notes on Routing Strategies" | |
clipping | Original title or descriptive | "Karpathy on LLM Wikis" | |
book-chapter | "Book Title — Chapter" | "Designing ML Systems — Ch. 8" | |
thread | "Forum — Topic" | "HN — MoE Scaling Discussion" | |
data | Descriptive title | "MoE Benchmark Results 2024" | |
query-result | "Topic — Aspect" | "MoE Routing — Design Decision" | |
section | The section name | "Scaling Research" |
Do not include the page type in the title ("Paper: Switch Transformer" ✗).
summary vs tldr
summarydescribes scope ("what is this page about?")tldrstates the conclusion ("what's the bottom line?")
read_when
Write as situations, not keywords:
Not: ["MoE", "scaling", "routing"] — that's what tags is for.
tags
Flat list, lowercase, hyphenated:
aliases
Alternative names and synonyms for this concept — keyword-indexed, so synonym queries in wiki_search hit this field directly:
Use for acronyms, prior names, and common informal variants. Lowercase preferred but not required — BM25 keyword matching is exact on FAST fields.
sources
Slugs of source pages that actually contributed claims:
concepts
Slugs of concept pages this page directly discusses or depends on:
Apply the backlink quality test: would a reader benefit from navigating there?
confidence
A float 0.0–1.0 on both page and claim objects. Same scale everywhere.
| Value | When to use | |
|---|---|---|
0.9 | Multiple corroborating sources, well-established | |
0.5 | Single source, or source has caveats | |
0.2 | Preliminary, speculative, or contradicted |
Default to 0.5 when unsure. Omit on claim objects when no certainty signal was recorded (absence is distinct from 0.5 neutral).
claims
Structured claims extracted from sources:
owner
Who is responsible — a person, team, or agent session ID.
superseded_by
Slug of the page that replaces this one. Use when a page is effectively replaced, not for minor updates. Creates a superseded-by graph edge.
Graph edges from frontmatter fields
Certain frontmatter fields create typed graph edges at ingest:
| Type | Field | Relation | Target types | |
|---|---|---|---|---|
| concept | sources | fed-by | All source types | |
| concept | concepts | depends-on | concept | |
| source types | sources | cites | All source types | |
| source types | concepts | informs | concept | |
| doc | sources | informed-by | All source types | |
| skill | document_refs | documented-by | doc | |
| any | superseded_by | superseded-by | Any |
Body [[wiki-links]] get a generic links-to relation.
Field aliasing
Skill pages use different field names. The engine aliases them at ingest time so they index uniformly:
| Source field | Canonical field | |
|---|---|---|
name | title | |
description | summary | |
when_to_use | read_when |
Aliases affect indexing only — files on disk are never rewritten.
Accumulation contract
When updating a page:
- Read the current page first —
wiki_content_read - Preserve existing list values — do not drop
tags,read_when,
sources, concepts, or claims
- Add new values to lists, do not replace them
- Update scalar fields only with clear reason
- Write the complete file, then
wiki_ingest
Common mistakes
| Mistake | Fix | |
|---|---|---|
Missing title | Engine rejects the file | |
Using source-summary as type | Pick specific source type | |
Missing read_when | Always include 2–5 retrieval conditions | |
| Listing every related source | Only sources that contributed claims | |
| Dropping existing tags on update | Read first, preserve existing values | |
Setting confidence: 0.9 without evidence | Default to 0.5 | |
| Classifying by topic instead of source nature | Blog about research → article |
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/frontmatter/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/geronimo-iia/llm-wiki-skills/frontmatter)