wiki-templates — for Claude Code wiki-templates, llm-wiki, community, for Claude Code, ide skills, ai-tools, claude-code, karpathy, knowledge-base, markdown

v1.0.0

À propos de ce Skill

Scenario recommande : Ideal for AI agents that need wiki page templates. Resume localise : # Wiki Page Templates Standard templates for all wiki page types. It covers ai-tools, claude-code, karpathy workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Fonctionnalités

Wiki Page Templates
Standard templates for all wiki page types. Every page created or updated in a vault MUST follow
Universal Frontmatter (all page types)
Every wiki page has this base frontmatter:
title: "Page Title"

# Sujets clés

RonanCodes RonanCodes
[1]
[1]
Mis à jour: 4/14/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

Scenario recommande : Ideal for AI agents that need wiki page templates. Resume localise : # Wiki Page Templates Standard templates for all wiki page types. It covers ai-tools, claude-code, karpathy workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Pourquoi utiliser cette compétence

Recommandation : wiki-templates helps agents wiki page templates. Wiki Page Templates Standard templates for all wiki page types. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Meilleur pour

Scenario recommande : Ideal for AI agents that need wiki page templates.

Cas d'utilisation exploitables for wiki-templates

Cas d'usage : Applying Wiki Page Templates
Cas d'usage : Applying Standard templates for all wiki page types. Every page created or updated in a vault MUST follow
Cas d'usage : Applying Universal Frontmatter (all page types)

! Sécurité et Limitations

  • Limitation : Standard templates for all wiki page types. Every page created or updated in a vault MUST follow these conventions.
  • Limitation : Every page created or updated in a vault MUST follow these conventions
  • Limitation : Requires repository-specific context from the skill documentation

About The Source

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Démo Labs

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ et étapes d’installation

These questions and steps mirror the structured data on this page for better search understanding.

? Questions fréquentes

Qu’est-ce que wiki-templates ?

Scenario recommande : Ideal for AI agents that need wiki page templates. Resume localise : # Wiki Page Templates Standard templates for all wiki page types. It covers ai-tools, claude-code, karpathy workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Comment installer wiki-templates ?

Exécutez la commande : npx killer-skills add RonanCodes/llm-wiki. Elle fonctionne avec Cursor, Windsurf, VS Code, Claude Code et plus de 19 autres IDE.

Quels sont les cas d’usage de wiki-templates ?

Les principaux cas d’usage incluent : Cas d'usage : Applying Wiki Page Templates, Cas d'usage : Applying Standard templates for all wiki page types. Every page created or updated in a vault MUST follow, Cas d'usage : Applying Universal Frontmatter (all page types).

Quels IDE sont compatibles avec wiki-templates ?

Cette skill est compatible avec Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Utilisez la CLI Killer-Skills pour une installation unifiée.

Y a-t-il des limites pour wiki-templates ?

Limitation : Standard templates for all wiki page types. Every page created or updated in a vault MUST follow these conventions.. Limitation : Every page created or updated in a vault MUST follow these conventions. Limitation : Requires repository-specific context from the skill documentation.

Comment installer ce skill

  1. 1. Ouvrir le terminal

    Ouvrez le terminal ou la ligne de commande dans le dossier du projet.

  2. 2. Lancer la commande d’installation

    Exécutez : npx killer-skills add RonanCodes/llm-wiki. La CLI détectera automatiquement votre IDE ou votre agent et configurera la skill.

  3. 3. Commencer à utiliser le skill

    Le skill est maintenant actif. Votre agent IA peut utiliser wiki-templates immédiatement dans le projet.

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

Upstream Repository Material

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

wiki-templates

# Wiki Page Templates Standard templates for all wiki page types. It covers ai-tools, claude-code, karpathy workflows. This AI agent skill supports Claude

SKILL.md
Readonly
Upstream Repository Material
The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

Wiki Page Templates

Standard templates for all wiki page types. Every page created or updated in a vault MUST follow these conventions.

Universal Frontmatter (all page types)

Every wiki page has this base frontmatter:

yaml
1--- 2title: "Page Title" 3date-created: YYYY-MM-DD 4date-modified: YYYY-MM-DD 5page-type: source-note | entity | concept | comparison | summary 6domain: 7 - vault-default-domain 8tags: 9 - relevant-tag 10sources: 11 - raw/filename.md 12 - https://original-url.com 13related: 14 - "[[related-page-name]]" 15---

Rules:

  • domain always includes the vault's default domain tag. Add more if content spans domains.
  • sources lists paths to raw/ files AND/OR original URLs. Never empty — every page traces to a source.
  • related lists wikilinks to related pages in the wiki.
  • date-modified updates whenever the page content changes.

Page Type: source-note

A summary of one ingested source. One source-note per source.

Location: wiki/sources/<source-name>.md

Additional frontmatter:

yaml
1source-url: https://original-url.com 2source-type: article | paper | video | tweet | gist | discussion | pdf | book | podcast | presentation 3author: "Author Name" 4date-accessed: YYYY-MM-DD 5raw-file: raw/filename.md

Structure:

markdown
1# <Source Title> 2 3## Overview 4Brief summary of what this source contains and why it matters. 5 6## Key Takeaways 7- Takeaway 1 8- Takeaway 2 9- Takeaway 3 10 11## Detailed Notes 12Deeper notes organized by topic. Link to [[entity]] and [[concept]] pages when mentioning them. 13 14## Quotes 15> Notable direct quotes with context. 16 17## Sources 18- **Raw file:** [filename.md](../raw/filename.md) 19- **Original URL:** [source-title](https://original-url.com) 20- **Author:** Author Name 21- **Accessed:** YYYY-MM-DD

Example: source-note

yaml
1--- 2title: "LLM Wiki — Karpathy's Idea File" 3date-created: 2026-04-12 4date-modified: 2026-04-12 5page-type: source-note 6domain: 7 - ai-research 8 - knowledge-management 9tags: 10 - llm 11 - knowledge-base 12 - obsidian 13sources: 14 - raw/karpathy-llm-wiki-gist.md 15 - https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f 16related: 17 - "[[andrej-karpathy]]" 18 - "[[llm-knowledge-bases]]" 19 - "[[obsidian-workflows]]" 20source-url: https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f 21source-type: gist 22author: "Andrej Karpathy" 23date-accessed: 2026-04-12 24raw-file: raw/karpathy-llm-wiki-gist.md 25--- 26 27# LLM Wiki — Karpathy's Idea File 28 29## Overview 30A pattern for building personal knowledge bases using LLMs. Instead of RAG, the LLM incrementally builds and maintains a persistent wiki of interlinked markdown files. 31 32## Key Takeaways 33- The wiki is a persistent, compounding artifact — not re-derived each query 34- Three layers: raw sources, the wiki, the schema (CLAUDE.md) 35- Four operations: ingest, query, lint, promote 36- [[andrej-karpathy]] uses [[obsidian-workflows]] as the viewer 37 38## Sources 39- **Raw file:** [karpathy-llm-wiki-gist.md](../raw/karpathy-llm-wiki-gist.md) 40- **Original URL:** [GitHub Gist](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) 41- **Author:** Andrej Karpathy 42- **Accessed:** 2026-04-12

Page Type: entity

A page about a person, organization, tool, framework, or other named entity.

Location: wiki/entities/<entity-name>.md

Additional frontmatter:

yaml
1entity-type: person | organization | tool | framework | service | dataset | publication 2aliases: 3 - "Alternative Name" 4 - "Abbreviation"

Structure:

markdown
1# <Entity Name> 2 3## Overview 4What/who this entity is and why it's relevant. 5 6## Key Facts 7- Fact 1 8- Fact 2 9 10## Relevance 11How this entity connects to the vault's domain. What role does it play in the knowledge base? 12 13## Mentions 14Pages where this entity appears: 15- [[source-note-1]] — context of mention 16- [[concept-page]] — how it relates 17 18## Sources 19- [[source-that-introduced-entity]] 20- [External link](https://url)

Example: entity

yaml
1--- 2title: "Andrej Karpathy" 3date-created: 2026-04-12 4date-modified: 2026-04-12 5page-type: entity 6domain: 7 - ai-research 8tags: 9 - ai 10 - deep-learning 11 - tesla 12 - openai 13sources: 14 - raw/karpathy-llm-wiki-gist.md 15 - raw/karpathy-viral-tweet.md 16related: 17 - "[[llm-knowledge-bases]]" 18 - "[[obsidian-workflows]]" 19entity-type: person 20aliases: 21 - "Karpathy" 22--- 23 24# Andrej Karpathy 25 26## Overview 27AI researcher. Previously Director of AI at Tesla, founding team at OpenAI, PhD from Stanford. Creator of the [[llm-knowledge-bases]] pattern. 28 29## Key Facts 30- Created the LLM Wiki "idea file" pattern (April 2026) 31- Original tweet got 55K likes, 6.5K retweets 32- Uses [[obsidian-workflows]] as his wiki viewer 33 34## Sources 35- [[karpathy-llm-wiki-gist]] — the original idea file 36- [[karpathy-viral-tweet]] — the tweet that started it all

Page Type: concept

A page about an idea, pattern, technique, or abstract concept.

Location: wiki/concepts/<concept-name>.md

Structure:

markdown
1# <Concept Name> 2 3## Definition 4Clear, concise definition of the concept. 5 6## How It Works 7Explanation of the concept, mechanics, or methodology. 8 9## Examples 10Concrete examples of the concept in practice. 11 12## Related Concepts 13- [[related-concept-1]] — how it relates 14- [[related-concept-2]] — how it differs 15 16## Sources 17- [[source-note]] — where this concept was discussed 18- [External link](https://url)

Example: concept

yaml
1--- 2title: "LLM Knowledge Bases" 3date-created: 2026-04-12 4date-modified: 2026-04-12 5page-type: concept 6domain: 7 - ai-research 8 - knowledge-management 9tags: 10 - llm 11 - wiki 12 - knowledge-base 13 - rag-alternative 14sources: 15 - raw/karpathy-llm-wiki-gist.md 16related: 17 - "[[andrej-karpathy]]" 18 - "[[rag-vs-wiki]]" 19 - "[[obsidian-workflows]]" 20--- 21 22# LLM Knowledge Bases 23 24## Definition 25A pattern where LLMs incrementally build and maintain a persistent wiki of interlinked markdown files, rather than re-deriving knowledge from raw documents on every query (as in RAG). 26 27## How It Works 281. **Ingest**: Source documents are processed into wiki pages 292. **Query**: Questions answered by reading the wiki, not raw docs 303. **Lint**: Periodic health checks for contradictions and gaps 314. **Promote**: Cross-project knowledge transferred between wikis 32 33## Related Concepts 34- [[rag-vs-wiki]] — comparison of RAG vs persistent wiki approaches 35- [[obsidian-workflows]] — the viewer/IDE for browsing wikis 36 37## Sources 38- [[karpathy-llm-wiki-gist]] — original pattern description

Page Type: comparison

A synthesis page comparing two or more concepts, tools, or approaches.

Location: wiki/comparisons/<comparison-name>.md

Structure:

markdown
1# <Thing A> vs <Thing B> 2 3## Summary 4One-paragraph synthesis of the comparison. 5 6## Comparison Table 7| Aspect | Thing A | Thing B | 8|--------|---------|---------| 9| ... | ... | ... | 10 11## Analysis 12Deeper analysis of tradeoffs, use cases, and recommendations. 13 14## Verdict 15When to use each, and which is recommended for what context. 16 17## Sources 18- [[source-1]] — evidence for Thing A 19- [[source-2]] — evidence for Thing B

Example: comparison

yaml
1--- 2title: "RAG vs Persistent Wiki" 3date-created: 2026-04-12 4date-modified: 2026-04-12 5page-type: comparison 6domain: 7 - ai-research 8 - knowledge-management 9tags: 10 - rag 11 - wiki 12 - architecture 13sources: 14 - raw/karpathy-llm-wiki-gist.md 15related: 16 - "[[llm-knowledge-bases]]" 17 - "[[andrej-karpathy]]" 18--- 19 20# RAG vs Persistent Wiki 21 22## Summary 23RAG re-derives knowledge each query from raw chunks. A persistent wiki compiles knowledge once and keeps it current. The wiki compounds; RAG doesn't. 24 25## Comparison Table 26| Aspect | RAG | Persistent Wiki | 27|--------|-----|-----------------| 28| Knowledge accumulation | None — re-derived each time | Compounds with every source | 29| Cross-references | Must be found each query | Already maintained | 30| Contradictions | Not flagged | Flagged during lint | 31| Maintenance cost | Low (just index) | Near-zero (LLM maintains) | 32| Setup complexity | Higher (embeddings, vector DB) | Lower (just markdown) | 33 34## Sources 35- [[karpathy-llm-wiki-gist]] — original argument for wiki over RAG

Page Type: summary

A high-level overview page that synthesizes across multiple sources and pages.

Location: wiki/<summary-name>.md (top level of wiki/)

Structure:

markdown
1# <Topic> — Summary 2 3## Overview 4High-level synthesis of the topic. 5 6## Key Themes 7- Theme 1 — brief description 8- Theme 2 — brief description 9 10## Open Questions 11- Question that needs more research 12- Unresolved contradiction between sources 13 14## Sources 15- [[source-1]] 16- [[source-2]]

Cross-Referencing Rules

  1. Always link entities and concepts when first mentioned on a page: [[entity-name]]
  2. Use the canonical page name as the link text. If an entity has aliases, link to the main page: [[andrej-karpathy|Karpathy]]
  3. Update the related frontmatter when adding links between pages
  4. Don't over-link — link on first mention per page, not every occurrence

Compétences associées

Looking for an alternative to wiki-templates or another community skill for your workflow? Explore these related open-source skills.

Voir tout

openclaw-release-maintainer

Logo of openclaw
openclaw

Resume localise : 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

widget-generator

Logo of f
f

Resume localise : Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and

flags

Logo of vercel
vercel

Resume localise : The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

138.4k
0
Navigateur

pr-review

Logo of pytorch
pytorch

Resume localise : Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

98.6k
0
Développeur