From rock-star-skills
Initialize the LLM Wiki. Creates directory structure, index, log, sets up qmd collection, and runs initial ingest of all existing content from raw/, docs/, and notes/. Run once per project.
npx claudepluginhub marvec/rock-star-skills --plugin rock-star-skillsThis skill is limited to using the following tools:
Set up a new LLM Wiki in the current project and run the first full ingest.
Ingest new sources into the LLM Wiki. Reads unprocessed files from raw/, docs/, and notes/, creates source summaries, updates entity/concept pages, maintains cross-references, and updates the index and log. Use when new files have been added.
Bootstraps a structured LLM-maintained personal wiki at a user-specified path for knowledge domains like research, codebases, notes, or analysis, with schema, flat pages, and citation rules.
Share bugs, ideas, or general feedback.
Set up a new LLM Wiki in the current project and run the first full ingest.
wiki/index.md already exists. If it does and has content beyond the template, ask the user whether to reinitialize (destructive) or skip.raw/, docs/, and notes/ directories exist. Create any that are missing.raw/attachments/ exists. Create if missing.Ensure the following directories and files exist:
wiki/
├── index.md # Master index of all wiki pages
├── log.md # Chronological log of operations
├── entities/ # Pages about specific things (people, companies, products, tools)
├── concepts/ # Conceptual/topic pages
├── sources/ # Source summaries (one per ingested source)
├── comparisons/ # Comparison tables, side-by-side analyses
└── synthesis/ # Cross-cutting analyses, insights
If files already exist, leave them as-is.
Run:
qmd collection add wiki ./wiki
This registers the wiki/ directory as a qmd collection named "wiki". If the collection already exists, skip.
Then update the index:
qmd update
If qmd is not installed, warn the user: npm install -g @tobilu/qmd and continue without it.
Collect ALL existing files that should be ingested:
raw/ — all markdown files and other documents (skip raw/attachments/)docs/ — all markdown files recursivelynotes/ — all markdown files recursivelyFor each file found, invoke the llmwiki:ingest skill's logic (or invoke the skill itself). Process files in batches using parallel subagents where possible:
wiki/sources/wiki/entities/ and wiki/concepts/[[wikilinks]] between related pagesAfter all subagents complete:
wiki/index.md with all pageswiki/log.md:
## [YYYY-MM-DD] init | Initialized wiki with N sources, M pages created
If qmd is available, run:
qmd embed
This builds vector embeddings for semantic search. If it fails or takes too long, skip — BM25 search still works.
Print a summary:
All wiki pages MUST follow these conventions:
Every wiki page has YAML frontmatter:
---
title: Page Title
type: entity | concept | source | comparison | synthesis
tags: [tag1, tag2]
sources: [relative/path/to/source.md]
created: YYYY-MM-DD
updated: YYYY-MM-DD
---
Use [[Page Title]] syntax for cross-references. Obsidian resolves these automatically. When creating a new page, add wikilinks to all related existing pages, and update those existing pages to link back.
Source summary filenames: kebab-case version of the source title, in wiki/sources/. Example: wiki/sources/cross-platform-tech-stacks-2026.md.
Use descriptive kebab-case filenames. Example: wiki/entities/expo.md, wiki/concepts/local-first-architecture.md.
.md extension