/init
Initialize a new LLM Wiki structure in this project (creates wiki/ and raw/ directories with templates).
$ npx -y skills add praneybehl/llm-wiki-plugin --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/init
Context preview
What this command does when you run it.
Initialize a new LLM Wiki structure in this project (creates wiki/ and raw/ directories with templates).
Command definition
init.mddescription: Initialize a new LLM Wiki structure in this project (creates wiki/ and raw/ directories with templates).
argument-hint: "[--wiki-dir <name>] [--raw-dir <name>]"
Initialize a new LLM Wiki in the current project. Use the `llm-wiki` skill to:
1. Open `skills/llm-wiki/references/retrieval-setup.md` and ask its setup questions in one grouped interaction: wiki/raw paths, model-cache location, graph usage, and agent-memory integration. 2. Explain that initialization installs and verifies the complete local runtime through `uv`: pinned FastEmbed, sqlite-vec, PyYAML, the `BAAI/bge-small-en-v1.5` model, the parse cache, and vectors for every existing section. No API key, provider consent, per-query fee, or outbound wiki/query text is involved. 3. After I answer, resolve the current project's absolute root, then run `python "${CLAUDE_PLUGIN_ROOT}/skills/llm-wiki/scripts/init_wiki.py" "<absolute-project-root>"` with my selected paths. The script path and project-root argument must remain separate; never run it against the plugin directory. Do not report setup complete unless its runtime JSON says `"status": "ready"`. 4. Walk me through the bootstrapped `SCHEMA.md` and ask whether I want to customize page types, tags, or workflow conventions. 5. Propose the approved agent-memory integration using `references/agent-memory-integration.md`. Show the exact addition and ask whether to append, create, or skip. Never write without approval. 6. Do not ingest a source yet. This command only completes an informed setup.
Arguments (if any): $ARGUMENTS
Read more
description: Initialize a new LLM Wiki structure in this project (creates wiki/ and raw/ directories with templates). argument-hint: "[--wiki-dir <name>] [--raw-dir <name>]"
Initialize a new LLM Wiki in the current project. Use the `llm-wiki` skill to:
1. Open `skills/llm-wiki/references/retrieval-setup.md` and ask its setup questions in one grouped interaction: wiki/raw paths, model-cache location, graph usage, and agent-memory integration. 2. Explain that initialization installs and verifies the complete local runtime through `uv`: pinned FastEmbed, sqlite-vec, PyYAML, the `BAAI/bge-small-en-v1.5` model, the parse cache, and vectors for every existing section. No API key, provider consent, per-query fee, or outbound wiki/query text is involved. 3. After I answer, resolve the current project's absolute root, then run `python "${CLAUDE_PLUGIN_ROOT}/skills/llm-wiki/scripts/init_wiki.py" "<absolute-project-root>"` with my selected paths. The script path and project-root argument must remain separate; never run it against the plugin directory. Do not report setup complete unless its runtime JSON says `"status": "ready"`. 4. Walk me through the bootstrapped `SCHEMA.md` and ask whether I want to customize page types, tags, or workflow conventions. 5. Propose the approved agent-memory integration using `references/agent-memory-integration.md`. Show the exact addition and ask whether to append, create, or skip. Never write without approval. 6. Do not ingest a source yet. This command only completes an informed setup.
Arguments (if any): $ARGUMENTS
Turn PDFs, articles, transcripts, and notes into a shared wiki that your AI agents can search, cite, and keep up to date. Add a source once. Ask questions later. Keep the useful answers.
Other commands on praneybehl-llm-wiki.
- /graph
Compile, lint, or query the wiki's typed graph layer.
Open command - /ingest
Ingest a source (paper, article, transcript, PDF, notes) into the LLM Wiki.
Open command - /lint
Run a structural and semantic health check on the LLM Wiki.
Open command - /query
Query the LLM Wiki — answer a question from accumulated knowledge with citations.
Open command - /stats
Show wiki size, shape, and link density — and which scaling threshold the wiki is at.
Open command - /upgrade
Upgrade an existing LLM Wiki to the current plugin version (adds missing files idempotently; walks me through any SCHEMA.md merges by hand).
Open command