llmwiki-ingest
Ingest one source document (or a folder of them) into the llmwiki. Use when the user drops a new markdown file, PDF, or URL into the wiki and asks you to…
Answer a question by querying the user's llmwiki. Use when the user asks about their own past work — "what did I decide about X", "what have I been working on", "how did I solve Y", "what's my preferred approach to Z", or any question that the wiki (built from their session
$ npx -y skills add Pratiyush/llm-wiki --skill llmwiki-query --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/llmwiki-queryContext preview
The summary Claude sees to decide when to auto-load this skill.
Answer a question by querying the user's llmwiki. Use when the user asks about their own past work — "what did I decide about X", "what have I been working on", "how did I solve Y", "what's my preferred approach to Z", or any question that the wiki (built from their session
name: llmwiki-query description: Answer a question by querying the user's llmwiki. Use when the user asks about their own past work — "what did I decide about X", "what have I been working on", "how did I solve Y", "what's my preferred approach to Z", or any question that the wiki (built from their session history) might answer. Always read the wiki first before falling back to external search.
Reads the user's local llmwiki (`llmwiki/wiki/`) and synthesises an answer to their question, with `[[wikilink]]` citations pointing to the source pages.
Invoke this skill when the user asks a question about their own work or history. Examples:
Do NOT invoke for questions that can be answered without the user's personal knowledge base (e.g., "how does TCP work?" → answer from general knowledge).
Follow the **Query Workflow** from the repo's `CLAUDE.md`:
1. **Locate the llmwiki install** (see `llmwiki-sync` skill for the fallback search order).
2. **Read `wiki/index.md`** to identify the set of pages that might be relevant.
3. **Read `wiki/overview.md`** to get the living synthesis context.
4. **Pick the most relevant pages** (sources, entities, concepts) based on the question.
5. **Read those pages** with the Read tool.
6. **Synthesise an answer** with inline `[[wikilink]]` citations. Quote directly from source pages when the wording matters.
7. **If the answer is substantial** (3+ paragraphs), ask the user whether to save it as a synthesis page:
Would you like me to save this as wiki/syntheses/<slug>.md for future reference?
If yes, write it using the Synthesis Page Format from CLAUDE.md.
8. **Append to `wiki/log.md`**:
## [YYYY-MM-DD] query | <short question>
If the wiki has no relevant pages:
1. Tell the user "I don't see anything about this in your wiki yet." 2. Suggest running `/wiki-sync` to pull in any recent sessions that might cover the topic. 3. If the topic is unlikely to be in session history, offer to answer from general knowledge (and make that explicit: "this is general knowledge, not from your wiki").
LLM-powered knowledge base from your Claude Code, Codex CLI, Cursor, Gemini CLI, and Obsidian sessions. Built on Andrej Karpathy's LLM Wiki pattern.
Repo: Pratiyush/llm-wiki
Ingest one source document (or a folder of them) into the llmwiki. Use when the user drops a new markdown file, PDF, or URL into the wiki and asks you to…
Sync Claude Code session transcripts into the user's llmwiki and ingest them into the wiki. Use when the user says "sync the wiki", "update llmwiki", "ingest…
Maintain an llmwiki-style open-source project across the full framework pipeline. Use when the user says "maintain the project", "check my tasks", "update…
Extract reusable patterns from recent sessions, propose framework improvements, and (with approval) update the framework docs. This is the dogfooding meta-loop…
Run the complete llmwiki pipeline from scratch — init, sync, graph, build, lint, and serve. Use when the user says "run everything", "full pipeline",…