maintainer
Meta-skill that loads all llmwiki governance docs and exposes the three maintainer slash commands.
Update a single wiki page in place without running a full re-ingest.
> /plugin marketplace add Pratiyush/llm-wiki > /plugin install llmwiki@llmwiki
How it fires
How this command gets triggered: by you, by Claude, or both.
/wiki-updateContext preview
What this command does when you run it.
Update a single wiki page in place without running a full re-ingest.
Update a single wiki page in place without running a full re-ingest.
Usage: /wiki-update <page-path> [reason]
`$ARGUMENTS` is the path to one wiki page — typically under `wiki/sources/`, `wiki/entities/`, or `wiki/concepts/`.
Use this when:
**Do NOT** use this for bulk changes — that's what `/wiki-ingest` and `/wiki-sync` are for.
Steps:
1. **Read the target page** using the Read tool. 2. **Read `wiki/index.md`** to understand how this page is referenced elsewhere. 3. **Read the source(s)** listed in the frontmatter's `sources:` field. 4. **Compute the delta** — what needs to change on the page? Typically one of:
5. **Edit the page** with minimal targeted changes. Use the Edit tool, not Write — this is a surgical update, not a rewrite. 6. **Update `last_updated`** in the frontmatter to today's date. 7. **If you added/removed wikilinks**, check whether backlinks on OTHER pages need updating. Report these to the user; don't update them automatically without permission. 8. **Append to `wiki/log.md`**:
## [YYYY-MM-DD] update | <page-name> — <reason>
Hard rules (per `.kiro/steering/page-format.md`):
After the update, summarize to the user: which page was changed, what the delta was, whether any other pages need follow-up updates, and the log entry you added.
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
Meta-skill that loads all llmwiki governance docs and exposes the three maintainer slash commands.
Run the canonical llmwiki code review against a pull request and post findings.
Apply labels + milestone + priority to a new issue using the llmwiki triage rules.
Run the full llmwiki pipeline end-to-end: build → graph → export all → lint.