maintainer
Meta-skill that loads all llmwiki governance docs and exposes the three maintainer slash commands.
Sync Claude Code (and Codex CLI) session transcripts into the llmwiki, then ingest the new ones into `wiki/`.
> /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-syncContext preview
What this command does when you run it.
Sync Claude Code (and Codex CLI) session transcripts into the llmwiki, then ingest the new ones into `wiki/`.
Sync Claude Code (and Codex CLI) session transcripts into the llmwiki, then ingest the new ones into `wiki/`.
Usage: /wiki-sync [project-substring]
Steps (run in this order, report progress to the user):
1. **Convert new sessions to markdown** by running:
python3 -m llmwiki sync $ARGUMENTS
Capture the summary line (`N converted, M unchanged, K live, J filtered, X errors`).
2. **If `N == 0`**: report "wiki is already up to date" and continue to step 6 (pending-prompt scan). Don't run ingest.
3. **If `N > 0`**: for each newly written markdown file under `raw/sessions/`, follow the **Ingest Workflow** from `CLAUDE.md`. Process one project at a time. If there are more than 20 new files total, ask the user whether to process them all or a subset first.
4. **Append to `wiki/log.md`**:
## [YYYY-MM-DD] sync | <N> sessions across <M> projects
5. **Report** to the user:
6. **Complete any pending agent-delegate syntheses (#316)** — the `agent` synthesis backend writes pending prompts to `.llmwiki-pending-prompts/<uuid>.md` that need you (the agent) to finalise. Run:
python3 -m llmwiki synthesize --list-pending
**If the output is "No pending prompts"**: skip to step 7.
**Otherwise** — for each pending prompt:
a. Read `.llmwiki-pending-prompts/<uuid>.md` — it contains the rendered prompt (body + frontmatter) that the pipeline already filled in.
b. Synthesize the wiki page body by following the prompt instructions. Emit the `<!-- suggested-tags: ... -->` comment as the first line per the prompt.
c. Write the synthesized body to a scratch file, then finalise:
python3 -m llmwiki synthesize --complete <uuid> --page wiki/sources/<project>/<date>-<slug>.md --body /tmp/synth-<uuid>.md
d. The CLI verifies the uuid matches the page's sentinel, rewrites the placeholder in place, and deletes `.llmwiki-pending-prompts/<uuid>.md`.
Process all pending prompts serially — the agent is single-conversation.
7. **Done.** Run `/wiki-build` if the caller asked for fresh HTML.
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.