Slash commands reference

Every /wiki-* (plus governance commands) in .claude/commands/, what it does, what it runs under the hood, and a realistic invocation example. Use these inside Claude Code — Codex CLI picks the same files up via install-skills.

Summary of 18 commands in 4 groups:

Group	Commands
Wiki pipeline (14)	`/wiki-init` `/wiki-sync` `/wiki-ingest` `/wiki-query` `/wiki-update` `/wiki-lint` `/wiki-candidates` `/wiki-synthesize` `/wiki-graph` `/wiki-reflect` `/wiki-build` `/wiki-serve` `/wiki-export-marp` `/wiki-all`
Governance / maintainer (4)	`/maintainer` `/release` `/review-pr` `/triage-issue`

Decision tree: which tool runs when?

CLI vs slash

You want to…	Use
…run a check in CI, a cron job, or a shell script	CLI (`python3 -m llmwiki …`)
…chain commands with `&&` / pipe to `jq`	CLI
…have the model read output + take follow-up actions	slash (inside Claude Code / Codex)
…answer a free-form question ("what did I decide about X?")	slash (`/wiki-query`)
…do one-shot builds, serves, graph generation	either — slashes wrap the CLI

Rule of thumb: if the output is for you to read + act on manually, use the CLI. If the output should feed back into an LLM turn, use the slash — the model sees the full stdout and can chain into the next step.

Eval vs lint

Two different QA surfaces that are easy to confuse:

Command	Checks	Severity model	When to run
`llmwiki lint` / `/wiki-lint`	Wiki content quality — frontmatter completeness, `[[wikilink]]` integrity, orphans, duplicate titles, stale pages, cache-tier consistency, tag-topic convention, stale references	15 rules with `error` / `warning` / `info` severities; `--fail-on-errors` exits non-zero only on errors	After every `/wiki-sync` or `/wiki-build`
`llmwiki eval`	Structural corpus health — site-wide metrics (total pages, orphan ratio, avg outbound links, broken-link rate, duplicate-slug rate, content-length distribution)	Pass / fail against configurable thresholds	In CI, weekly, or when comparing two wiki snapshots

In plain English: lint checks each page against its contract; eval checks the whole wiki against health thresholds. A page passing lint doesn't mean the corpus passes eval, and vice versa.

Reach for lint first when something looks wrong with a specific page. Reach for eval when you want to compare two builds (is the wiki trending healthier? getting more orphans?).

Wiki pipeline

`/wiki-init`

What: scaffolds an empty llmwiki — creates raw/, wiki/, site/ and seeds wiki/index.md, wiki/log.md, wiki/overview.md, plus the nine navigation files (CRITICAL_FACTS.md, MEMORY.md, SOUL.md, hints.md, hot.md, dashboard.md).

Wraps: python3 -m llmwiki init.

When to use: first time in a fresh repo, or after deleting wiki/ to start over.

Example:

/wiki-init

Claude Code will respond by running init and surfacing which files were seeded.

`/wiki-sync`

What: convert new Claude Code (+ Codex + Cursor + etc.) .jsonl sessions into markdown under raw/sessions/, then ingest into wiki/.

Wraps: python3 -m llmwiki sync.

Arguments Claude may pass through: --dry-run, --since, --project, --force, --vault. Say any of them in natural language — "sync but only sessions from this week" becomes --since $(date -v-7d +%Y-%m-%d).

When to use: at the end of each coding block. Also the only command that triggers auto-ingest of new pages into wiki/.

Example:

/wiki-sync
/wiki-sync only my llm-wiki project
/wiki-sync but don't auto-build afterwards
/wiki-sync into my Obsidian vault at ~/Documents/Obsidian Vault

Expected output (narrated):

==> claude_code: 3 new sessions since last sync
✓ wrote 3 pages under raw/sessions/
✓ ingested into wiki/sources/
✓ auto-build: site/ rebuilt (690 HTML files)

`/wiki-ingest <path>`

What: ingest one source document or folder into wiki/. Reads the file, creates / updates the matching wiki/sources/<slug>.md, extracts entities into wiki/entities/, creates candidates in wiki/candidates/ for anything it hasn't seen before.

Wraps: the Ingest Workflow in CLAUDE.md (no single CLI — it's a slash-command-driven workflow that the model orchestrates).

When to use: you dropped a source file manually (a PDF, a Jira ticket export, a meeting transcript) and want it in the wiki.

Examples:

/wiki-ingest raw/sources/2026-04-17-incident.md
/wiki-ingest raw/jira/
/wiki-ingest ~/Downloads/meeting-transcript.vtt

`/wiki-query <question>`

What: answer a question from the wiki. Reads wiki/index.md + wiki/overview.md + any cache_tier: L1 pages, then walks relevant source / entity / concept pages and synthesises an answer with inline [[wikilinks]] back to the originals.

Wraps: the Query Workflow in CLAUDE.md.

When to use: "have I solved this before?" / "when did I add X?" / "which sessions touched Y?".

Examples:

/wiki-query when did I add the lint rules?
/wiki-query which agent did I use for refactoring the cache-tier module?
/wiki-query summarize every session about Obsidian integration

Save prompt: if the answer runs 3+ paragraphs, Claude will offer to save it under wiki/syntheses/<slug>.md.

`/wiki-update <page>`

What: surgically edit one wiki page without re-ingesting. Useful for fixing broken wikilinks, updating stale frontmatter, adding a missing ## Connections line.

When to use: lint flagged something, you know the fix, you don't want to re-run sync.

Example:

/wiki-update wiki/entities/RAG.md add a Connections section linking to Karpathy and llm-wiki

`/wiki-lint`

What: run every registered lint rule (15 at last count: 8 structural + 3 LLM-powered + stale_candidates (#51) + cache_tier_consistency (#52) + tags_topics_convention (#302) + stale_reference_detection (#303)). The live number is printed by llmwiki lint --help.

Wraps: python3 -m llmwiki lint.

Rules, in order:

frontmatter_completeness
frontmatter_validity
link_integrity
orphan_detection
content_freshness
entity_consistency
duplicate_detection
index_sync
contradiction_detection (LLM)
claim_verification (LLM)
summary_accuracy (LLM)
stale_candidates
cache_tier_consistency
tags_topics_convention (G-16 · #302)
stale_reference_detection (G-17 · #303)

Example:

/wiki-lint
/wiki-lint include LLM-powered rules
/wiki-lint just the link_integrity rule

`/wiki-synthesize`

What: call the configured LLM backend on every new raw/sessions/*.md to produce wiki/sources/<slug>.md.

Wraps: python3 -m llmwiki synthesize (respects the synthesis.backend key in sessions_config.json — dummy / ollama and, in-progress on #315, claude-api).

Natural-language flags Claude translates:

You say	Runs
"just show me what it would cost"	`synthesize --estimate`
"preview without writing"	`synthesize --dry-run`
"check the backend is reachable"	`synthesize --check`
"re-synthesize everything"	`synthesize --force`

Example:

/wiki-synthesize
/wiki-synthesize with a cost estimate
/wiki-synthesize force a re-run of every source

`/wiki-candidates`

What: triage pending candidates — promote, merge, or discard.

Wraps: python3 -m llmwiki candidates list + follow-ups.

When to use: /wiki-lint reported a stale_candidates info line, or /wiki-sync produced new wiki/candidates/*.md files.

Example:

/wiki-candidates

Claude will walk the queue one at a time and offer actions per candidate.

`/wiki-graph`

What: build the knowledge graph. Nodes = wiki pages, edges = [[wikilinks]]. Emits graph/graph.json + graph/graph.html.

Wraps: python3 -m llmwiki graph.

Example:

/wiki-graph

Then open site/graph.html (auto-copied from graph/graph.html during build) or the compiled URL in the served site.

`/wiki-reflect`

What: higher-order self-reflection pass over the whole wiki. Looks for gaps, patterns, duplicated-topic clusters, areas where a synthesis page would help.

No CLI wrapper — it's a model-orchestrated workflow that reads the index + overview + sample of pages and outputs suggestions.

Example:

/wiki-reflect

Use sparingly; it's the most token-heavy command.

`/wiki-build`

What: regenerate the static HTML site.

Wraps: python3 -m llmwiki build.

When to use: after manual edits to wiki/, or when you want to see a fresh site without running the full sync pipeline.

Example:

/wiki-build
/wiki-build to ~/public_html
/wiki-build in tree search mode

`/wiki-serve`

What: start a local HTTP server for the built site.

Wraps: python3 -m llmwiki serve.

Example:

/wiki-serve
/wiki-serve on port 9000

The server is local-only (127.0.0.1) by default. Say "on my LAN" and Claude will pass --host 0.0.0.0.

`/wiki-export-marp`

What: generate a Marp slide deck from wiki pages matching a topic.

Wraps: python3 -m llmwiki export-marp --topic ….

Example:

/wiki-export-marp topic "cache tiers"
/wiki-export-marp topic Karpathy save to ~/slides/karpathy.marp.md

`/wiki-all`

What: run the full pipeline end-to-end — build → graph → export all → lint.

Wraps: python3 -m llmwiki all.

When to use: after /wiki-sync, when you want a CI-ready site in one shot instead of chaining /wiki-build + /wiki-graph + /wiki-lint yourself.

Example:

/wiki-all
/wiki-all --graph-engine builtin
/wiki-all --skip-graph --strict

Pass --strict to turn any lint warning into a non-zero exit, which is exactly what CI wants. Pass --skip-graph or --graph-engine builtin when the optional Graphify backend is not installed.

Governance / maintainer

`/maintainer`

Meta-skill that loads all llmwiki governance docs (CONTRIBUTING.md, CODE_OF_CONDUCT.md, docs/maintainers/*) and exposes the three maintainer slash commands below.

Use before doing anything governance-related.

`/release`

Walk through the llmwiki release process step by step — tag, changelog cut, GitHub Release note, PyPI publish (via OIDC), Homebrew tap bump, Docker image push.

`/review-pr`

Run the canonical llmwiki code review against a pull request and post findings.

Example:

/review-pr 265

Reads the PR via gh pr view + gh pr diff, applies the review checklist from docs/maintainers/, posts inline comments.

`/triage-issue`

Apply labels + milestone + priority to a new GitHub issue using the llmwiki triage rules.

Example:

/triage-issue 280

How the slash commands get installed

The repo ships .claude/commands/*.md — Claude Code picks them up automatically when it opens the repo (no separate install step).

For Codex CLI / Cursor / Gemini CLI / other agents, copy the .claude/commands/wiki-*.md files into the corresponding skill directory for that agent (typically .codex/skills/ or .agents/skills/) — the file format is portable across agents.

Extending

To add a new slash command:

Create .claude/commands/wiki-<name>.md with a one-line docstring on line 1 (that's the summary Claude Code surfaces).
Describe the workflow in prose. Reference existing CLI commands rather than embedding shell in the body.
Run /wiki-lint — the docs/reference/ guardrail test (see tests/test_docs_structure.py) will pick up the new command.
Document it here; the CI guard requires every .claude/commands/*.md to have a matching entry.

CLI reference — the underlying python3 -m llmwiki … surface.
UI reference — every screen on the compiled site, with what's reachable from where.
Tutorial 03 — Use with Claude Code — the minimum daily loop built on these commands.

Slash commands reference

Decision tree: which tool runs when?

CLI vs slash

Eval vs lint

Wiki pipeline

/wiki-init

/wiki-sync

/wiki-ingest <path>

/wiki-query <question>

/wiki-update <page>

/wiki-lint

/wiki-synthesize

/wiki-candidates

/wiki-graph

/wiki-reflect

/wiki-build

/wiki-serve

/wiki-export-marp

/wiki-all

Governance / maintainer

/maintainer

/release

/review-pr

/triage-issue

How the slash commands get installed

Extending

Related

`/wiki-init`

`/wiki-sync`

`/wiki-ingest <path>`

`/wiki-query <question>`

`/wiki-update <page>`

`/wiki-lint`

`/wiki-synthesize`

`/wiki-candidates`

`/wiki-graph`

`/wiki-reflect`

`/wiki-build`

`/wiki-serve`

`/wiki-export-marp`

`/wiki-all`

`/maintainer`

`/release`

`/review-pr`

`/triage-issue`