torben/chemenu
1
1 Fork 0
Code Issues 40 Pull Requests Actions Packages Releases 41 Wiki Activity
Page: How to Query the wiki
Pages
Dev Development Explanation Architecture Explanation Configuration tiers Explanation Knowledge and commitment Explanation Language boundaries Explanation Model and effort selection Explanation Ownership and templates Explanation Pipeline rationale Explanation Telemetry and evaluation Explanation Version model Explanation Why gates are code Explanation Home How to Back up to a synced folder How to Browse with obsidian How to Capture repository docs How to Collect from a synced folder How to Export guidelines How to Export to a synced folder How to Fetch pages behind a login How to Ingest a source How to Maintain the wiki How to Query the wiki How to Run the weekly review How to Set up the mcp server How to Trace and score sessions How to Troubleshoot How to Update an instance How to Use 1password for settings How to Write a site handler How to Install Reference Commands Catalog and log Reference Commands Configuration Reference Commands Content migrations Reference Commands Distribution and versioning Reference Commands Exports Reference Commands Finding and checking Reference Commands Git Reference Commands Instance health Reference Commands Links and citations Reference Commands Pages Reference Commands Provenance Reference Commands Raw material and uploads Reference Commands Telemetry Reference Commands Types instructions and docs Reference Commands Workshop runs and session budget Reference Commands Reference Configuration Reference Exit codes Reference Page types Reference Skills Reference Tutorials First source to first answer Tutorials Sample source Tutorials
Clone
3
How to Query the wiki
Wiki Mirror edited this page 2026-10-16 14:43:37 +00:00
Unescape Escape
Table of Contents
This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

Generated from docs/how-to/query-the-wiki.md at v10.1.0 – edit the repository, not this wiki.

Query the wiki

Ask the wiki a question and get an answer built from its compiled pages, with the pages and sources it came from. The agent answers using the wiki-query skill (skill catalogue), which only reads unless you ask it to keep an answer.

What you say

Ask the way you would ask a colleague:

What projects use MQTT?
Show me the architecture of HA Integration
Compare gdeploy and plugnburn-edl
What decisions were made about E3DC integration?

What you get back

An answer that names the wiki pages it came from and the sources behind them. Where the wiki has no source for a claim, the agent says so instead of filling the gap. An answer it cannot back is never written into the wiki either.

If an answer is worth keeping - a comparison you will want again, a synthesis across several pages - the agent proposes filing it back as a page. It names the pages it would create before it creates any, and nothing is written unless you agree.

Asking for the exact wording

Some questions are about the text itself - what a rule says word for word, which value stands in a table of a manual:

What exactly does rule 16:3e say?
Which torque does table 4 of the assembly manual give?

The agent still starts from a page. For the wording it follows that page to its source page, then to the outline in the header of the source's derived text, and reads only the passage's lines - it never searches raw/. The quote comes in the language of the original, with the source page and the page number. Markings the derivation added (bold, italic, highlighting) are left out of the quote, and struck-through text is said to be struck rather than quoted as if it were in force.

Two answers point at work for later. If the derived text has no outline and is too long to read whole, the agent says the wording cannot be reached directly and names the way to change that: a new raw derive of the original, accepted with raw accept --replaces. If the answer stands in the source but on no page, the agent answers with the quote and names the page that is missing it, offering to complete it - it writes nothing on its own.

Searching yourself

The agent searches with the same command you can run:

tools/wikitool search "<text>"
tools/wikitool search --field entity_type=system
tools/wikitool search --field '!sources'          # pages without a sources: list

search covers all of kb/, by text, by frontmatter or both. Each hit carries the page's path and full title, so you can open it directly. It only reads, and it does not count against the session's call budget, because looking before acting is the habit worth encouraging. The predicate forms are in the command reference.

For browsing rather than searching, kb/index.md is the catalog map, and each collection carries its own INDEX.md. All of these are generated. Read them, but never edit them. To browse the pages as a graph, see Browse the wiki in Obsidian.

Asking from another machine

A consumer that is not a terminal on this machine can ask the same questions through the MCP read server and get the same answers: Set up the MCP read server. The one difference is the exact wording above: the read server serves pages only, never raw/, so a reader over MCP gets the wording only where a page carries it.