kb-query
Skill1 starsChanged 39 days agoMITView on GitHub
Answers questions from the <SUBJECT> knowledge base, a wiki on <one-line scope>, with a cited synthesis. Use for how-do-I, what-is, what-does-<source>-say, compare-X-vs-Y, and 'what does the KB have on X' questions in that domain. Not for adding material (kb-intake) or auditing (kb-lint).
6 other projects use a version of this.
Adopted by
Most recently taken up by
- Iabstergo1/pdf-to-study-kbtheir own version, first seen Nov 7, 2026
- walkwithedi/drive-wikitheir own version, first seen Nov 1, 2026
- walkwithedi/evergreen-wikitheir own version, first seen Oct 11, 2026
- davidmatousek/tachitheir own version, first seen Oct 10, 2026
- viniciusbedum/vb-ai-contexttheir own version, first seen Sep 25, 2026
- tjkuhns/explodabletheir own version, first seen Apr 19, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- davidmatousek/tachi★ 95same name
- Iabstergo1/pdf-to-study-kb★ 2same name
- viniciusbedum/vb-ai-context★ 2same name
- walkwithedi/evergreen-wiki★ 2same name
- tjkuhns/explodable★ 1same name
- walkwithedi/drive-wiki★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- kb-ingestSkill
- kb-intakeSkill
- kb-lintSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Find: Search wiki/index.md with rg, read the relevant pages, and follow their links where the question crosses concepts.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
kb-query
Answers from the wiki as a synthesis, not a retrieval.
- Find. Search
wiki/index.mdwithrg, read the relevant pages, and follow their links where the question crosses concepts. For detail beyond a page, read the source's local clip (clip:on its stub) rather than the network. - Register. The page is already the better reference, so the answer adds value by interpretation: synthesise, don't reformat a page. Pick one framing as the spine and use the others in support. Prose by default; bullets only for genuinely enumerated content, tables only for real comparisons. Length is functional: the smallest answer that covers the question.
- Attribute in prose by author or name ("
<Author>argues…"), then list the pages once at the end:**Sources:** [[<source-slug>]] (<author>), [[<page-slug>]] (wiki synthesis).Inline[[slug]]only where the prose names a concept worth linking. - Recap. A substantive answer ends with an
**In short:**block of 3–6 one-line bullets, before the Sources line, stated once; short answers skip it. - Honesty. Answer from the KB, and label anything from your own knowledge as such. When the KB lacks the answer or covers it partly, say what is missing and where it might be found (the upstream URLs of related stubs).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

