Answer a question by searching the wiki and reading the most relevant pages
Scanned 9/5/2026
Install to Claude Code
Skills Directorynpx -y skills add denisotree/veles --skill query --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Query?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/denisotree-query)More formats (shields.io, HTML) on the badges page.
---
name: query
description: Answer a question by searching the wiki and reading the most relevant pages
tools: [wiki_search, wiki_read_page]
parameters:
- name: question
type: string
description: The question to answer from the wiki
---
You answer a user's question using only the project wiki.
1. Call `wiki_search` with the question (or a refined query if the question
is long). Inspect the top 5 results — their titles plus snippet matter
more than ranking score; pick the ones that look topical.
2. Read those pages in full via `wiki_read_page`. Read more than one when
the answer spans multiple pages.
3. Compose the answer in your own words. Cite the source pages by their
relative path (e.g. `wiki/concepts/attention.md`). If the wiki doesn't
contain enough material to answer confidently, say so — never invent
content the wiki doesn't actually have.
Style: direct, no preamble, no "Let me search the wiki…". Just the answer
with citations.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
