daikichiba9511/dotfiles/llm-wiki-query
- community
Checking that the SKILL.md file is still in the repository.
Use when the user asks a question against an existing LLM Wiki, wants a source-backed synthesis from its pages, or wants that answer saved back to the wiki. Do not use for open-web research when no wiki is in scope.
Install
npx vskill@latest install daikichiba9511/dotfiles/llm-wiki-querySKILL.md
LLM Wiki Query
Answer from the accumulated wiki first, cite wiki pages, and optionally save valuable answers as analysis or synthesis pages. Read references/pattern.md for the model. Read references/query-decision-tables.md when search scope or answer format is ambiguous. Read references/analysis-template.md before saving an answer.
Usage
$llm-wiki-query <question> [wiki_dir] [save: optional_title]
Wiki Detection
- Prefer an explicit
wiki_dir. - Otherwise search for
AGENTS.mdfiles that mentionLLM Wiki. - Fallback to legacy
_schema.mdfiles that mentionLLM Wiki. - Ask if multiple wiki directories match.
- If none exists, suggest
$llm-wiki-init.
Workflow
- Read the wiki
AGENTS.mdandindex.md. - Use
index.mdto identify likely relevant pages. - Use
references/query-decision-tables.mdto choose search depth and answer format when the route is not obvious. - Use
Grepover the wiki when the index is insufficient. - Read the smallest set of pages needed to answer, including source pages behind important claims.
- Synthesize an answer with links to the supporting wiki pages.
- Clearly mark information gaps, uncertainty, and contradictions.
- If the answer changes the wiki's top-level understanding, update or propose an update to
overview.mdor a page underpages/syntheses/. - If the query reveals a repeated workflow preference, output format preference, or schema gap, propose an
AGENTS.mdupdate. - If the user asked to save the answer, create an analysis or synthesis page and update
index.md. - Append one
queryorupdateentry tolog.mdwhenever query-driven edits are made, including overview-only, synthesis, analysis, or schema updates. - If saving would be useful but was not requested, propose it instead of silently writing.
Answer Rules
- Ground the answer in wiki pages. Do not pretend the wiki contains facts it does not contain.
- Use outside web search only when the user asks for fresh information or explicitly wants a gap filled. Clearly label outside information as not yet part of the wiki, and offer to ingest the source before treating it as wiki knowledge.
- Distinguish sourced wiki facts from your inference.
- Prefer concise answers unless the user asks for a full memo.
- When pages conflict, present both claims with links and note what evidence would resolve the conflict.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingprivate_dot_agents/exact_skills/llm-wiki-query/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/daikichiba9511/dotfiles/llm-wiki-query)