wiki-query · rohitg00 — Claude Code skill: what it does, how to install
wiki-query queries local markdown wikis indexed by wiki-builder using SQLite FTS5 BM25 retrieval. It delivers top passages with citations so the agent builds on existing notes.
MIT ★ 2,966 updated 2026-09-29
/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflowWhat wiki-query does
The skill calls node $SKILL_ROOT/scripts/query.js search across all indexed wikis or within a single slug filter. Output returns snippet texts, page identifiers, and BM25 rank values, where more negative numbers signal closer matches. Snippets default to 16 tokens around the matched term, adjustable through --snippet-len.
The related command uncovers adjacent pages by using an existing file title and summary as search terms. When wired to the pro-workflow SessionStart hook, Claude inspects user prompts on launch and automatically injects up to three matching pages as context.
Matching relies solely on BM25 keyword scoring without vector lookups or MMR reranking. Without an index generated by wiki-builder, the script cannot return any records.
What it helps with
- Search local documentation via SQLite BM25 scoring
- Inspect knowledge coverage before drafting new wiki pages
- Locate related articles using an existing page summary
- Retrieve markdown citations formatted with file paths
Example prompts for the agent
- Search the wiki for episodic memory concepts
- Find related notes for
wiki/concepts/episodic-memory.md - What does the wiki say about park-2023 generative agents?
How to install wiki-query
1Plugin marketplace
/plugin marketplace add rohitg00/pro-workflow/plugin install pro-workflow@pro-workflowThis installs the whole pro-workflow plugin with all its skills
2Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill wiki-query -a claude-code3Manually: put the files in place
~/.claude/skills/wiki-query/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/wiki-query/
1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill wiki-query -a codex2Manually: put the files in place
.agents/skills/wiki-query/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill wiki-query -a cursor2Manually: put the files in place
.cursor/skills/wiki-query/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rohitg00/pro-workflow skills/wiki-query2Manually: put the files in place
.github/skills/wiki-query/SKILL.md1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill wiki-query -a gemini-cli2Platform CLI
gemini skills install https://github.com/rohitg00/pro-workflow --path skills/wiki-queryManually: put the files in place
.devin/skills/wiki-query/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about wiki-query
How do I install wiki-query in Claude Code?
Register the marketplace repository and install the plugin by running /plugin marketplace add rohitg00/pro-workflow followed by /plugin install pro-workflow@pro-workflow. You can also run npx skills add rohitg00/pro-workflow --skill wiki-query -a claude-code.
What does wiki-query do?
It searches pre-indexed documentation using SQLite FTS5 BM25 scoring. Each hit returns formatted source metadata following [wiki:<slug>] <title> — <rel_path>.
What search limitations exist in wiki-query?
Queries rely strictly on BM25 without vector search or reranking passes. The preview snippet covers 16 tokens around hits unless customized with --snippet-len.
Source text
SKILL.md · MIT
---
name: wiki-query
description: Query pro-workflow wikis via SQLite FTS5 BM25 retrieval. Returns top-K passages with citations. Use when answering a question that any of the user's wikis already covers, when the user says "what does the wiki say about X", "ask wiki", "search wikis", or before drafting a new wiki page (to avoid duplication).
---
# Wiki Query
FTS5 BM25 retrieval over wiki pages indexed by `wiki-builder`.
## When to use
- Before writing any new wiki page → check coverage first
- User asks a domain question that may already live in a wiki
- "Ask the <slug> wiki: <question>"
- Verifying citations before quoting a claim
- `SessionStart` auto-load when prompt matches a known wiki topic
## Commands
```
node $SKILL_ROOT/scripts/query.js search "<query>" [--wiki <slug>] [--limit 10] [--json]
node $SKILL_ROOT/scripts/query.js related <slug> <rel-path> [--limit 5]
node $SKILL_ROOT/scripts/query.js show <slug> <rel-path>
```
`search` with no `--wiki` ranks across all wikis. `related` finds adjacent pages by reusing the page's title + summary as the query.
## Output
JSON-friendly. Each hit:
```
{
"page_id": 12,
"wiki_slug": "agent-memory",
"rel_path": "wiki/concepts/episodic-memory.md",
"title": "Episodic Memory",
"snippet": "... [time-stamped] traces, distinct from semantic ...",
"rank": -3.21
}
```
Lower (more negative) rank = better BM25 match.
## Citing back
Every wiki hit must be cited as:
```
[wiki:<slug>] <title> — `<rel_path>`
```
Do not paraphrase a hit without showing the source.
## SessionStart integration
When `pro-workflow`'s SessionStart hook detects wiki-relevant terms in the user prompt, it runs `query.js search "<prompt>" --limit 3` and injects top hits into the session as a hint:
```
[wiki-query] 3 relevant pages:
- agent-memory · wiki/concepts/episodic-memory.md
- agent-memory · wiki/papers/park-2023-generative-agents.md
- ...
```
Helps Claude recall existing knowledge instead of redoing research.
## Limits (Phase 3.3.0)
- BM25 only. Vector search arrives 3.3.2 with sqlite-vec.
- No re-ranking. MMR diversity arrives with the research loop in 3.3.1.
- Snippet window is 16 tokens around match — tune via `--snippet-len`.
© Rohit Ghumare · MIT · rohitg00/pro-workflow
Similar skills
All skills for Agent setup: memory, context, orchestration →wiki-query by other authors comes first.