Wiki Query

BM25 full-text search over your pro-workflow wikis, built on SQLite FTS5. Run it before drafting new wiki pages to avoid duplicating coverage, or when the user asks "what does the wiki say about X." Returns ranked passages with citations in a JSON-friendly format. The SessionStart integration is clever: it auto-queries on relevant prompts and injects top hits so Claude recalls existing knowledge instead of researching from scratch. Right now it's pure BM25 with basic snippets. Vector search and MMR diversity are planned for later releases, but the current implementation already solves the main problem of surfacing what you've already documented.

skills.sh installs: 157
GitHub stars: 2.9K
last updated: Jun 8, 2026

View on GitHub

Install

$ npx -y skills add rohitg00/pro-workflow --skill wiki-query --agent claude-code

Installs into .claude/skills of the current project.

Files

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 wiki: "
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.