01 Fts5 Search banner
disler disler

01 Fts5 Search

Development community

Description

Replace Inkwell's naive LIKE post filter with a real SQLite FTS5 full-text index that ranks results by relevance and returns a highlighted snippet of the matching text. Why it matters: a writer with two hundred drafts searches for a half-remembered phrase, not a substring. LIKE '%term%' scans every row, cannot rank, matches inside words, and hands back only a title — so the writer still opens four posts to find the line they meant. Where: apps/inkwell/server.ts (schema, triggers, the GET /api/

Installation

Installs to ~/.claude/skills/disler-inkwell-agent-sandboxes-and-software-factory-01-fts5-search/SKILL.md

Terminal
mkdir -p ~/.claude/skills/disler-inkwell-agent-sandboxes-and-software-factory-01-fts5-search && curl -fsSL https://raw.githubusercontent.com/disler/inkwell-agent-sandboxes-and-software-factory/HEAD/prompts/01-fts5-search.md -o ~/.claude/skills/disler-inkwell-agent-sandboxes-and-software-factory-01-fts5-search/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

Full documentation available on GitHub

View Source Repository