route-by-query-shape

When the agent calls memory_search with a relationship-shaped query ("who did I talk to about X"), redirect to the knowledge_graph backend where it will…

Skill by Bitterbot-AI

IndexedMIT★ 2,478

Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/bitterbot-ai-route-by-query-shape

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

When the agent calls memory_search with a relationship-shaped query ("who did I talk to about X"), redirect to the knowledge_graph backend where it will actually find the answer.

Use cases: backend, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/route-by-query-shape

What's inside

Skill name: route-by-query-shape
Description: When the agent calls memory_search with a relationship-shaped query ("who did I talk to about X"), redirect to the knowledge_graph backend where it will actually find the answer.
License: MIT
Instructions: 15 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

# route-by-query-shape

When you ask Bitterbot a relationship question — "who did I talk to about Q4?", "who worked with me on Foo?" — the vector-based `memory_search` often misses because the answer lives in entity relationships, not in chunk text. The graph backend gets these right.

This interceptor watches `memory_search` calls, detects relationship-shaped queries, extracts the salient entity, and re-routes the call to the graph backend before it executes.

## What you'll see

For relationship questions, the agent will hit the knowledge graph rather than searching through unstructured text. Expect noticeably better hit rates on "who did X with Y" style questions.

## Implementation

Built-in interceptor `route-by-query-shape:relationship` lives in `src/agents/skills/builtin-interceptors/route-by-query-shape.ts`. Fires up to 12 times per session.

From Bitterbot-AI/bitterbot-desktop, MIT.

Signals

Stars: 2,478
Forks: 422
Open issues: 5
Last commit (this folder): May 23, 2026 (5 months ago)
Last release: Oct 22, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/Bitterbot-AI/bitterbot-desktop
Website: bitterbot.ai
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from Bitterbot-AI

Cite this page

route-by-query-shape skill. Agent Mart. https://agentmart.dev/skills/bitterbot-ai-route-by-query-shape (last updated 2026-10-24)