oracle

Claude-powered Q&A agent that answers questions about an indexed codebase using vector retrieval from ChromaDB. Supports /spec and /gaps commands.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./workspace/skills/oracle/SKILL.md

Oracle

The Oracle is the user-facing intelligence layer. It answers questions about the codebase by retrieving relevant context from ChromaDB and passing it to Claude. It always retrieves before answering — never from memory alone.

Capabilities

Natural language Q&A about the codebase
/spec [filepath] — generate structured specification summaries
/gaps — identify unindexed files, thin coverage, staleness
Always cites file paths and line numbers
search_codebase tool for vector retrieval

Scripts

retriever.py — search_codebase tool implementation
agent.py — Oracle agent loop with command routing
spec.py — SpecGenerator class
gaps.py — GapDetector class

Repository: tombrewsviews/repository-os-mvp
Path: workspace/skills/oracle/SKILL.md
Commit: a30d1b4

Last updated: ~21 hours ago
First committed: 6 months ago

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.