CalibratedDecisions.

Repo · Coding & code review

skillmine

Mines coding-agent sessions (Claude Code, Codex CLI, Kimi CLI, OpenCode, Antigravity) for reusable knowledge: local embeddings cluster near-duplicate…

Open github.com ↗

From the repository

Mine your coding-agent sessions (Claude Code, Codex, Kimi, OpenCode, Antigravity) into skills, runbooks and agents. LLM decides, you undo.

How builders describe it

Mines coding-agent sessions (Claude Code, Codex CLI, Kimi CLI, OpenCode, Antigravity) for reusable knowledge: local embeddings cluster near-duplicate windows, TypeSafe Jev (or Laya / Haiku) gates whether a cluster taught something reusable, and a planner model writes skills or runbooks with…

The decision Jev makes

Label a change, score its risk, pick the relevant file, or decide whether a coding agent should continue.

Where it fits

Code review and coding agents are full of small questions: is this change risky, what kind of fix is this, which file matters. These projects answer them with Jev and route the rest to people or bigger models. All 450 coding & code review projects →

Related projects