Repositories

Deep codebase review framework with staged human-directed prompts, structured review artifacts, and CLI support for incremental maintenance reviews.

Run a command with secrets fetched just-in-time, injected leak-tight, and gone on exit — plus a safe, scoped direnv. Rust.

One search, two windows: re-scores a cached last30days report under a shorter lookback and diffs the rankings to separate breakouts from fading from sustained. Offline companion skill — no extra API calls.

Agent skill for clear technical and product writing: draft, revise, and audit docs on Google + GDS style while preserving facts, tokens, and voice.

Operational guidance for AI coding agents—not setup docs, but best practices for using tools well.

Staged prompts for deep, opinionated reviews of skills — the behavior patches that steer agents. Centered on behavioral validation, not just careful reading.