🧰 Engineering practice

Diagnoses bugs by reproducing first and naming the root cause before any code changes — reproduce, instrument, bisect, prove the fix against the reproduction, leave a regression test. Use whenever something is reported broken, failing, or behaving wrong, before attempting a fix.

Interrogates a finished diff adversarially before it becomes a commit or PR — correctness, edge cases, security, and performance challenges the author must answer or fix. Use when a feature or fix is declared done, before committing, opening a PR, or handing work to review.

Enforces Uplift Duo house code style — naming, comments, error handling, and structure. Use when writing, editing, or reviewing code in any language.

Produces dual effort estimates — traditional human-developer weeks alongside an agent-driven build-days + tokens + cost figure assuming a tight, increasingly-unsupervised feedback loop. Use when asked to estimate effort, time, cost, timeline, "how long", "how much", or scope for a build, feature, migration, or refactor.

Applies the Uplift Duo git workflow — branch naming, commit triggers, the emoji commit message format, GitHub defaults, and merge rules. Use when branching, committing, merging, or creating repos.

Audits a directory of git repositories and produces an interactive Project Audit — per-repo descriptions, % complete, ratings (market size, value, code quality, security, momentum), bugs by severity, feature suggestions and improvements with type tags, major-change timelines, tech-stack analysis with recommended alternatives, AI model attribution by percent, token usage (commit-block estimates vs measured transcripts with a completeness comparison), total AI thinking time, and a copy-paste improvement prompt per repo. Use when the user asks to audit, review, rate, or take stock of their repos, projects, or portfolio, asks "what's the state of my projects", or wants a project audit for any time window.