Hands-on prompt engineering and LLM evaluation. Built around a diagnose-then-ship loop: forensic transcript critique ▎ that names the exact failure mode, paired with a fixer that produces complete, deployment-ready rewrites — not ▎ vague advice.
Diagnose software project risk, uncover the real blockers, and turn messy delivery problems into executable recovery plans.
Stress-test any plan, PRD or decision: find the 3-5 assumptions that would kill it, with kill criteria and the cheapest test for each. Or turn a fuzzy idea into a discovery brief with opportunities, options, experiments and metrics.
Guide incidents and repeated failures through root-cause diagnosis before fixes or retries.
From a local ISSUE file to a verified, committed deliverable — with a fresh-subagent acceptance gate that catches wrong screenshots and leaked logic.
Before you write code, kill the causes of rework. A phase-gate skill that runs a pre-implementation diagnosis (clarify requirements, success criteria, non-goals, hidden risks) and sets up the dev environment (toolchain check, repo init, dependency/secret/config templates, DB/API contract, folder layout). Each gate must pass before moving on. Delivers a diagnosis report, a stack-selection doc, and a ready-to-build foundation to hand off to implementation.
Turns a user story or ticket into a verified, minimal test suite. Derives every case from a formal technique (boundary value analysis, equivalence partitioning, decision tables), reduces configuration combinations pairwise, and runs a deterministic script to prove coverage instead of just listing cases. Includes a security pass built from real OWASP findings and Playwright export.
A red-team review protocol (agent skill) for any project artifact: documents, code, quant strategies, reports.
Turn video scripts into structured retention audits — map hook failures, desertion windows, and re-engagement fixes using attention psychology.