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.
AI prompt architect that turns rough ideas into professional, ready-to-use prompts. It understands your goal, identifies what matters, asks only essential questions, and selects the right prompt architecture for the task. Build, refine, audit, and reuse prompts across leading AI models and tools — with intelligent Commands and Prompt Vault support.
Analysez logs, diagnostics, erreurs et éléments techniques fournis afin d’identifier des causes probables, prioriser les anomalies et préparer un plan de correction.
This agent helps Python teams using the Anthropic or OpenAI SDK safely cut LLM spend without risking regressions. With zero code changes, it maps call sites and runs your test scenarios to rank token waste from missed prompt caching or heavy model tiers. It tests fixes in isolated git worktrees, enforcing a strict "do-no-harm" gate that reverts any patch failing to preserve behavior. It delivers a clear savings audit that converts into verified, behavior-preserving code patches upon opt-in.
I've spent years building production software, designing enterprise architectures, reviewing thousands of code changes, and optimizing AI-assisted development workflows. This Skill packages proven engineering, planning, documentation, testing, and code-review practices into a lightweight workflow that helps AI understand any project before making changes, reducing mistakes, hallucinations, unnecessary token usage, and repeated context loading.