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.
Audits your test suite's output for silently vanished tests, unexplained skips, and suspiciously fast runs — turns green CI into a real signal.
Analyze failed CI/CD pipelines, identify likely root causes, inspect repository configuration and code context, and produce actionable, validated remediation guidance for GitHub Actions, GitLab CI, Jenkins, and related development pipelines.
Born from running 50 MCP tools at once: Claude picked wrong tools, logged nothing, and 50 tools were unmanageable. DB2MCP hides every query behind 4 fixed tools. The AI says what it needs, a BM25 score picks the query, weak or tied scores return "none" or a question; call will not run without a purpose, so every call is logged. Add tables, the 4 never change. Connection string in, 5 minutes later your AI queries your DB. Every answer links to a dashboard and Excel of the same query. Read-only.
Point it at your repo (or a specific change) and it scaffolds a unit-test suite for you — auto-detects your runner (Jest/Vitest, pytest, Go, XCTest, JUnit/Kotest), writes idiomatic AAA tests matching your conventions, then RUNS them and fixes test-side failures until green. It never edits your source — a real bug is reported, not papered over. Zero config.
A senior-engineer-style code review assistant: severity-ranked findings, security smell detection, and constructive feedback across 8 language families.
Academic sanity-check with interactive HTML dashboard. Detects look-ahead bias, over-parameterization, and benchmarks against 10 canonical blueprints via animated SVG gauges and color-coded KPI cards. Parses natural language, code, or CSV uploads. Output auto-adapts (EN/ZH-TW/ZH-CN). Built on De Prado (2018). For students and strategy developers. Not financial advice.
Turn prompts or workflows into testable, launch-ready AI Skill products.