← ClaudeAtlas

diagnoselisted

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
wakqasahmed/ai-engineering-workflow-skills · ★ 2 · AI & Automation · score 68
Install: claude install-skill wakqasahmed/ai-engineering-workflow-skills
# Diagnose Source: adapted from [mattpocock/skills — engineering/diagnosing-bugs](https://github.com/mattpocock/skills/blob/main/skills/engineering/diagnosing-bugs/SKILL.md). Synced 2026-09-03 to bring Phase 1 feedback loop criteria and Phase 2 reproduction & minimisation in line with upstream. The `## Redact` section below was missing from the original import and is cited separately. A discipline for hard bugs. Skip phases only when explicitly justified. When exploring the codebase, use the project's domain glossary to get a clear mental model of the relevant modules, and check ADRs in the area you're touching. ## Redact Source: [mattpocock/skills — engineering/diagnosing-bugs](https://github.com/mattpocock/skills/blob/main/skills/engineering/diagnosing-bugs/SKILL.md), added here 2026-08-26 (missing from this skill's original import). This skill has you show commands, outputs, and captured artifacts. **Redact every secret first**: write `<REDACTED>` in its place. Build loops against env vars, so the credential stays in the environment rather than in what you show. Captured artifacts carry auth headers: quote only the lines that carry the signal. If the redacted output is not enough to diagnose the bug, say so and ask the user. ## Phase 1 — Build a feedback loop **This is the skill.** Everything else is mechanical. If you have a fast, deterministic, agent-runnable pass/fail signal for the bug, you will find the cause — bisection, hypothesis-testing, and instrumentati