--- title: "Diagnosing Bugs: review, setup & limitations · Undominated.ai" canonical: https://undominated.ai/skills/mattpocock-diagnosing-bugs/ description: "A debugging procedure that establishes a reproducible symptom, tests competing explanations and preserves a regression check." --- # Diagnosing Bugs: review, setup & limitations · Undominated.ai > A debugging procedure that establishes a reproducible symptom, tests competing explanations and preserves a regression check. [← Explore all skills](/skills/) TESTING AND RELIABILITY / Matt Pocock # Diagnosing Bugs A debugging procedure that establishes a reproducible symptom, tests competing explanations and preserves a regression check. See setup guidance ↓Original source ↗ SOURCE REVIEW Reviewed 2026-09-22 Evidence 8 linked sources Publisher Matt Pocock Licence MIT ↗ Revision c55ee46073ed Read what was—and wasn’t—checked ↓ “Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.” Matt Pocock · upstream description ↗ Our analysis follows below. 01 / THE REASONING ## Why this made the selection. - Requires a red-capable reproduction before edits, so an apparent improvement has a concrete behavior to compare against. - Tests one hypothesis at a time and asks for the original scenario to be rerun after the fix, including removal of temporary instrumentation. ### A good fit for - Intermittent defects or performance regressions where the first plausible explanation is unreliable - Collaborative debugging when a user must run the reproduction in an inaccessible environment ### Weigh up before choosing - The included human-in-the-loop shell script is an editable single-line-input template, not a ready-made test runner or secret-redaction tool. - A blocked reproduction remains blocked; this procedure cannot establish a fix from an explanation alone. - Stress tests and instrumentation need a suitable target and explicit scope; the prompt supplies no operating-system sandbox. 02 / THE REVIEW RECORD ## What we actually inspected. Source review has boundaries. A clear record is more useful than a “safe” badge. ### Material inspected - skills/engineering/diagnosing-bugs/SKILL.md - README.md (installation and supported-host sections) - LICENSE - skills/engineering/diagnosing-bugs/agents/openai.yaml - skills/engineering/diagnosing-bugs/scripts/hitl-loop.template.sh ### Our findings - The definition distinguishes observations from hypotheses and ties each proposed mechanism to a falsification test. - The full HITL helper was inspected: it prints user-supplied answers and needs adaptation to the real scenario. ### Not established by this review - No upstream definition, helper, installer or generated workload was executed. - No end-to-end agent session or effectiveness benchmark was run. The review applies to the material and revision named here. A newer upstream release can change its behavior. 03 / PUT IT TO WORK ## Add a skill to your workflow. Upstream setup instructions ↗ DOCUMENTED COMMAND npx skills add https://github.com/mattpocock/skills/tree/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/engineering/diagnosing-bugs --skill diagnosing-bugs Copy command ↗ Copying does not execute this command. It may retrieve a newer version than the reviewed source. - Install the complete skill directory, including its references and helpers; select your intended host and project scope. - Review the instructions before invoking them. The source revision is pinned; the installer was not executed or version-pinned by this review. ### Before you start - Node.js/npm and git for the documented Skills installer - An agent host that supports the skill format and the tools required by the workflow ### Compatibility Claude Code · Codex ### Repository instructions and host-provided tools - Read the relevant source, logs and tests - Edit a bounded reproduction, instrumentation and an authorized fix - Run approved tests; redact sensitive outputs before sharing ### Cost model MIT-licensed instructions; agent usage and test or infrastructure compute are separate. 04 / FOLLOW THE EVIDENCE ## The source trail. Our notes are separate from the original resource. Check upstream before adopting a new version. - Definition at the reviewed revision ↗ Checked 2026-09-22 https://github.com/mattpocock/skills/blob/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/engineering/diagnosing-bugs/SKILL.md Supports: summary, upstreamDescription, whySelected, bestFor, limitations, review, access - Publisher installation guidance ↗ Checked 2026-09-22 https://github.com/mattpocock/skills/blob/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/README.md Supports: install, compatibility - Licence at the reviewed revision ↗ Checked 2026-09-22 https://github.com/mattpocock/skills/blob/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/LICENSE Supports: license, access.cost - Reviewed companion: skills/engineering/diagnosing-bugs/agents/openai.yaml ↗ Checked 2026-09-22 https://github.com/mattpocock/skills/blob/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/engineering/diagnosing-bugs/agents/openai.yaml Supports: review, limitations, install, access - Reviewed companion: skills/engineering/diagnosing-bugs/scripts/hitl-loop.template.sh ↗ Checked 2026-09-22 https://github.com/mattpocock/skills/blob/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/engineering/diagnosing-bugs/scripts/hitl-loop.template.sh Supports: review, limitations, install, access - Skills installer: README.md ↗ Checked 2026-09-22 https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md Supports: install - Skills installer: src/git.ts ↗ Checked 2026-09-22 https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/src/git.ts Supports: install - Skills installer: src/source-parser.ts ↗ Checked 2026-09-22 https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/src/source-parser.ts Supports: install KEEP COMPARING ## Other approaches to consider. Related by category or shared topics. These are alternatives to inspect, not a measured quality order. [### Superpowers Systematic Debugging ↗ Moves debugging from reproducible evidence through a single hypothesis to a verified fix, with a stop point for repeated failed attempts.](/skills/obra-systematic-debugging/)[### Bug Receipt ↗ Creates an evidence-bearing defect or incident handoff that distinguishes verified, partial and blocked outcomes.](/skills/github-bug-receipt/)[### Superpowers Test-Driven Development ↗ Makes an observed failing behavior test the entry point for implementation and checks that assertions can detect real production mistakes.](/skills/obra-test-driven-development/) [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)