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.
97%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
The canonical home for this skill is diagnose in agranado2k/google-books-clojure
A discipline for hard bugs. Skip phases only when explicitly justified.
When exploring the codebase, use docs/domain-glossary.md to get a clear mental model of the relevant modules, and check the decision records in docs/adr/ covering the area you're touching — a "bug" that is actually a recorded decision is a very expensive fix.
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 instrumentation all just consume that signal. If you don't have one, no amount of staring at code will save you.
Spend disproportionate effort here. Be aggressive. Be creative. Refuse to give up.
.claude/skills/diagnose/scripts/hitl-loop.template.sh so the loop is still structured. Captured output feeds back to you.Build the right feedback loop, and the bug is 90% fixed.
Treat the loop as a product. Once you have a loop, ask:
A 30-second flaky loop is barely better than no loop. A 2-second deterministic loop is a debugging superpower.
The goal is not a clean repro but a higher reproduction rate. Loop the trigger 100×, parallelise, add stress, narrow timing windows, inject sleeps. A 50%-flake bug is debuggable; 1% is not — keep raising the rate until it's debuggable.
Stop and say so explicitly. List what you tried. Ask the user for: (a) access to whatever environment reproduces it, (b) a captured artifact (HAR file, log dump, core dump, screen recording with timestamps), or (c) permission to add temporary production instrumentation. Do not proceed to hypothesise without a loop.
Do not proceed to Phase 2 until you have a loop you believe in.
Run the loop. Watch the bug appear.
Confirm:
Do not proceed until you reproduce the bug.
Generate 3–5 ranked hypotheses before testing any of them. Single-hypothesis generation anchors on the first plausible idea.
Each hypothesis must be falsifiable: state the prediction it makes.
Format: "If is the cause, then will make the bug disappear / will make it worse."
If you cannot state the prediction, the hypothesis is a vibe — discard or sharpen it.
Show the ranked list to the user before testing. They often have domain knowledge that re-ranks instantly ("we just deployed a change to #3"), or know hypotheses they've already ruled out. Cheap checkpoint, big time saver. Don't block on it — proceed with your ranking if the user is away.
Each probe must map to a specific prediction from Phase 3. Change one variable at a time.
Tool preference:
Tag every debug log with a unique prefix, e.g. [DEBUG-a4f2]. Cleanup at the end becomes a single grep. Untagged logs survive; tagged logs die.
Perf branch. For performance regressions, logs are usually wrong. Instead: establish a baseline measurement (timing harness, high-resolution clock, profiler, query plan), then bisect. Measure first, fix second.
Write the regression test before the fix — but only if there is a correct seam for it.
A correct seam is one where the test exercises the real bug pattern as it occurs at the call site. If the only available seam is too shallow (single-caller test when the bug needs multiple callers, unit test that can't replicate the chain that triggered the bug), a regression test there gives false confidence.
If no correct seam exists, that itself is the finding. Note it. The codebase architecture is preventing the bug from being locked down. Flag this for the next phase.
If a correct seam exists:
Required before declaring done:
[DEBUG-...] instrumentation removed (grep the prefix)Then ask: what would have prevented this bug? If the answer is architectural — no good test seam, tangled callers, hidden coupling — that is a decision, not a chore. Hand it to /improve-codebase-architecture, which turns "there was no correct seam" into a designed deepening; the specifics this diagnosis produced (which seam was missing, which callers the bug needed) are exactly the input that skill's exploration phase otherwise has to guess at. What comes out is a record under docs/adr/ or a ticket via /to-tickets — never a drive-by refactor on top of the fix (shared invariant §10). Make the recommendation after the fix is in, not before: you have more information now than when you started.
Adapted from engineering/diagnose in mattpocock/skills — MIT, see .claude/skills/LICENSE-mattpocock-skills.md. Tool names in the loop list were generalised, and the architectural hand-off at the end names this kit's /improve-codebase-architecture and the decision record it produces.
agranado2k/tic-tac-toe-with-agentic-sdlc
931d5f3
Canonical home
since Nov 19, 2026
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.