AGENT SKILL

diagnosing-bugs

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose", "debug this", "debugge das", "finde den Fehler", or reports something broken, throwing, failing, or slow ("kaputt", "geht nicht", "Fehler", "langsam").

License 许可
MIT
最近更新
2026-10-05
Stars
★ 0
Forks
0

01 前言 Front Matter

name
diagnosing-bugs
description
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose", "debug this", "debugge das", "finde den Fehler", or reports something broken, throwing, failing, or slow ("kaputt", "geht nicht", "Fehler", "langsam").

03 SKILL.md 正文

Diagnosing Bugs

A discipline for hard bugs. Skip phases only when explicitly justified.

When exploring the codebase, read CONTEXT.md (if it exists) for a clear mental model of the relevant modules, and check the ADRs in the area you're touching.

Phase 1 — Build a feedback loop

This is the skill. Everything else is mechanical. If you have a tight pass/fail signal for the bug — one that goes red on this bug — you will find the cause; bisection, hypothesis-testing, and instrumentation all just consume it. 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.

Ways to construct one — try them in roughly this order

  1. Failing test at whatever seam reaches the bug — unit, integration, e2e.
  2. Curl / HTTP script against a running dev server.
  3. CLI invocation with a fixture input, diffing stdout against a known-good snapshot.
  4. Headless browser script (Playwright / Puppeteer) — drives the UI, asserts on DOM/console/network.
  5. Replay a captured trace. Save a real network request / payload / event log to disk; replay it through the code path in isolation.
  6. Throwaway harness. Spin up a minimal subset of the system (one service, mocked deps) that exercises the bug code path with a single function call.
  7. Property / fuzz loop. If the bug is "sometimes wrong output", run 1000 random inputs and look for the failure mode.
  8. Bisection harness. If the bug appeared between two known states (commit, dataset, version), automate "boot at state X, check, repeat" so you can git bisect run it.
  9. Differential loop. Run the same input through old-version vs new-version (or two configs) and diff outputs.
  10. HITL loop. Last resort. If a human must click, drive them with a structured human-in-the-loop script — the human performs the step, its captured output feeds back to you — so the loop stays repeatable instead of ad-hoc.

Build the right feedback loop, and the bug is 90% fixed.

Tighten the loop

Treat the loop as a product. Once you have a loop, tighten it:

  • Can I make it faster? (Cache setup, skip unrelated init, narrow the test scope.)
  • Can I make the signal sharper? (Assert on the specific symptom, not "didn't crash".)
  • Can I make it more deterministic? (Pin time, seed RNG, isolate filesystem, freeze network.)

A 30-second flaky loop is barely better than no loop; a 2-second deterministic one is tight — a debugging superpower.

Non-deterministic bugs

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.

When you genuinely cannot build a loop

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.

Completion criterion — a tight loop that goes red

Phase 1 is done when the loop is tight and red-capable: you can name one command — a script path, a test invocation, a curl — that you have already run at least once (paste the invocation and its output), and that is:

  • [ ] Red-capable — it drives the actual bug code path and asserts the user's exact symptom, so it can go red on this bug and green once fixed. Not "runs without erroring" — it must catch this specific bug.
  • [ ] Deterministic — same verdict every run (flaky bugs: a pinned, high reproduction rate, per above).
  • [ ] Fast — seconds, not minutes.
  • [ ] Agent-runnable — you can run it unattended; a human in the loop only via a structured HITL script.

If you catch yourself reading code to build a theory before this command exists, stop — jumping straight to a hypothesis is the exact failure this skill prevents. No red-capable command, no Phase 2.

Phase 2 — Reproduce + minimise

Run the loop. Watch it go red — the bug appears.

Confirm:

  • [ ] The loop produces the failure mode the user described — not a different failure that happens to be nearby. Wrong bug = wrong fix.
  • [ ] The failure is reproducible across multiple runs (or, for non-deterministic bugs, at a high enough rate to debug against).
  • [ ] You have captured the exact symptom (error message, wrong output, slow timing) so later phases can verify the fix.

Minimise

Once it's red, shrink the repro to the smallest scenario that still goes red. Cut inputs, callers, config, data, and steps one at a time, re-running the loop after each cut — keep only what's load-bearing for the failure.

Why bother: a minimal repro shrinks the hypothesis space in Phase 3 (fewer moving parts to suspect) and becomes the clean regression test in Phase 5.

Done when every remaining element is load-bearing — removing any one makes the loop go green. Do not proceed until you have reproduced and minimised.

Phase 3 — Hypothesise

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 X is the cause, then changing Y will make the bug disappear / changing Z 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 AFK.

Phase 4 — Instrument

Each probe must map to a specific prediction from Phase 3. Change one variable at a time.

Tool preference:

  1. Debugger / REPL inspection if the env supports it. One breakpoint beats ten logs.
  2. Targeted logs at the boundaries that distinguish hypotheses.
  3. Never "log everything and grep".

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, performance.now(), profiler, query plan), then bisect. Measure first, fix second.

Phase 5 — Fix + regression test

Write the regression test before the fix — but only if there is a correct seam for it. A correct seam exercises the real bug pattern as it occurs at the call site. If the only available seam is too shallow (a single-caller test when the bug needs multiple callers, a unit test that can't replicate the triggering chain), a test there gives false confidence.

If no correct seam exists, that itself is the finding. Note it — the architecture is preventing the bug from being locked down. Flag it for the next phase.

If a correct seam exists:

  1. Turn the minimised repro into a failing test at that seam.
  2. Watch it fail.
  3. Apply the fix.
  4. Watch it pass.
  5. Re-run the Phase 1 loop against the original (un-minimised) scenario.

Phase 6 — Cleanup + post-mortem

Required before declaring done:

  • [ ] Original repro no longer reproduces (re-run the Phase 1 loop)
  • [ ] Regression test passes (or absence of seam is documented)
  • [ ] All [DEBUG-...] instrumentation removed (grep the prefix)
  • [ ] Throwaway prototypes deleted (or moved to a clearly-marked debug location)
  • [ ] The hypothesis that turned out correct is stated in the commit / PR message — so the next debugger learns

Then ask: what would have prevented this bug? If the answer involves architectural change (no good test seam, tangled callers, hidden coupling), hand off to cape:architect with the specifics. Make the recommendation after the fix is in, not before — you have more information now than when you started.

04 同仓库更多 Skills

colenet-gmbh
colenet-gmbh/colenet-claude-code-plugin

triage

Backlog management — move not-yet-worked-up items through triage roles into agent-ready briefs, whatever their origin. Use when the user wants to sort or work up a backlog of bug reports, feature requests, or ideas, mentions "triage", "triagieren", "Backlog sichten", "Backlog pflegen", "sort the backlog", "manage the backlog", or points at an untriaged item in docs/work/01-backlog.

★ 0
colenet-gmbh
colenet-gmbh/colenet-claude-code-plugin

teach

Teach the user a new skill or concept over multiple sessions, turning the current directory into a stateful teaching workspace grounded in a mission, trusted resources, and beautiful lessons. Use when the user wants to learn or be taught something, or says "teach me", "bring mir bei", "lehre mich", "ich will X lernen", "mach mich fit in", "onboard me on", "help me learn".

★ 0
colenet-gmbh
colenet-gmbh/colenet-claude-code-plugin

research

Delegate reading legwork to a background agent — investigate a question against high-trust primary sources (official docs, source code, specs, first-party APIs) and leave the findings as a cited Markdown note in the repo. Use when engineering work needs docs, API, or codebase facts gathered before building, or the user says "recherchiere das", "schau in den Docs nach", "lies dich in X ein", "research this", "gather the facts on", "read up on". For a broad, multi-source web report with adversarial fact-checking, reach for deep-research instead; cape:research is the lighter, repo-bound feeder that leaves a note behind.

★ 0
colenet-gmbh
colenet-gmbh/colenet-claude-code-plugin

prototype

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

★ 0
colenet-gmbh
colenet-gmbh/colenet-claude-code-plugin

handoff

Compact the current conversation into a handoff document for another agent to pick up.

★ 0
colenet-gmbh
colenet-gmbh/colenet-claude-code-plugin

grilling

Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.

★ 0