borghei/Claude-Skills / engineering/bug-diagnosis
bug-diagnosis
VerifiedFind the root cause of hard bugs with a fast pass/fail repro, ranked falsifiable hypotheses and bisection. Use when a bug resists quick fixes, a failure is intermittent, or a regression needs tracing to its cause.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 14.3 KB |
| assets/diagnosis-log-template.md | markdown | 1.9 KB |
| assets/repro-script-template.sh | script | 1.4 KB |
| assets/sample_debug_log.txt | markdown | 1.0 KB |
| assets/sample_diagnosis_log.json | config | 1.6 KB |
| assets/sample_diagnosis_log_passing.json | config | 1.8 KB |
| references/bisection-instrumentation-redaction.md | markdown | 8.7 KB |
| references/reproduction-signals.md | markdown | 7.8 KB |
| scripts/hypothesis_log.pyexecutable | script | 10.2 KB |
| scripts/redact_scan.pyexecutable | script | 8.3 KB |
assets/diagnosis-log-template.md
View on GitHub# Diagnosis Log — <bug title>
**Reported by:** <name / ticket> **Owner:** <name> **Opened:** YYYY-MM-DD
**Status:** investigating | fixed | blocked
**Debug tag:** `[DBG-xxxx]` (every temporary log line carries it)
## 1. Symptom
- Expected: <what should happen>
- Actual: <exact error text, wrong value or measured latency — redacted>
- First seen: <date, release, or commit>
- Scope: <who / which inputs are affected; who is not>
## 2. Reproduction signal
| Field | Value |
|-------|-------|
| Command | `<one command; secrets read from environment variables>` |
| Asserts | <the specific symptom it checks> |
| Runs / red runs | <n> / <n> |
| Runtime | <seconds> |
| Minimised | yes / no — <what was removed> |
| Pinned | clock, seed, locale, network, workers |
## 3. Hypotheses (write all before testing any)
| ID | Mechanism | Prediction (if … then …) | Experiment | Prior | Cost (min) | Status | Evidence |
|----|-----------|--------------------------|------------|-------|-----------|--------|----------|
| H1 | | | | | | open | |
| H2 | | | | | | open | |
| H3 | | | | | | open | |
## 4. Experiments (one variable each)
| # | Hypothesis | Change | Variable changed | Result | Notes |
|---|------------|--------|------------------|--------|-------|
| 1 | | | | | |
## 5. Bisection (if used)
- Space: commits / input records / flags / dependency versions
- Good: <state> Bad: <state>
- Result: <first bad state> — attach `git bisect log` or the halving trail
## 6. Cause
<The confirmed hypothesis, the evidence that confirmed it, and why it produces
the symptom.>
## 7. Fix and regression test
- Regression test: `<path::name>` — seen failing before the fix: yes / no
- If no test: reason no seam reaches the failure pattern
- Original signal green after fix: yes / no
- `grep -rn "<debug tag>"` returns nothing: yes / no
- Shared artefacts passed through `redact_scan.py`: yes / no
## 8. Follow-ups
- <design issue surfaced, monitoring gap, related bugs>
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |