Build & Code / D11
ProPreview cut from the real Pro body
Fix a failing test suite
Triage failing tests by root cause, isolate regressions, and propose minimal fixes.
For
Engineers
Time per use
15 min
Format
.md and .skill
How to use it
- 1.Open ChatGPT or Claude.Either works. The skill is just text.
- 2.Inspect the real preview, then unlock the full file.One click; no install, no setup.
- 3.Paste it as your first message.The assistant now knows how to do this one job.
- 4.Give it your specifics, get the result.Roughly 15 min, every time you need it.
Skill filed11-fix-a-failing-test-suite.skill.md1.2 KB
Run once
Advanced
Install permanently ↓Mobile apps: if ChatGPT or Claude opens blank, tap the message box and paste. Skillbook copies first.
Mobile apps: if ChatGPT or Claude opens blank, tap the message box and paste. Skillbook copies first.
Fill the blanks first.
These fields update the skill preview and the ChatGPT/Claude buttons instantly.
IncludePaste failing test names, stack traces, assertions, logs, screenshots, or CI output.
IncludePRs, commits, dependency updates, env changes, data changes, or config changes.
IncludeRelevant files, framework, test runner, mocks, fixtures, APIs, or timing constraints.
IncludeLocal runs, other suites, browser checks, CI jobs, or unaffected paths.
Install as agent behavior
Permanent agent install needs the full body.
This page is only showing a preview. Unlock the full skill to install it in Claude Code, Claude Projects, or a Custom GPT.
# Fix a failing test suite
You are a test triage lead. I will paste failing test output, recent changes, and context. Separate real regressions from brittle tests and propose the smallest safe fix.
## Inputs
Test output: {{test_output||Paste failing test names, stack traces, assertions, logs, screenshots, or CI output.}}
Recent changes: {{recent_changes||PRs, commits, dependency updates, env changes, data changes, or config changes.}}
System context: {{system_context||Relevant files, framework, test runner, mocks, fixtures, APIs, or timing constraints.}}
What already passed: {{what_passed||Local runs, other suites, browser checks, CI jobs, or unaffected paths.}}
## Output
**1. Failure grouping.** Cluster failures by likely root cause.
**2. Top hypothesis.** The most likely cause and evidence.
**3. Regression vs test issue.** Which failures indicate product behavior changed and which may be stale or flaky.
**4. Fix plan.** Minimal code or test changes, in order.
**5. Verification loop.** Exact rerun order to confirm progress.
**6. Reviewer note.** What to explain in the PR so reviewers trust the fix.
## Rules
[Preview stops here. Unlock the Pro library for the full rules, guardrails, examples, and copyable file.]The rest is in the Pro library.
This preview is cut from a real Pro workflow. Unlock the founding Pro library for the full file, rules, examples, and installable skill.
Full Pro file includes
- ✓ Input checklist
- ✓ Step-by-step workflow
- ✓ Quality bar
- ✓ Guardrails
- ✓ Output format
- ✓ Example run
- ✓ Install formats
Other things on the Build & Code shelf