- Home
- Skills
- Testing & Debugging
- Playwright CI Triage
Playwright CI Triage
Turn a failed Playwright CI run into grouped investigation notes: retry history, error evidence and trace findings in HTML, Markdown and JSON.
$5.90
Works with the AI Agents you already use
Playwright CI Triage
Example session with this skill installed
Our Playwright CI run failed again. Triage test-results/report.json and tell me which failures are real and which are flaky.
- Read your context and instructions
- Compiled the playwright ci triage
- Generated the document
Summary
Scanned the supplied Playwright JSON report: 6 tests, 2 unexpected, 1 flaky, 2 expected, 1 skipped. One real regression, one flaky test, and one expected-failure test that now passes.
Report outcomes
| Outcome | Count |
|---|---|
| expected | 2 |
| flaky | 1 |
| skipped | 1 |
| unexpected | 2 |
Assertion mismatch: demo.spec.cjs > broken checkout total
Status: unexpected · Attempts: failed, failed
Error: expect(received).toBe(expected)
Expected: 29
Received: 19
> 4 | test('broken checkout total', async () => { expect(19).toBe(29); });
Failed on both attempts, so this is a consistent failure, not flakiness. Next check: compare the checkout total source with the fixture price.
Assertion mismatch: demo.spec.cjs > retry recovers
Status: flaky · Attempts: failed, passed
Passed only on retry. Next check: open the retry 0 trace and look for a timing or state dependency.
Needs investigation: demo.spec.cjs > unexpectedly repaired defect
Status: unexpected · Expected failed · Attempts: passed, passed
A test marked test.fail() now passes. Either the defect was fixed (remove the annotation) or the test no longer exercises it.
Next steps
- Fix the checkout total regression first; it blocks the release.
- Review the flaky test trace before re-running CI.
- Update the
test.fail()annotation once the fix is confirmed.
Full reports written to report/triage.html, triage.md and triage.json.
triage.html
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
Give your coding agent a repeatable workflow for failed Playwright runs. A bundled Python scanner (standard library only) reads your Playwright JSON report and produces HTML, Markdown and JSON summaries with error evidence, retry outcomes and attachment references. The skill then guides the agent through source and trace checks before it proposes a fix.
Included (v0.2.0)
- SKILL.md workflow
- Python scanner, no dependencies
- Retry history and expected-status handling
- Local trace ZIP analysis: failed actions, slow actions, HTTP error responses
- Sample reports from an intentionally failing demo suite
- Self-tests:
python tests/selftest.py
Limits
Tested with Playwright 1.65.0 trace format 10; other versions are flagged for review. Root cause still needs investigation in your project.
Requires Python 3.10+. Tested with Playwright 1.65.0 trace format 10. Does not extract ZIP contents. Trace root must contain all referenced attachment paths.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 4 days ago
Requires