CtrlK
BlogDocsLog inGet started
Tessl Logo

triage-e2e-test

Triage a specific Positron e2e test that is already failing or flaking in CI. Given a test name, surface its recent distinct failure modes from history, pull evidence for one mode, and reason to a root cause collaboratively with the engineer, landing on a concrete test fix or a product-bug repro. Test-centric counterpart to e2e-failure-analyzer (run-centric). For authoring a brand-new test, use author-e2e-tests.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured orchestrator skill: actionable commands, a clearly sequenced workflow with real validation checkpoints, and clean progressive disclosure to existing reference and script files. The only weakness is mild redundancy between the Scripts and Record-the-result sections that could be tightened.

Suggestions

De-duplicate the record-diagnosis.js invocation and outcome narration: describe the command once in Scripts and have Record-the-result reference it by name rather than restating the full flags.

Trim restated rules in the body that already appear in 'Non-negotiable rules' (e.g. the 'Never increase a timeout' / 'one green run is not proof' points resurface in Reproduce and fix) to single cross-references.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes Claude's competence (no explaining what e2e tests or flakes are), but the record-diagnosis invocations and outcome narration are repeated near-verbatim across the Scripts and Record-the-result sections, which could be tightened.

2 / 3

Actionability

Provides fully executable, copy-paste-ready commands with concrete flags ('node .../triage-history.js --test-key ... --lookback-days 14'), a real failure-mode table with a Seen-on column, and an explicit outcome-to-command mapping.

3 / 3

Workflow Clarity

Clear multi-stage sequence (Start/resume, Investigate, Root cause, Reproduce/fix, Record) with explicit validation checkpoints and feedback loops — checkpoint.js refuses phase=done until an outcome is set, 'Zero runs is never a clean result,' and the RED-bar and read-the-summary-first guards.

3 / 3

Progressive Disclosure

SKILL.md is a concise overview pointing to five real, one-level-deep reference files (history-query, prior-triage, evidence-escalation, diagnosis-block, reproduction), each linked at the exact stage that needs it, with deterministic work split into scripts/ — no nested references and easy navigation.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities, gives natural trigger terms, and explicitly bounds when to use it versus adjacent skills. It answers both what and when without padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'surface its recent distinct failure modes from history,' 'pull evidence for one mode,' 'reason to a root cause,' 'landing on a concrete test fix or a product-bug repro.' This matches the anchor for listing multiple specific concrete actions, beyond merely naming a domain.

3 / 3

Completeness

Clearly answers both what (the action sequence) and when — 'already failing or flaking in CI' and the explicit boundary 'For authoring a brand-new test, use author-e2e-tests' serve as explicit trigger guidance equivalent to a 'Use when...' clause.

3 / 3

Trigger Term Quality

Uses natural terms an engineer would say — 'e2e test,' 'failing or flaking in CI,' 'failure modes,' 'root cause,' 'test fix,' 'product-bug repro' — giving good coverage of common phrasings rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

Carves a clear test-centric niche and explicitly disambiguates from siblings — 'Test-centric counterpart to e2e-failure-analyzer (run-centric)' and 'For authoring a brand-new test, use author-e2e-tests' — making it unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
posit-dev/positron
Reviewed

Table of Contents

Is this your skill?

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.