CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-analyze-test-failures

Use when the user mentions flaky tests, tests that pass locally but fail in CI, race conditions in tests, or needs to diagnose WHY a specific test fails.

69

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

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

The body is highly actionable with concrete grep queries, executable code, and a clear audit sequence, but it is longer than necessary due to duplicated output/severity examples and lacks an explicit retry-after-fix feedback loop for the batch diagnostic workflow.

Suggestions

Consolidate the Output Format section and Severity Definitions / False Positives sections, which repeat information already implied by the pattern annotations (CRITICAL/HIGH/MEDIUM/LOW).

Add an explicit feedback loop to the Audit Process (e.g. after fixes, re-run 'swift test --iterations 100' and only close the report when stable) to raise workflow clarity for this batch-diagnostic skill.

Trim the duplicated full markdown report templates in 'Output Format' and 'When No Issues Found' to a brief schema, keeping the body a lean overview.

DimensionReasoningScore

Conciseness

The body is mostly efficient code+pattern reference material, but the redundant Output Format examples and repeated severity/false-positive sections restate content Claude can already infer from the patterns, adding padding.

3 / 5

Actionability

Every pattern pairs an explicit Grep/Glob query with copy-paste Swift before/after examples and concrete shell commands (e.g. 'xcsym crash --format=summary', 'swift test --iterations 100'), giving fully executable guidance.

5 / 5

Workflow Clarity

The Audit Process is a clearly sequenced Step 1-3 with explicit verification ('Read surrounding context', 'Verify it's a real issue'), and the crash pattern adds a routing table, though batch diagnosis lacks an explicit validate-and-retry feedback loop.

4 / 5

Progressive Disclosure

Content is well organized into labeled sections (patterns, audit process, output format, severity, false positives) with no nested references and no bundle files; it is a self-contained overview, though some reference-style material (full output templates) could be trimmed from the inline body.

4 / 5

Total

16

/

20

Passed

Description

92%Weight 40%Scale 1-5

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

The description is strong: concrete domain, explicit trigger clause, natural user phrasing, and a clear niche. It uses third-person voice throughout with no over-claims.

DimensionReasoningScore

Specificity

The description names the domain (diagnosing flaky tests) and concrete scenarios (pass locally but fail in CI, race conditions, diagnose WHY a test fails), but does not enumerate the distinct diagnostic techniques the skill actually performs.

4 / 5

Completeness

It explicitly answers 'what' (diagnose WHY tests fail, especially flaky failures in Swift Testing) and 'when' via a clear 'Use when the user mentions...' clause with concrete triggers.

5 / 5

Trigger Term Quality

It includes natural user phrases such as 'flaky tests', 'tests that pass locally but fail in CI', 'race conditions in tests', and 'diagnose WHY a specific test fails' that map directly to what a user would say.

5 / 5

Distinctiveness Conflict Risk

The Swift Testing / iOS flaky-test niche with explicit trigger terms is clearly distinct and unlikely to fire for unrelated skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
CharlesWiltgen/Axiom
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.