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.

64

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./axiom-codex/skills/axiom-analyze-test-failures/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 executable code and concrete detection commands and a clear audit workflow with verification checkpoints. Its main weaknesses are conciseness (duplicated worked examples and restated pattern tables) and progressive disclosure (a monolithic file with inline material that belongs in reference files).

Suggestions

De-duplicate: remove the verbatim restatement of the Pattern 1 example from the Output Format section and have it reference the pattern, and collapse the Best Practices table / Severity Definitions where they restate existing pattern content.

Move the large Output Format template and the XCTest Legacy section into reference files (e.g. OUTPUT_FORMAT.md, LEGACY_XCTEST.md) and link to them from a leaner overview to improve progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly efficient — concrete code, grep regexes, and commands with no concept-explanation padding — but it repeats material: the Pattern 1 example is restated verbatim in the Output Format section, and the Best Practices table and Severity Definitions restate the patterns, so it could be tightened.

2 / 3

Actionability

Every pattern ships executable ❌/✅ Swift code, concrete Grep patterns (e.g. \.sink\s*\{|completion\s*:"), and copy-paste shell commands (xcsym crash --format=summary, swift test --parallel --num-workers 8); the pattern_tag routing table is directly usable.

3 / 3

Workflow Clarity

The Audit Process is a clear three-step sequence with an explicit validation checkpoint (Step 3: "Verify it's a real issue", "Check if fix is already present") plus a False Positives to Avoid section and an after-fix verification loop (swift test --iterations 100).

3 / 3

Progressive Disclosure

It is a single ~400-line monolithic SKILL.md with no bundle references, and inline content that could be separate (the full Output Format template, XCTest Legacy patterns) is not split out, though section headers keep it reasonably navigable.

2 / 3

Total

10

/

12

Passed

Description

72%

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 excels at trigger-term quality and distinctiveness with natural, specific phrasing, but is capped by weak capability specificity and an implied rather than stated "what". Adding one clause naming the concrete actions (scan Swift test files, flag flaky patterns, suggest fixes) would lift specificity and completeness.

Suggestions

Add an explicit capability clause naming what the skill does, e.g. "Scans Swift test files for flaky patterns (missing confirmation, shared state, missing @MainActor) and produces a ranked report with fixes".

Keep the strong "Use when..." triggers but pair them with the "what" so both halves of completeness are explicit rather than implied by "diagnose".

DimensionReasoningScore

Specificity

The description names a specific problem domain ("flaky tests", "race conditions in tests", "diagnose WHY a specific test fails") but does not enumerate concrete actions the skill performs (e.g. scanning test files, matching patterns, producing a report); the capability is only implied by "diagnose".

2 / 3

Completeness

It has a strong explicit "when" ("Use when the user mentions...") but the "what" is only implied — it never states the skill analyzes the codebase for flaky patterns and emits findings, so it does not clearly answer both what AND when.

2 / 3

Trigger Term Quality

Phrases like "flaky tests", "tests that pass locally but fail in CI", "race conditions in tests", and "diagnose WHY a specific test fails" are exactly the natural terms a developer would say when they need this skill.

3 / 3

Distinctiveness Conflict Risk

Flaky/intermittent test diagnosis is a clear niche with distinct triggers that are unlikely to fire for unrelated testing or coding skills.

3 / 3

Total

10

/

12

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.