CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-debug-tests

Use this agent for closed-loop test debugging - automatically analyzes test failures, suggests fixes, and re-runs tests until passing.

67

Quality

80%

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-debug-tests/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.

A highly actionable, well-sequenced debugging workflow with strong feedback loops. It loses points on token efficiency (redundant restated triage) and progressive disclosure (monolithic body, missing referenced bundle files).

Suggestions

De-duplicate the failure triage that appears in the failure-pattern table, the Error Quick Reference, and the Decision Tree — keep one canonical source and cross-reference it.

Move the xcsym crash-triage table and the pattern reference into a real reference file (e.g. references/xcsym-ref.md) and link to it, so the referenced path actually exists and the body stays a lean overview.

Split the large failure-pattern / fix recipe tables into a reference doc and keep SKILL.md as the phased overview + decision tree.

DimensionReasoningScore

Conciseness

Mostly actionable and assumes Claude's competence, but ~322 lines with restated triage across the failure-pattern table, Error Quick Reference, and Decision Tree could be tightened.

2 / 3

Actionability

Executable xcodebuild/xcresulttool/xcsym commands and concrete BEFORE/AFTER Swift fixes are copy-paste ready, with only minor <SCHEME_NAME> placeholders.

3 / 3

Workflow Clarity

A clear 7-phase RUN→CAPTURE→ANALYZE→SUGGEST→FIX→VERIFY→REPORT loop with an explicit verify re-run, max-3-iteration escalation, and a decision tree.

3 / 3

Progressive Disclosure

No references/scripts/assets bundle files exist, so the body is a monolithic >50-line document; pointers like 'skills/xcsym-ref.md' reference no real file and there is no content split for discovery.

2 / 3

Total

10

/

12

Passed

Description

82%

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 specific, action-oriented description with natural trigger terms and a clear niche. Its main weakness is the thin 'when' guidance — a single trigger phrase rather than an explicit Use-when clause enumerating scenarios.

Suggestions

Add an explicit 'Use when ...' clause enumerating trigger scenarios, e.g. 'Use when a UI test fails, when the user reports a failing/red test, or when tests need to be fixed and re-run until green.'

Include a few common user phrasings ('failing test', 'red test', 'test failure') to broaden trigger coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'analyzes test failures, suggests fixes, and re-runs tests until passing' — rather than vague domain language.

3 / 3

Completeness

The 'what' is clear, but the 'when' is only a single 'Use this agent for closed-loop test debugging' clause with no enumerated explicit triggers, capping completeness at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

Natural terms a user would say ('test debugging', 'test failures', 'fixes', 're-runs tests') are present and relevant.

3 / 3

Distinctiveness Conflict Risk

The closed-loop 're-runs tests until passing' framing is a distinct niche unlikely to fire for unrelated skills.

3 / 3

Total

11

/

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.