CtrlK
BlogDocsLog inGet started
Tessl Logo

senior-laravel-developer-phpunit-interpreter

Cleans and interprets raw PHPUnit CI logs into a compact, AI-friendly failure report. Use this skill whenever the user pastes or uploads a PHPUnit log, GitHub Actions test output, CI test results, or asks to interpret/summarize/analyze failing tests. Trigger even if the user says things like "here's my test output", "tests are failing", "can you look at my PHPUnit log", or pastes a block of text that contains PHPUnit output. Always use this skill before attempting to diagnose failures.

74

Quality

91%

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

92%

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

A tightly written, highly actionable log-cleaning skill with a clear sequenced workflow and copy-paste output template. The main gap is the absence of any progressive-disclosure structure — everything lives in one monolithic file with no reference materials.

Suggestions

Consider moving the detailed output-structure template and failure-format examples into a reference file (e.g. references/output-format.md) referenced from the body, leaving the main SKILL.md as a concise overview to improve progressive_disclosure.

Add a brief verification checkpoint (e.g. "confirm the cleaned output preserves every error/failure/warning/deprecation/risky entry from the source log before returning") to make the workflow's quality-control step explicit.

If the skill grows, split the Root Cause Analysis and Architectural Diagnosis sections into a separate diagnostic-reference so the core cleanup procedure stays scannable.

DimensionReasoningScore

Conciseness

The body is lean and directive — bullet rules for cleanup, path stripping, and stack-trace processing with no re-explanation of concepts Claude already knows; every section earns its place.

3 / 3

Actionability

It gives exact, copy-paste-ready guidance: concrete removal lists (timestamps, ANSI codes, successful `✔` tests), preserved failure-format code blocks, and a full output template with placeholders.

3 / 3

Workflow Clarity

Sections are explicitly sequenced (General Cleanup → Path Cleanup → Stack Trace Processing → Failure Formats → Duplicate Removal → Formatting → Output Structure → Conditional Output Rule), with the conditional rule acting as a branch checkpoint; validation/feedback loops are not applicable to read-only log interpretation, so the level-3 sequence clarity stands.

3 / 3

Progressive Disclosure

The skill is a single ~165-line monolithic SKILL.md with no external references or progressive-disclosure structure; while well-sectioned, the detailed output template and failure-format examples are inline rather than split into reference files, matching the level-2 anchor of content that could be better organized.

2 / 3

Total

11

/

12

Passed

Description

90%

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, well-scoped description that clearly states both capability and trigger conditions with excellent natural-language trigger terms. The only weakness is that the stated capability is a single cohesive pipeline rather than a list of multiple distinct actions.

DimensionReasoningScore

Specificity

"Cleans and interprets raw PHPUnit CI logs into a compact, AI-friendly failure report" names the domain and concrete actions, but they describe one cohesive pipeline rather than the multiple distinct actions (e.g. extract, fill, merge) the level-3 anchor calls for.

2 / 3

Completeness

It explicitly answers both what ("Cleans and interprets raw PHPUnit CI logs into a compact, AI-friendly failure report") and when ("Use this skill whenever the user pastes or uploads...") with explicit trigger guidance, matching the level-3 anchor.

3 / 3

Trigger Term Quality

It covers natural user terms — "PHPUnit log", "GitHub Actions test output", "CI test results", "interpret/summarize/analyze failing tests" — plus quoted phrases users would actually say ("here's my test output", "tests are failing", "can you look at my PHPUnit log").

3 / 3

Distinctiveness Conflict Risk

The PHPUnit/CI-log niche is sharply scoped with distinct triggers (PHPUnit logs, GitHub Actions test output), making it 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
Bottelet/DaybydayCRM
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.