mflux-testing

Run tests in mflux (fast/slow/full), preserve image outputs, and handle golden image diffs safely.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/mflux-testing/SKILL.md

Quality

Content

72%Weight 40%Scale 1-3

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

The body is well-structured and actionable with concrete commands, paths, and a clear golden-update workflow, but it carries some repetition in the manual-validation section and lacks an explicit validation feedback loop for the destructive reference-image replacement step.

Suggestions

Tighten the Manual validation section by stating the "look up the command via mflux-cli and verify with --help" pattern once instead of repeating it for the save and generate steps.

Add an explicit validate→fix→retry checkpoint to the golden-image update workflow, e.g. confirm the mismatch is within the 15% threshold and re-inspect output_*.png vs reference_*.png before replacing and committing.

Dimension	Reasoning	Score
Conciseness	Mostly lean and free of concepts Claude already knows, but the Manual validation section repeats "Use the mflux-cli skill to look up..." and "Verify CLI usage with the command's --help" twice, and could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance — Makefile targets (make test-fast/test-slow/test), the MFLUX_PRESERVE_TEST_OUTPUT=1 env var, specific paths (tests/resources/reference_.png, output_.png), and a commit-message example; the deferral to the mflux-cli skill for model-specific commands is explicitly justified flexibility.	3 / 3
Workflow Clarity	The golden-image update workflow is numbered with an inspection step, but replacing reference images is a destructive/batch operation lacking an explicit validate→fix→retry checkpoint, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Well-organized into clear sections (When to Use, Instructions, Updating golden images, Manual validation) with one-level-deep, clearly signaled references to the mflux-cli and mflux-debugging skills; under the simple-skills guideline this warrants a 3 with no bundle files to mismanage.	3 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 specific and clearly niche-scoped to mflux testing, but it omits an explicit "Use when..." trigger clause and natural trigger-term variations, which caps both completeness and trigger-term quality at 2.

Suggestions

Add an explicit "Use when..." clause with natural trigger terms, e.g. "Use when running mflux tests (fast/slow/full), debugging failing image tests, or reviewing golden image mismatches."

Include common natural variations users would say (e.g. "failing tests", "image mismatches", "reference images") so trigger-term coverage reaches a 3.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Run tests in mflux (fast/slow/full)", "preserve image outputs", and "handle golden image diffs safely" — matching the anchor for several specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does but provides no explicit "when to use it" trigger; per the guideline, a missing "Use when..." clause caps completeness at 2.	2 / 3
Trigger Term Quality	Includes some natural terms a user would say ("Run tests", "golden image diffs", "mflux") but misses common variations and has no explicit "Use when..." trigger clause, so it is not a full-3 coverage of natural phrasings.	2 / 3
Distinctiveness Conflict Risk	The mflux-specific niche and golden-image terminology make it clearly distinguishable and unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: filipstrand/mflux
Path: .cursor/skills/mflux-testing/SKILL.md
Commit: 4ac641e

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.