mflux-manual-testing

Manually validate mflux CLIs by exercising the changed paths and reviewing output images/artifacts.

Quality

64%

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-manual-testing/SKILL.md

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 a lean, actionable manual-testing playbook with concrete commands, explicit per-check verification statements, and clear sectioning. It falls just short of top marks due to a placeholder inline script, light motivational padding, and a diffusers section that could be split out.

Suggestions

Replace the diffusers `python -c "..."` placeholder with a complete executable inline snippet or a concrete file-based example so the comparison step is copy-paste ready.

Tighten the opening rationale and 'Notes' section to remove motivation Claude already infers, pushing conciseness toward a 5.

Consider moving the diffusers reference-comparison workflow into a dedicated reference file linked from SKILL.md to improve progressive disclosure and keep the core checklist lean.

Dimension	Reasoning	Score
Conciseness	Checklist-style content assumes Claude's familiarity with mflux and mostly earns its tokens; minor motivational padding ('Some regressions... are easiest to catch') and a few explanatory asides could be trimmed.	4 / 5
Actionability	Provides concrete, executable commands (uv tool install, mflux-save, --stepwise-image-output-dir, --low-ram, --metadata) with specific flags; the diffusers inline `python -c "..."` placeholder is the main gap keeping it from a 5.	4 / 5
Workflow Clarity	Clear change-driven sequence (reinstall → identify changes → run relevant checks → review output → optional diffusers comparison) with explicit confirm/verify checkpoints and a human-in-the-loop review step, though a formal validate→fix→retry feedback loop is only implied.	4 / 5
Progressive Disclosure	Well-organized single-file skill with clear section headers and a one-level, clearly signaled reference to the sibling mflux-debugging skill; the standalone diffusers comparison block is a minor candidate for extraction into its own reference file.	4 / 5
	Total	16 / 20 Passed

Description

53%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 specific to the mflux CLI niche and states concrete actions, but it omits an explicit 'Use when' trigger clause and lacks natural trigger-term variations, which together cap the completeness and trigger scores at 3.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when you changed mflux CLI entrypoints or image/metadata saving and want manual confidence beyond automated tests.'

Include natural trigger terms users would actually say, such as 'manual testing', 'test the CLI', or 'sanity-check mflux output'.

Briefly enumerate the distinct check types (generation, save/load, stepwise, low-RAM, metadata) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (mflux CLIs) and two concrete actions ('exercising the changed paths' and 'reviewing output images/artifacts'), but coverage is not comprehensive — no enumeration of the distinct check types.	3 / 5
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Contains relevant keywords ('validate', 'mflux CLIs', 'images/artifacts') but misses common natural variations a user would say such as 'test', 'testing', or 'manual test'.	3 / 5
Distinctiveness Conflict Risk	Narrowly scoped to mflux CLI manual validation with a distinct niche; minor overlap risk only with closely related mflux skills such as mflux-debugging.	4 / 5
	Total	13 / 20 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-manual-testing/SKILL.md
Commit: 1430b27

Reviewed: 2 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.