mflux-manual-testing

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

Quality

75%

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

92%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 a tight, actionable manual-test checklist with concrete commands, clear sequencing, and explicit validation checkpoints; its only weakness is that all content lives in one monolithic file rather than being progressively disclosed via a reference file for the diffusers comparison.

Dimension	Reasoning	Score
Conciseness	The body is a lean, command-driven checklist that assumes Claude's competence; it does not explain what mflux, CLIs, or diffusers are, and the brief framing prose earns its place.	3 / 3
Actionability	Provides fully executable commands (e.g. `uv tool install --force --editable --reinstall .`, a complete `mflux-generate` invocation with all flags, `HF_HUB_OFFLINE=1`) and specific flags to verify; the one `python -c "..."` placeholder is explicitly justified by pointing to the mflux-debugging skill.	3 / 3
Workflow Clarity	Clear sequencing from "When to Use" → "Strategy" → conditional CLI checks → human-in-the-loop output review, with explicit confirm/verify checkpoints and a branching "If visuals differ" feedback loop in the diffusers section.	3 / 3
Progressive Disclosure	The skill is a single SKILL.md with no bundle files and no file-based navigation; the fairly substantial diffusers reference-comparison section is inline content that could be split into a separate reference file, matching the score-2 anchor.	2 / 3
	Total	11 / 12 Passed

Description

57%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 concrete and domain-specific, but it lacks an explicit "Use when..." trigger and omits several natural user terms, capping completeness and trigger quality at the middle level.

Suggestions

Add an explicit trigger clause, e.g. "Use when you have changed mflux CLI entrypoints, callbacks, or image/metadata saving and want to manually confirm real command behavior before merging."

Add natural user-facing terms like "manual testing", "regression test", or "smoke test" alongside "validate" so the description matches how a user would phrase the request.

Optionally name one or two more concrete checks (e.g. metadata sidecar, low-RAM path) to raise specificity beyond the current two actions.

Dimension	Reasoning	Score
Specificity	"exercising the changed paths" and "reviewing output images/artifacts" are concrete actions naming the mflux CLI domain, but coverage is not comprehensive (omits metadata, save/load, low-ram, and the diffusers comparison covered in the body), matching the score-2 anchor.	2 / 3
Completeness	Clearly states what the skill does, but there is no "Use when..." clause or equivalent explicit trigger; per the guidelines a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant terms like "validate", "mflux CLIs", and "output images/artifacts", but misses common natural variations a user would say such as "test", "regression test", or "manual testing" (despite the skill's own name).	2 / 3
Distinctiveness Conflict Risk	The "mflux CLIs" niche is highly specific and unlikely to trigger for unrelated skills, matching the clear-niche anchor with low conflict risk.	3 / 3
	Total	9 / 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-manual-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.