mflux-cli

Navigate MFLUX CLI capabilities, locate commands by area, and summarize supported features.

Quality

66%

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-cli/SKILL.md

Quality

Content

65%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 concise, well-organized map of MFLUX CLI capabilities that assumes Claude's competence and avoids concept padding. It is held back by limited actionability (no executable commands or concrete paths) and a large inline capability inventory that could be externalized.

Suggestions

Add at least one concrete, runnable example CLI invocation (e.g. a representative text-to-image command) so guidance is executable rather than purely structural.

Move the 'Capability inventory' into a references file (e.g. CAPABILITIES.md) and keep SKILL.md as a tighter overview that links to it, improving progressive disclosure.

Provide a short validation step for verifying CLI support against current entrypoints (e.g. 'run the model's CLI with --help to confirm flags before constructing a call') to add a checkpoint to the workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — terse bullets and short section intros with no over-explanation of what a CLI or a model is, matching 'lean and efficient; every token earns its place'. It is above level 2 because there is no padded or unnecessary explanatory content.	3 / 3
Actionability	It names concrete identifiers such as '--low-ram', '--stepwise-image-output-dir', and 'MODEL_INFERENCE_STEPS', but is deliberately path-agnostic ('structure, not exact paths') and provides no executable CLI commands or copy-paste examples, matching 'some concrete guidance but incomplete'. It is above level 1 because specific flags and a named constant are given, and below level 3 because nothing is directly runnable.	2 / 3
Workflow Clarity	'How to find commands' gives a loose sequence of where to look (central parser, model package, shared package, utilities), but there are no validation checkpoints or feedback loops and the skill spans multiple purposes, matching 'steps listed but validation gaps'. It is below level 3 because no explicit checkpoints or error-recovery loops are present.	2 / 3
Progressive Disclosure	The single self-contained file is well-sectioned for easy navigation, but the lengthy 'Capability inventory' block (core generation through utilities) is inline content that could be split into a reference file, matching 'content that should be separate is inline'. It is above level 1 because organization is clear, and below level 3 because nothing is split off with signaled one-level-deep references.	2 / 3
	Total	9 / 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 distinctive, naming concrete navigation and summarization actions tied to the MFLUX CLI niche. Its main weakness is the absence of an explicit 'when to use' trigger clause and limited coverage of natural user phrasings.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about mflux CLI commands, supported models, or how to generate images via the CLI.'

Broaden trigger terms with natural phrasings users actually say, such as 'generate an image', 'which model', 'image generation', and 'CLI flags'.

Keep the third-person voice but consider mentioning a representative capability (e.g. text-to-image generation) to improve trigger-term coverage without padding.

Dimension	Reasoning	Score
Specificity	The description names three concrete actions — 'Navigate MFLUX CLI capabilities', 'locate commands by area', and 'summarize supported features' — matching the anchor that lists multiple specific concrete actions. It is above level 2 because the actions are distinct and comprehensive for the skill's purpose rather than naming only a domain and a couple actions.	3 / 3
Completeness	It clearly states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2. It is above level 1 because the 'what' is explicit, and below level 3 because the 'when' is missing rather than explicit.	2 / 3
Trigger Term Quality	It includes relevant keywords ('MFLUX CLI', 'commands', 'supported features') a user might say, but lacks common natural variations like 'generate an image', 'model', or 'which model', matching 'some relevant keywords but missing common variations'. It is not level 3 because the coverage of natural user phrasings is thin.	2 / 3
Distinctiveness Conflict Risk	The MFLUX-CLI qualifier carves out a clear niche unlikely to trigger for unrelated skills, matching 'clear niche with distinct triggers; unlikely to conflict'. It is above level 2 because the domain binding is specific rather than a generic capability that could overlap others.	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-cli/SKILL.md
Commit: 4ac641e

Reviewed: 7 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.