cli-anything-comfyui

Command-line interface for ComfyUI - AI image generation workflow management via ComfyUI REST API. Designed for AI agents and power users who need to queue workflows, manage models, download generated images, and monitor the generation queue without a GUI.

Quality

69%

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 ./comfyui/agent-harness/cli_anything/comfyui/skills/SKILL.md

Quality

Content

68%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 highly actionable — every command group comes with concrete, copy-paste-ready examples and sensible agent-specific guidance — but it is held back by redundant example repetition and by the absence of validation steps around batch/destructive operations like download-all and queue clear. Tightening the duplicated examples and adding a verify step for batch operations would lift both weak dimensions.

Suggestions

Remove the duplicated opening description and consolidate the repeated example commands (e.g., show 'system stats' and 'models loras' once) to cut noticeable token redundancy.

Add explicit validation around batch/destructive operations, e.g., 'After images download-all, verify the file count matches images list output for that prompt-id' and a confirmation check before 'queue clear'.

Make the 'More Information' references concrete and linkable (path to README.md/TEST.md in the bundle, or remove them if the files aren't shipped with the skill).

Dimension	Reasoning	Score
Conciseness	The body repeats the frontmatter description verbatim in the opening paragraph, and the same commands appear multiple times across sections ("cli-anything-comfyui system stats" appears in Basic Commands, Examples, and Output Formats), so it is mostly efficient but includes unnecessary repetition that could be tightened — matching the 3 anchor rather than the 4 anchor's 'minor instances'.	3 / 5
Actionability	Commands are fully executable and copy-paste ready with realistic flags and values ("queue prompt --workflow my_workflow.json", "images download --filename ComfyUI_00001_.png --output ./out.png", "download-all --prompt-id <id> --output-dir ./outputs"), and the examples cover the common cases (system checks, model discovery, queue and monitor, image download).	5 / 5
Workflow Clarity	The 'For AI Agents' section provides a useful ordered checklist including a pre-flight check ("Verify ComfyUI is running with system stats before other commands"), but batch and destructive operations ("images download-all", "queue clear") are presented with no validation or verification steps, which per the judging guidelines caps workflow clarity at 3.	3 / 5
Progressive Disclosure	The single SKILL.md is well-organized into clear sections (Usage, Command Groups, Examples, Output Formats, For AI Agents), and no bundle files exist so nothing needs splitting; however, the 'More Information' pointers ('See README.md in the package', 'HARNESS.md in the cli-anything-plugin') are vague and non-clickable, matching the 4 anchor's 'references mostly clear; minor organization gaps' rather than the well-signaled references of a 5.	4 / 5
	Total	15 / 20 Passed

Description

70%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 and distinct, naming a clear niche (ComfyUI REST API management) and several concrete actions, but it lacks an explicit 'Use when...' trigger clause, which both caps completeness and slightly weakens its discoverability. Adding trigger guidance (e.g., 'Use when the user mentions ComfyUI, generating images, or managing generation queues') would raise it substantially.

Suggestions

Add an explicit trigger clause such as 'Use when the user mentions ComfyUI, Stable Diffusion image generation, or needs to manage generation workflows/queues programmatically.'

Include natural synonyms and specifics users would actually say, e.g., 'checkpoints', 'LoRA', 'Stable Diffusion', alongside 'models'.

Optionally mention remaining capability areas (system stats, execution history, workflow validation) to close the minor coverage gaps in the action list.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("queue workflows, manage models, download generated images, and monitor the generation queue") but omits other capabilities it covers (system stats, execution history, workflow validation), so it fits 'several specific actions; minor gaps' rather than the comprehensive coverage of a 5.	4 / 5
Completeness	The 'what' is clear (CLI for ComfyUI image generation workflow management), but there is no 'Use when...' clause or equivalent trigger guidance; the 'when' is only weakly implied by "Designed for AI agents and power users who need to...", which per the judging guidelines caps completeness at 3 rather than 4.	3 / 5
Trigger Term Quality	Includes natural terms users would say ("ComfyUI", "AI image generation", "workflow", "models", "images") with good coverage, but misses common synonyms and specifics like Stable Diffusion, checkpoints, or LoRA, fitting 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	"ComfyUI" and "ComfyUI REST API" name a specific application twice, giving a clear niche with distinct triggers and minimal conflict risk with other skills; it does not fall to 4 because there is no meaningful overlap with closely related skills.	5 / 5
	Total	16 / 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: HKUDS/CLI-Anything
Path: comfyui/agent-harness/cli_anything/comfyui/skills/SKILL.md
Commit: 34f5195

Reviewed: 1 day 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.