comfyui

Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.

Quality

83%

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

Quality

Content

85%

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

A highly actionable, well-structured skill body with concrete commands, clear sequenced workflows, and strong progressive disclosure into real reference files. The main weakness is length and some command repetition that could be tightened for token efficiency.

Suggestions

Consolidate the repeated comfy-cli install/launch commands so each appears in one canonical place and other sections cross-reference it, reducing length and duplication.

Resolve the missing workflows/ directory referenced in the example-workflows section so the navigation it promises is real.

Dimension	Reasoning	Score
Conciseness	The body is dense and table/decision-tree driven with almost no padding about concepts Claude already knows, but at ~613 lines it repeats commands across the Quick Start, Decision Tree, Path D, and Post-Install sections and could be tightened, matching the 'mostly efficient but could be tightened' anchor at 2 rather than the lean anchor at 3.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands such as 'python3 scripts/run_workflow.py --workflow ... --args ...', exact curl examples, and concrete flags, matching the 'fully executable, copy-paste ready' anchor at 3.	3 / 3
Workflow Clarity	Core Workflow is explicitly sequenced (Steps 1-4) with validation checkpoints (health_check.py, check_deps.py is_ready, smoke test) and feedback loops (auto_fix_deps runs check then fixes; re-export on editor format), and a verification checklist covers batch/destructive operations, matching the clear-sequence-with-validation anchor at 3.	3 / 3
Progressive Disclosure	A clear 'What's in this skill' overview signals four one-level-deep reference files (all present in references/) and a scripts table, with content appropriately split out; the only minor gap is the referenced workflows/ directory being absent, which does not undermine the well-organized structure.	3 / 3
	Total	11 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description that concretely names the skill's actions and distinct ComfyUI niche. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which limits the completeness score.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to generate images/video/audio with ComfyUI, run or inspect a ComfyUI workflow, or manage ComfyUI nodes and models.'

Include common model-name triggers users say (Stable Diffusion, SDXL, Flux, SD3) to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the lifecycle and execution domains: 'install, launch, manage nodes/models, run workflows with parameter injection' alongside 'Generate images, video, and audio', matching the comprehensive-actions anchor rather than the partial-actions anchor at 2.	3 / 3
Completeness	It strongly answers 'what' but has no explicit 'Use when...' clause or equivalent trigger guidance, so per the guideline a missing explicit trigger caps completeness at 2; it cannot reach the 3 anchor that requires both explicit what AND when.	2 / 3
Trigger Term Quality	Includes natural user-facing terms like 'Generate images, video, and audio', 'ComfyUI', and 'workflows' that a user would plausibly say; coverage is good though it omits some model-name variations (Stable Diffusion, SDXL, Flux), keeping it solidly at 3 rather than below.	3 / 3
Distinctiveness Conflict Risk	'with ComfyUI' plus comfy-cli/REST/WebSocket execution carve a clear niche unlikely to trigger for unrelated skills, matching the distinct-triggers anchor at 3 rather than the overlap-prone anchors below.	3 / 3
	Total	11 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (613 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/creative/comfyui/SKILL.md
Commit: 5be99b6

Reviewed: about 14 hours 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.