modly-cli

Use when an agent needs to call a running Modly desktop instance from the terminal to generate/export image-to-3D assets through canonical JSON-first automation commands.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%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.

A well-structured, highly actionable CLI reference with concrete commands, expected JSON output, and a verification checklist. It is slightly held back by inlined auxiliary sections that could live in separate reference files and by a missing batch feedback loop.

Suggestions

Move the Legacy Compatibility, Experimental ComfyUI, and Developer-Only API helpers into one-level-deep reference files (e.g. LEGACY.md, EXPERIMENTAL.md) and link to them from SKILL.md to improve progressive disclosure.

Add an explicit validate/fix/retry feedback loop for the batch workflow (e.g. inspect failures from the run, re-run only failed entries) since batch is a risky multi-item operation.

Tighten the experimental prose describing fallback behavior into a short bullet list to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands and JSON examples and no padding about concepts Claude already knows, though the experimental/legacy/dev sections contain prose that could be trimmed slightly.	4 / 5
Actionability	Copy-paste-ready commands cover the common cases (health, model, workflow-run, generate, batch, legacy) and concrete JSON output shapes are shown, making guidance fully executable.	5 / 5
Workflow Clarity	A clear prerequisite-to-generate sequence exists with a verification checklist providing checkpoints, but the batch path lacks an explicit validate/fix/retry feedback loop.	4 / 5
Progressive Disclosure	Section headers give decent structure, but all content (legacy, experimental, dev, batch) is inlined in a ~180-line single file with no one-level-deep reference files, so material that could be split remains inline.	3 / 5
	Total	16 / 20 Passed

Description

87%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.

A strong, third-person description with an explicit 'Use when' trigger that clearly states both purpose and invocation context. It is specific and distinctive; its only weakness is missing common synonyms and 3D file extensions in the trigger terms.

Suggestions

Add concrete 3D output file extensions users might name (e.g. '.glb', '.gltf', '.obj') to broaden natural trigger coverage.

Consider adding a synonym like 'mesh' or '3D model' alongside 'image-to-3D assets' to match varied user phrasing.

Dimension	Reasoning	Score
Specificity	Names the domain (Modly, image-to-3D) and several concrete actions ('call a running Modly desktop instance from the terminal', 'generate/export image-to-3D assets', 'JSON-first automation commands'), with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what (call a running Modly instance from the terminal to generate/export image-to-3D assets via JSON-first automation commands) and when ('Use when an agent needs to call...'), using third person voice.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('generate/export image-to-3D assets', 'from the terminal') plus 'Modly', but is missing common synonyms and file extensions like .glb/.gltf that users might mention.	4 / 5
Distinctiveness Conflict Risk	The 'Modly desktop instance' and 'image-to-3D assets' niche is highly specific with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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	13 / 16 Passed

Repository: lightningpixel/modly
Path: tools/modly-cli/SKILL.md
Commit: 3ae371c

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.