fal-3d

Generate 3D models from text or images via fal.ai. Useful for game assets, AR previews, product mockups, and concept sculpting.

Quality

61%

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 ./skills/fal-3d/SKILL.md

Quality

Content

53%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 lean, well-organized catalogue entry that clearly signals it defers to an upstream bundle for the real workflow. Its main weakness is actionability: it offers a URL to open and high-level install/invoke hints rather than concrete, executable steps for actually generating 3D models.

Suggestions

Replace the `open <url>` pointer with the concrete install command (e.g., the git clone / copy step into the agent's skills directory) and a minimal fal.ai API call example so the body is executable without leaving the skill.

Make the workflow explicit and verifiable: number the steps (install bundle -> confirm the skill is registered -> invoke `fal-3d` or a trigger phrase) and add a quick check that the skill is discoverable before invoking.

Drop the verbatim repeat of the frontmatter description in 'What it does' or replace it with content that adds value over the frontmatter.

Dimension	Reasoning	Score
Conciseness	The body is short and avoids explaining concepts Claude already knows, but the 'What it does' section repeats the frontmatter description verbatim and there is light meta-framing ('This catalogue entry advertises the skill in Open Design...'), so it is efficient with minor trimmable redundancy rather than perfectly lean.	4 / 5
Actionability	The only concrete command is `open https://github.com/fal-ai-community/skills`, which just opens a browser; the actual task workflow ('install the upstream bundle', 'invoke by name') is given as high-level hints with no executable steps or code for 3D generation, matching 'minimal concrete guidance; missing the specific steps to execute'.	2 / 5
Workflow Clarity	A rough sequence is present (inspect upstream README -> install upstream bundle -> invoke by name/trigger), but the install step is unspecified (no concrete command) and there are no checkpoints; the underspecified middle step keeps it at 'sequence present but gaps' rather than a clean simple-skill 5.	3 / 5
Progressive Disclosure	No bundle files exist, but the body is well-sectioned (What it does / Source / How to use) and points to one clearly-signaled external reference (the upstream repo) for the full assets/scripts/references; it is not a 5 because the reference is a 'inspect the README for exact paths' pointer rather than clean one-level-deep file navigation.	4 / 5
	Total	13 / 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.

A clear, mostly well-targeted description that states the capability and gives use-case-based when-guidance without fluff. It is held back from the top band by listing use cases rather than several distinct concrete actions and by lacking an explicit 'Use when...' trigger clause.

Suggestions

Replace 'Useful for ...' with an explicit trigger clause such as 'Use when the user asks to create 3D models from text or images, or mentions game assets, AR previews, product mockups, or concept sculpting.'

Add concrete actions beyond 'generate' (e.g., exports .glb/.obj meshes, applies textures, optimizes topology) and relevant file extensions/synonyms to raise specificity and trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action ('Generate 3D models from text or images via fal.ai') but then lists use cases ('game assets, AR previews, product mockups, and concept sculpting') rather than additional distinct actions, so it lands at 'domain + 1-2 actions' rather than 'several specific actions'.	3 / 5
Completeness	It clearly states what ('Generate 3D models from text or images via fal.ai') and gives when-guidance via 'Useful for game assets, AR previews...'; the 'when' is present but not phrased as an explicit 'Use when the user mentions...' clause, so it is not a 5.	4 / 5
Trigger Term Quality	Natural keywords a user would say are well covered ('3D models', 'text or images', 'game assets', 'AR previews', 'product mockups', 'concept sculpting'), but synonyms and file extensions (e.g., .glb, .obj, mesh) are missing, stopping short of comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The 3D-generation-via-fal.ai niche is distinct with specific triggers, but 'game assets' and 'AR previews' could overlap with a general game-asset or AR skill, so it is 'mostly distinct; minor overlap risk' rather than minimal conflict.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/fal-3d/SKILL.md
Commit: 1a7a23d

Reviewed: about 5 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.