fal-tryon

Virtual try-on — see how clothes look on a person via fal.ai's hosted try-on models. Useful for ecommerce, lookbooks, and styling experiments.

Quality

59%

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-tryon/SKILL.md

Quality

Content

57%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 a well-structured, concise catalogue pointer with clear navigation to the upstream bundle, but it offers little executable guidance — the actual try-on workflow is deferred entirely to an external repo with only a vague 'install' instruction.

Suggestions

Replace the vague 'install the upstream bundle' instruction with a concrete command (e.g. the exact git clone path and target skills directory).

Use a portable command instead of macOS-only `open` (e.g. `xdg-open`/a documented URL), or simply state the URL to visit.

Inline a minimal runnable example of invoking a fal.ai try-on model so the skill is actionable without leaving SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding or over-explanation of known concepts, but the 'What it does' section duplicates the frontmatter description verbatim, a minor trim opportunity that keeps it just below a 5.	4 / 5
Actionability	Guidance is high-level ('install the upstream bundle into your active agent's skills directory') with no concrete install command, and the only command (`open https://...`) just opens a URL rather than executing the try-on task — matching the 'minimal concrete guidance; missing specific steps' anchor.	2 / 5
Workflow Clarity	A recognizable three-step sequence is present (install bundle → inspect upstream README → invoke by name/triggers), but steps are vaguely defined with no checkpoints; the destructive/batch validation cap does not apply since this is a non-destructive pointer skill.	3 / 5
Progressive Disclosure	This under-50-line skill is cleanly sectioned (What it does / Source / How to use) and points to a single, well-signaled, one-level-deep upstream reference with no nesting or buried refs, fitting the simple-skill exception for a 5.	5 / 5
	Total	14 / 20 Passed

Description

61%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 clearly conveys a distinct niche and concrete primary action with decent natural keywords, but it lacks an explicit 'Use when...' trigger clause and only names a single concrete action, capping completeness and specificity.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to preview garments on a person, build a lookbook, or stage ecommerce/styling visuals.'

Expand the action list beyond the single 'see how clothes look on a person' to name 1-2 more concrete operations (e.g. swap garments, generate on-model product shots).

Include common phrasings users actually say (e.g. 'try on clothes', 'virtual fitting') directly in the description text.

Dimension	Reasoning	Score
Specificity	Names the domain ('Virtual try-on') and one concrete action ('see how clothes look on a person via fal.ai's hosted try-on models') but lists no further specific actions, matching the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action anchor 4.	3 / 5
Completeness	Has a clear 'what' but the 'when' is only weakly present as use-case framing ('Useful for ecommerce, lookbooks, and styling experiments') rather than an explicit 'Use when...' trigger clause, which the guidelines cap at 3.	3 / 5
Trigger Term Quality	Includes natural terms users would say — 'virtual try-on', 'ecommerce', 'lookbooks', 'styling experiments' — giving good keyword coverage; not a 5 because common variations like the exact phrase 'try on clothes' and synonyms are absent from the description itself.	4 / 5
Distinctiveness Conflict Risk	'Virtual try-on' via fal.ai is a clear, distinct niche with low conflict risk; not a 5 because 'ecommerce styling' could overlap marginally with broader image/styling skills.	4 / 5
	Total	14 / 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-tryon/SKILL.md
Commit: 1a7a23d

Reviewed: about 4 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.