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

64%

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

72%

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 concise, well-organized catalogue/pointer entry that routes the agent to the upstream bundle, but it provides no executable try-on code or concrete install workflow, capping actionability and workflow clarity at 2.

Suggestions

Add a concrete, runnable install snippet (e.g., the exact git clone / copy command and target skills-directory path) instead of directing the user to 'inspect the upstream README for exact paths'.

Include at least one executable example of invoking a fal.ai try-on model (API call or CLI command) so the skill is actionable on its own.

Make the workflow explicit with sequenced steps and a verification checkpoint (e.g., confirm the skill appears in the agent's skill list before invoking by name).

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and contains no padding or explanations of concepts Claude already knows; every line earns its place.	3 / 3
Actionability	It offers a concrete command ('open https://github.com/fal-ai-community/skills') and a clear invocation instruction, but no executable code that actually performs the try-on and no copy-paste runnable workflow, leaving guidance incomplete.	2 / 3
Workflow Clarity	The sequence ('install the upstream bundle... then ask the agent to invoke') is present but vague — there is no concrete install path or command, only 'inspect the upstream README for exact paths' — so the single action is ambiguous and checkpoints are implicit.	2 / 3
Progressive Disclosure	No bundle files exist and the body points one level out to a single external upstream URL rather than nesting local references; the short sections are well organized, which earns 3 for a sub-50-line skill needing no external refs.	3 / 3
	Total	10 / 12 Passed

Description

57%

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 (virtual try-on via fal.ai) but gives only one concrete action and lacks an explicit 'Use when...' trigger clause, leaving it at the mid-level for specificity, trigger quality, and completeness.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user wants to virtually try on clothes, preview outfits on a person, or build ecommerce lookbooks and styling mockups').

Enumerate multiple concrete actions the skill performs (e.g., 'composite a garment onto a person photo, swap outfits, generate lookbook variants') to lift specificity from 2 to 3.

Expand trigger-term coverage with common user phrasings such as 'try on clothes', 'outfit preview', 'virtual fitting room', and 'garment mockup'.

Dimension	Reasoning	Score
Specificity	It names the domain ('virtual try-on') and a concrete action ('see how clothes look on a person via fal.ai's hosted try-on models'), but offers only a single action rather than the multiple specific concrete actions required for a 3.	2 / 3
Completeness	The 'what' is clear, but 'when' is only implied via 'Useful for ecommerce, lookbooks, and styling experiments'; the missing explicit trigger guidance caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Natural terms like 'virtual try-on', 'lookbooks', and 'ecommerce styling' appear, but there is no explicit 'Use when...' clause and common phrasing variations are missing, so it stops at 2 rather than 3.	2 / 3
Distinctiveness Conflict Risk	'Virtual try-on' scoped to 'fal.ai's hosted try-on models' is a clear niche with distinct triggers that is unlikely to conflict with other skills.	3 / 3
	Total	9 / 12 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: f2760fd

Reviewed: about 15 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.