Name: retail-virtual-tryon
Rating: 61.6 (1 reviews)
Author: google

retail-virtual-tryon

Creates virtual try-on agents supporting image and video (catwalk animation) try-ons on Google Cloud (Gemini image models and Veo on Gemini Enterprise Agent Platform). Handles resource setup, user photo uploading, image/video generation pipelines, local testing, and evaluation.

Quality

73%

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/retail/virtual-tryon/SKILL.md

Quality

Content

71%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 highly actionable with concrete, executable commands and well-sequenced workflows including validation checkpoints, but it is somewhat repetitive and inlines material that could be offloaded to its existing reference and asset files. Navigation to the bundle's reference file is not signaled from the body.

Suggestions

Reduce repetition of the `setup.py --config ./design-spec.md` command by defining it once and referencing it, to tighten the token budget.

Link to references/tryon-architecture.md and move the full Mode 1/Mode 2 question-format blocks into a reference file so SKILL.md stays an overview.

Add explicit error-recovery feedback loops (on setup/export failure: read error, fix, re-run) for the fragile provisioning and deploy steps.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of generic concept explanations, but it repeats the `setup.py --config ./design-spec.md` invocation ~6 times and re-states overlapping Mode 1/Mode 2 material, so it could be tightened rather than trimmed of only minor instances.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: exact shell commands, real Python smoke-test snippets with product IDs, gcloud deploy commands, iframe embed HTML, and a troubleshooting table with specific error patterns and fixes.	5 / 5
Workflow Clarity	Processes are clearly sequenced with ordered Execution Rules and numbered per-mode auto-execution steps, and checkpoints exist ('Verify each step succeeded', GCS sync verification, smoke tests, completion checklist); explicit per-step error-recovery feedback loops are only implied, leaving minor validation gaps.	4 / 5
Progressive Disclosure	Section structure is clear and bundle files (scripts/, references/tryon-architecture.md, assets/) are real, but the body inlines large referenceable blocks (full question tables, deploy instructions) and never links to references/tryon-architecture.md, so references are present but not clearly signaled.	3 / 5
	Total	15 / 20 Passed

Description

75%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 is specific and distinctive, naming concrete capabilities and a clear niche, but it omits an explicit 'when to use' trigger clause, which caps its completeness. Trigger-term coverage is good but lacks synonyms that users might naturally say.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when building virtual try-on / fitting rooms for e-commerce or generating catwalk-style try-on videos').

Include common synonyms users might say — 'fitting room', 'VTO', 'catwalk video' — alongside the existing terminology.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Creates virtual try-on agents', 'catwalk animation try-ons', and 'resource setup, user photo uploading, image/video generation pipelines, local testing, and evaluation' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The 'what' is clear and detailed, but there is no 'Use when...' or equivalent explicit trigger clause; per the judging guidelines a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('virtual try-on', 'catwalk animation', 'Google Cloud', 'Gemini'), but misses common synonyms/extensions like 'fitting room' or 'VTO', so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (virtual try-on with catwalk video on Google Cloud via Gemini/Veo) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: google/adk-samples
Path: skills/retail/virtual-tryon/SKILL.md
Commit: 17f314a

Reviewed: 1 day 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.