CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sirv-ai-studio

Guide for using Sirv AI Studio (www.sirv.studio), an AI-powered image and video processing platform. Use when working with Sirv AI Studio, product photography or product images, background removal, image upscaling, AI image or video generation, lifestyle scenes, virtual try-on, alt text generation, 3D model generation, batch image processing, e-commerce image workflows, or marketplace optimization. IMPORTANT - If sirv-ai MCP tools are available (sirv_remove_background, sirv_upscale, sirv_generate, etc.), USE THEM directly for image processing tasks instead of telling user to visit the website.

69

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 overview body: executable MCP guidance with a copy-paste install snippet, a clear workflow with pre- and post-batch validation, and excellent reference routing. Minor deductions for repeated check-credits guidance and the absence of an explicit error-recovery loop.

Suggestions

State the check-credits-before-batch guidance once (keep it in Best Practices or Red Flags) and drop the duplicate mentions to save tokens.

Add a short error-recovery loop to the Workflow/Verification section, e.g., what to do when a batch job runs out of credits mid-run or representative outputs fail inspection (retry with a cheaper model, resume the batch, re-prompt).

DimensionReasoningScore

Conciseness

The body is mostly lean — a compact MCP tool table, terse Workflow/Red Flags sections — but the check-credits-before-batch guidance is stated three times (Workflow step 3, Best Practices #1, Red Flags #2), and the MCP-tools-first emphasis repeats what the description already says.

4 / 5

Actionability

Guidance is fully executable: a tool table with exact MCP tool names and key parameters, a copy-paste-ready .mcp.json install snippet, concrete per-tool chaining guidance ("Remove BG → Upscale → Lifestyle → Alt Text"), and specific verification checks.

5 / 5

Workflow Clarity

The 7-step Workflow is clearly sequenced with validation checkpoints (step 3 credit check before batch jobs, step 7 verification, plus a dedicated Verification checklist), so the batch-operation cap does not apply; however, no explicit error-recovery loop (what to do when verification fails) is stated.

4 / 5

Progressive Disclosure

The body is a clear ~98-line overview with a dedicated "When to Read References" section pointing to four real, one-level-deep reference files (mcp-tools.md, asset-product-tools.md, rest-api.md, platform.md — all verified present), plus well-signaled cross-links to sibling skills.

5 / 5

Total

18

/

20

Passed

Description

83%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 description: concrete capabilities, natural and extensive trigger terms, and an explicit use-when clause. The only weakness is that a few trigger terms are generic image operations not anchored to the product/e-commerce context.

Suggestions

Anchor generic operation triggers to the e-commerce context (e.g., "product image background removal" instead of bare "background removal") to reduce overlap with general image-editing skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "background removal, image upscaling, AI image or video generation, lifestyle scenes, virtual try-on, alt text generation, 3D model generation, batch image processing" — giving comprehensive coverage of the skill's operations rather than vague domain framing.

5 / 5

Completeness

It explicitly answers both what ("an AI-powered image and video processing platform" with named operations) and when ("Use when working with Sirv AI Studio, product photography..., background removal, ..."), with concrete trigger phrases.

5 / 5

Trigger Term Quality

Trigger phrases are natural things users would say: "product photography or product images", "background removal", "image upscaling", "virtual try-on", "batch image processing", "e-commerce image workflows", "marketplace optimization", plus the brand term "Sirv AI Studio".

5 / 5

Distinctiveness Conflict Risk

The Sirv-branded, e-commerce-image niche is mostly distinct, but generic operation triggers like "background removal" and "image upscaling" could also fire for a user wanting a general image-editing skill, creating minor overlap risk.

4 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

IgorVaryvoda/image-optimization-skill

Path

skills/sirv-ai-studio/SKILL.md

Reviewed

Table of Contents

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.