CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ecommerce-image-workflow

Reference-product ecommerce image workflow for generating a compact set of product-faithful main, feature, and lifestyle images from real product reference photos. V1 requires uploaded product imagery and intentionally defers brief-only concept generation and platform-specific batch exports.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ecommerce-image-workflow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 strongly actionable, well-sequenced workflow with real validation checkpoints (Step 0 gate, script error handling, pre-handoff checklist) and an appropriately split checklist reference. Its main defects are localized redundancy in the Hard rules section and a resource map that advertises a nonexistent example.html file.

Suggestions

Fix the resource map: either add example.html to the bundle or remove it from the tree (and update the frontmatter preview entry), since the file it lists does not exist.

Deduplicate the Hard rules section against the intro and step bodies (e.g., the V1 reference-only and media-dispatcher rules each appear twice) to save tokens.

Include one fully assembled example slot prompt (fidelity lock + slot instructions) and briefly note the source of the OD_NODE_BIN/OD_BIN/imageModel variables to make dispatch copy-paste ready.

DimensionReasoningScore

Conciseness

The bash dispatch script, slot table, and manifest example all earn their place, but the "Hard rules" section restates the intro and step content (V1 reference-only rule, media dispatcher rule, manifest rule), and the 35-line JSON manifest example could be trimmed to essentials.

4 / 5

Actionability

Concrete and mostly executable: exact fidelity-lock prompt text, a full generate/wait bash script with exit-code handling, exact stop-reply text, and a complete manifest JSON example. Minor gaps: OD_*/imageModel variables are unexplained, and slot prompts are bullet guidance rather than one fully assembled example prompt.

4 / 5

Workflow Clarity

Steps 0-7 are clearly sequenced with explicit validation checkpoints: a Step 0 reference-image gate with an exact stop reply, exit-code and retry handling in the dispatch loop, a stop-and-inform path when --image is unsupported, a manifest honesty rule, and a mandatory references/checklist.md pass before handoff — a feedback loop appropriate for this batch operation.

5 / 5

Progressive Disclosure

Good structure with a resource map and a clearly signaled, verified one-level-deep reference (references/checklist.md, which exists). However, the resource map lists example.html, which is absent from the actual bundle — a dangling navigation pointer that also backs the frontmatter preview entry.

4 / 5

Total

17

/

20

Passed

Description

66%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 states a clear, concrete capability with honest V1 scope boundaries, but omits any explicit "Use when..." trigger guidance, which both caps completeness and leaves natural trigger phrases out of the description itself. Distinctiveness is good thanks to the reference-product constraint.

Suggestions

Add an explicit trigger clause to the description, e.g. "Use when the user provides product reference photos and needs a marketplace image set (main, feature, lifestyle)."

Work one or two natural trigger phrases into the description (e.g. "ecommerce product images", "packshot", "product photography") so it matches how users actually phrase the request.

DimensionReasoningScore

Specificity

Concrete deliverables are named ("main, feature, and lifestyle images from real product reference photos") plus explicit scope limits ("V1 requires uploaded product imagery and intentionally defers brief-only concept generation"), but coverage is not comprehensive (manifest/gallery artifacts unmentioned).

4 / 5

Completeness

The "what" is clear (generating a product-faithful ecommerce image set from reference photos), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Natural phrases users would say appear ("ecommerce image", "main, feature, and lifestyle images", "product reference photos"), but common variations like "packshot", "product photography", or "listing photos" are missing.

4 / 5

Distinctiveness Conflict Risk

"Reference-product ecommerce image workflow" with the reference-photo requirement is a well-bounded niche with only minor overlap risk against generic product-photography or image-generation skills.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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/ecommerce-image-workflow/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.