CtrlK
BlogDocsLog inGet started
Tessl Logo

imagegen

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

67

2.16x
Quality

92%

Does it follow best practices?

Impact

65%

2.16x

Average score across 11 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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, actionable skill reference with a clear sequenced workflow, validation/iteration checkpoints, and clean one-level-deep reference navigation. Its main weakness is conciseness: some inline sections duplicate the bundled reference files.

Suggestions

Move the "Prompting best practices (short list)" into references/prompting.md and keep only a one-line pointer, since that file already covers prompting principles.

Relocate the two worked "Examples" to references/sample-prompts.md (which already holds copy/paste recipes) and reference them inline instead of duplicating.

Condense the inline "Use-case taxonomy" to the slug list alone and move the per-slug descriptions into references/sample-prompts.md, retaining only the slugs needed for classification.

DimensionReasoningScore

Conciseness

The body is operational and free of basic-concept padding, but inline material such as the 13-bullet "Prompting best practices" list and the two worked examples duplicate content already in references/prompting.md and references/sample-prompts.md and could be tightened.

2 / 3

Actionability

Provides copy-paste-ready install commands ("uv pip install openai pillow"), a concrete CLI path (scripts/image_gen.py), a fill-in prompt template, an explicit decision tree, and taxonomy slugs — fully actionable guidance rather than vague direction.

3 / 3

Workflow Clarity

The 8-step workflow is clearly sequenced with an explicit validation checkpoint (step 6: inspect and validate subject, style, composition, text accuracy, invariants) and a single-change iterate/re-run feedback loop (step 7), satisfying the rubric for batch/edit operations.

3 / 3

Progressive Disclosure

A clear overview body points to five well-signaled, one-level-deep reference files via a dedicated "Reference map" plus inline pointers; all referenced paths are real files and none nest beyond one level.

3 / 3

Total

11

/

12

Passed

Description

100%

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 concise yet comprehensive: it names the API, lists concrete generation/edit actions, gives an explicit "Use when" trigger, and mentions the required API key. It reads naturally and would reliably fire for the right requests.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants" — matching the anchor for listing several specific actions.

3 / 3

Completeness

Explicitly answers both: what (generate/edit via the OpenAI Image API, run the bundled CLI, require OPENAI_API_KEY) and when ("Use when the user asks to generate or edit images...").

3 / 3

Trigger Term Quality

Natural phrasing a user would say ("generate or edit images", "background removal or replacement", "transparent background", "product shots", "concept art", "batch variants") gives good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Scoped to the OpenAI Image API with a named bundled CLI and image-specific triggers, giving it a clear niche unlikely to collide with other skills.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
foryourhealth111-pixel/Vibe-Skills
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.