CtrlK
BlogDocsLog inGet started
Tessl Logo

gpt-image-1-5

Generate and edit images using OpenAI's GPT Image 1.5 model. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports text-to-image generation and image editing with optional mask. DO NOT read the image file first - use this skill directly with the --input-image parameter.

90

2.29x
Quality

88%

Does it follow best practices?

Impact

94%

2.29x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is gpt-image-1-5 in intellectronica/agent-skills

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, highly actionable skill body with executable commands and clear sectioning. Its main weaknesses are minor repetition between usage and examples sections and the absence of an explicit error-recovery/feedback loop in the editing workflow.

Suggestions

De-duplicate the Usage and Examples command blocks: keep the parameter syntax in Usage and move only distinct worked scenarios into Examples to trim tokens.

Add a short validation/recovery step to the editing workflow (e.g., 'If the edit fails or output looks wrong, check the mask alpha and retry with --quality high') to strengthen the feedback loop.

Consider tightening the quality/size mapping lists into a compact table to reduce vertical padding.

DimensionReasoningScore

Conciseness

Mostly lean with no concept-explaining fluff, but the usage and examples sections repeat near-identical invocations and the quality/size mapping lists are slightly padded; a few sentences could be trimmed.

4 / 5

Actionability

Fully executable, copy-paste-ready commands with absolute paths, concrete flag syntax, a precise filename pattern, and worked examples covering generation, transparent backgrounds, and both editing modes.

5 / 5

Workflow Clarity

Editing workflows are clearly sequenced with numbered steps for the without-mask and with-mask cases, and the API-key fallback is an explicit checkpoint, but there is no error-recovery feedback loop beyond 'script exits with an error message'.

4 / 5

Progressive Disclosure

A single well-organized SKILL.md under ~140 lines with no need for external reference files; the simple-skill exception applies and section headers (Usage, Parameters, Filename Generation, Output, Examples) make navigation easy.

5 / 5

Total

18

/

20

Passed

Description

91%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, specific description with clear 'what' and explicit 'when' trigger guidance and rich natural-language synonyms. The only minor gap is that some editing capabilities (inpainting, background changes) are shown via examples rather than enumerated as named actions.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Generate and edit images', 'text-to-image generation and image editing with optional mask'), but coverage is not exhaustive (e.g., inpainting/background changes described only via examples rather than named actions).

4 / 5

Completeness

Explicitly answers both 'what' (image generation/editing via GPT Image 1.5, text-to-image, mask-based editing) and 'when' with concrete 'Use when...' trigger clauses for both generation and modification of existing files.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage with synonyms ('generate, create, edit, modify, change, alter, or update images') plus example user phrases ('modify this image', 'change the background', 'replace X with Y') that map closely to what users actually say.

5 / 5

Distinctiveness Conflict Risk

Anchored to a specific model name ('GPT Image 1.5') with a clear image-gen/edit niche and concrete triggers, leaving only minor overlap risk with other image-handling skills.

4 / 5

Total

18

/

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
intellectronica/agent-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.