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.
Install with Tessl CLI
npx tessl i github:intellectronica/agent-skills --skill gpt-image-1-586
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillAgent success when using this skill
Validation for skill structure
Discovery
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.
This is an excellent skill description that hits all the marks. It provides specific capabilities, comprehensive trigger terms covering multiple natural phrasings users would employ, explicit 'Use when' guidance, and clear distinctiveness through model specification and use case examples. The inclusion of operational guidance ('DO NOT read the image file first') adds practical value.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Generate and edit images', 'text-to-image generation', 'image editing with optional mask'. Also specifies the model used (GPT Image 1.5) and includes technical guidance about the --input-image parameter. | 3 / 3 |
Completeness | Clearly answers both what ('Generate and edit images using OpenAI's GPT Image 1.5 model') and when ('Use when the user asks to generate, create, edit...'). Includes explicit 'Use when' clause with comprehensive trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'generate', 'create', 'edit', 'modify', 'change', 'alter', 'update images', 'change the background', 'replace X with Y'. Includes both action verbs and example phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche around image generation/editing. Specifies the exact model (GPT Image 1.5), distinguishes between text-to-image and image editing, and provides specific use cases that wouldn't overlap with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid, actionable guidance for image generation and editing with clear executable examples. However, it's somewhat verbose with parameter mappings Claude could infer, and lacks validation/error handling guidance for a workflow that involves external API calls and file operations. The structure is adequate but could benefit from better progressive disclosure.
Suggestions
Add error handling guidance: what to do if API key is invalid, if input image format is unsupported, or if the script fails
Condense parameter mapping tables - Claude can infer that 'portrait' means portrait format without explicit mapping
Add a validation step to verify the output image was created successfully before informing the user
Consider moving detailed filename generation rules and parameter tables to a separate reference file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary verbosity, such as the detailed parameter mapping tables (Claude can infer 'portrait' -> portrait format) and the extensive filename generation examples that could be condensed. | 2 / 3 |
Actionability | Provides fully executable bash commands with all parameters clearly documented. Examples are copy-paste ready with realistic values and cover all major use cases (generation, editing with/without mask). | 3 / 3 |
Workflow Clarity | The editing workflows are clear but lack validation checkpoints. There's no guidance on what to do if the script fails, how to verify the output is correct, or error recovery steps for common issues like invalid API keys or unsupported image formats. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but everything is in one file when some content (like the detailed parameter mapping tables or filename generation rules) could be referenced separately. The skill is somewhat long for a single-file approach. | 2 / 3 |
Total | 9 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.