openai-image-gen
Generate images using OpenAI's DALL-E 3 API. Use when needing to create graphics, icons, backgrounds, or any visual assets. Requires OPENAI_API_KEY in environment.
81
71%
Does it follow best practices?
Impact
97%
3.46xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xbigboss/claude-code/openai-image-gen/SKILL.mdQuality
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 a strong, well-crafted description that concisely covers what the skill does (generates images via DALL-E 3), when to use it (creating graphics, icons, backgrounds, visual assets), and includes practical details (API key requirement). It uses third person voice correctly and includes natural trigger terms that users would employ when requesting image generation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'generate images', 'create graphics, icons, backgrounds, or any visual assets'. Also specifies the tool (DALL-E 3 API) and a prerequisite (OPENAI_API_KEY). | 3 / 3 |
Completeness | Clearly answers both 'what' (generate images using DALL-E 3 API) and 'when' ('Use when needing to create graphics, icons, backgrounds, or any visual assets') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'images', 'graphics', 'icons', 'backgrounds', 'visual assets', 'DALL-E'. These cover common variations of image generation requests. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to image generation via DALL-E 3 specifically, which is a distinct niche. The mention of OpenAI's DALL-E 3 API and specific visual asset types makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides clear, executable commands for DALL-E 3 image generation, but is severely bloated by project-specific Gothic Cathedral presets that dominate the document and are irrelevant to the general skill. The core functionality (4 parameters to a shell script) is simple and well-documented, but the lack of content separation and the inclusion of site-specific prompts inline significantly reduce its quality as a reusable skill.
Suggestions
Move all Gothic Cathedral presets to a separate file (e.g., GOTHIC-PRESETS.md) and reference it from the main skill with a single link, keeping SKILL.md focused on the general image generation workflow.
Add a verification step after generation, such as checking file existence and size (e.g., `ls -la output.png` or checking the script's exit code).
Remove or relocate the cost reference with specific 2024 dates to avoid time-sensitive information in the main body.
Trim the Tips section—Claude already knows prompt engineering basics; focus only on DALL-E 3-specific quirks.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is heavily bloated with site-specific preset prompts (Gothic Cathedral Presets) that are not generalizable and consume the majority of the document. The core skill (calling a shell script with 4 parameters) could be conveyed in ~20 lines. The presets are essentially copy-paste prompt strings for one specific website, wasting significant token budget. | 1 / 3 |
Actionability | All commands are fully executable, copy-paste ready bash invocations with concrete file paths, specific prompts, and explicit parameter values. The parameter table is clear and complete. | 3 / 3 |
Workflow Clarity | This is essentially a single-step task (run a script), so complex workflow isn't needed. However, there's no validation step—no mention of checking if the image was actually saved, verifying file size, or handling API errors beyond basic troubleshooting. For a skill that costs money per invocation, a verification step would be valuable. | 2 / 3 |
Progressive Disclosure | All content is in a single monolithic file. The Gothic Cathedral presets (which are project-specific) should be in a separate reference file. The batch script is referenced but no bundle files are provided. The core skill is buried under pages of preset prompts. | 1 / 3 |
Total | 7 / 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.
- Repository
- NeverSight/skills_feed
- Commit
aa009ea
- 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.