openai-image-gen

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

Quality

57%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./openclaw/skills/openai-image-gen/SKILL.md

Quality

Content

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 strong actionability with concrete, executable examples covering multiple models and configurations. However, it's somewhat verbose with inline parameter reference tables that could be extracted to a separate file, and it lacks error handling or validation guidance for common failure modes (missing API key, rate limits, invalid parameter combos). The timeout warning is a nice practical touch.

Suggestions

Move the detailed model-specific parameter tables to a separate REFERENCE.md file and link to it from the main skill, keeping only the most essential defaults inline.

Add brief error handling guidance: what to check if generation fails (API key set, valid parameter combinations, rate limits), especially since this involves external API calls.

Add a prerequisites line mentioning the OPENAI_API_KEY environment variable requirement, which is critical for execution.

Dimension	Reasoning	Score
Conciseness	The model-specific parameters section is quite detailed and reference-like, which could potentially live in a separate file or be more condensed. The core run instructions are efficient, but the extensive parameter tables add bulk that borders on documentation Claude could infer from help flags.	2 / 3
Actionability	Provides fully executable commands with concrete flags and examples covering multiple models and configurations. The usage examples are copy-paste ready with realistic prompts and flag combinations.	3 / 3
Workflow Clarity	The workflow is essentially a single command invocation, which is clear, but there's no validation or error handling guidance. The timeout warning is helpful, but there's no feedback loop for failures (e.g., API key missing, rate limits, invalid parameter combinations).	2 / 3
Progressive Disclosure	The model-specific parameters section is extensive inline content that could be split into a reference file. The structure is reasonable with clear sections, but the detailed parameter tables make the skill longer than necessary for an overview document. No bundle files are provided to offload this content.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 and identifies a clear, distinctive niche with specific capabilities (batch image generation, prompt sampling, gallery creation). However, it completely lacks a 'Use when...' clause, which is critical for Claude to know when to select this skill. It also misses common user-facing trigger terms like 'DALL-E' or 'generate pictures'.

Suggestions

Add a 'Use when...' clause, e.g., 'Use when the user wants to batch-generate images, create an image gallery, or use the OpenAI DALL-E API to produce multiple images at once.'

Include common user trigger terms such as 'DALL-E', 'image generation', 'generate pictures', 'bulk images', or 'AI-generated images' to improve discoverability.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: batch-generate images, random prompt sampling, and generating an index.html gallery. These are distinct, actionable capabilities.	3 / 3
Completeness	Describes what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'when' is entirely absent, this scores a 1.	1 / 3
Trigger Term Quality	Includes relevant terms like 'images', 'OpenAI Images API', 'gallery', and 'batch-generate', but misses common user variations like 'DALL-E', 'image generation', 'bulk images', or 'create pictures'. The term 'prompt sampler' is somewhat technical.	2 / 3
Distinctiveness Conflict Risk	The combination of batch image generation via OpenAI Images API with a random prompt sampler and HTML gallery output is a very specific niche that is unlikely to conflict with other skills.	3 / 3
	Total	9 / 12 Passed

Validation

72%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 8 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	8 / 11 Passed

Repository: trpc-group/trpc-agent-go
Commit: 43b120c

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.