CtrlK
BlogDocsLog inGet started
Tessl Logo

openai-image-gen

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

57

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/openai-image-gen/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%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.

The body is highly actionable with executable commands for every model family and is concisely organized into clear sections, but the batch-generation workflow lacks an explicit validation/verification step and the model-parameter detail is somewhat inlined rather than progressively disclosed.

Suggestions

Add an explicit verification step after generation, e.g. 'Check prompts.json to confirm each prompt has a corresponding image file before opening the gallery.'

Move the per-model size/quality parameter tables into a references file (e.g. PARAMETERS.md) and link to it, keeping only the defaults and the most common example inline.

Trim the 'not yet implemented in this script' note unless it is actionable, since it describes absence rather than guidance.

DimensionReasoningScore

Conciseness

Largely efficient with well-organized sections and example commands that earn their tokens; the only padding is the explanatory parentheticals on size/quality defaults and the unimplemented-parameter note, which could be trimmed.

4 / 5

Actionability

Provides fully executable, copy-paste-ready commands across GPT image models, DALL-E 3, and DALL-E 2 with concrete flags (--count, --size, --quality, --output-format) covering the common cases.

5 / 5

Workflow Clarity

The run step and flags are clear, but this is a batch image-generation operation with no explicit validation/verification checkpoint (e.g. confirm images were written, check prompts.json mapping), which per the batch-operation guidance caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Good structure with a single script bundle (scripts/gen.py) referenced via {baseDir} and well-organized sections (Run, Model-Specific Parameters, Output); references are clear and only one level deep, though the model-parameter tables are inlined where a reference file could carry the bulk.

4 / 5

Total

16

/

20

Passed

Description

60%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.

The description is concise and names concrete capabilities with a distinct OpenAI Images API niche, but it omits any explicit 'Use when...' trigger guidance and lacks the natural user-facing keywords that would make it surface reliably.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when the user wants to generate images, create DALL-E/GPT image variants, or build a prompt-driven image gallery.'

Replace skill-internal phrasing like 'Random prompt sampler' with natural user terms such as 'generate images from random or custom prompts'.

Include synonyms and model names users actually say — 'DALL-E', 'image generation', '.png' — to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain (OpenAI Images API) and several concrete actions (batch-generate, random prompt sampler, gallery), though 'batch-generate' and 'sampler' are slightly generic compared to the comprehensive anchor at 5.

4 / 5

Completeness

Has a clear 'what' (batch-generate images via OpenAI Images API with a sampler and gallery) but no 'Use when...' clause or equivalent trigger guidance, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Contains 'OpenAI Images API' and 'gallery' but lacks the natural phrases and synonyms a user would say (e.g. 'generate images', 'DALL-E', 'image generation', file extensions); 'random prompt sampler' is skill-internal jargon rather than a user trigger.

3 / 5

Distinctiveness Conflict Risk

Scoped specifically to the OpenAI Images API with a random-prompt-sampler niche, making it mostly distinct from other image skills with only minor overlap risk.

4 / 5

Total

14

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

13

/

16

Passed

Repository
trpc-group/trpc-agent-go
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.