CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

baoyu-image-gen

AI image generation with OpenAI GPT Image 2.5, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate and Agnes APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.

Quality

87%

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

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-engineered, highly actionable skill body: executable commands, complete option/environment tables, a blocking preference-load step with fallbacks, and batch retry/reporting behavior. The only notable costs are mild redundancy around codex-cli details and the absence of an explicit output-verification step.

DimensionReasoningScore

Conciseness

The body is dense with skill-specific facts (env var tables, model defaults, provider quirks) and never explains concepts Claude already knows. Minor trimming is possible: codex-cli setup and caveats are restated across the Options table, Environment Variables, the Codex OAuth section, and Provider Selection.

4 / 5

Actionability

Commands are copy-paste ready ("${BUN_X} {baseDir}/scripts/main.ts --prompt \"A cat\" --image cat.png"), every CLI flag and environment variable is tabulated with defaults, and exact EXTEND.md paths with a load-priority chain are given. Examples cover single, reference-image, batch, and provider-pinned cases.

5 / 5

Workflow Clarity

There is a blocking Step 0 with an ordered fallback table, an explicit provider-selection priority order, and error handling with auto-retry ("each image retries up to 3 attempts; final output reports success count, failure count, and per-image failure reasons"), which satisfies batch validation. It falls short of a 5 because there is no explicit verification of the generated output before delivery and the overall flow is organized by topic rather than one end-to-end sequence.

4 / 5

Progressive Disclosure

The body is a genuine overview: provider details, config schema, first-time setup, and usage examples are split into one-level-deep files under references/ (all verified to exist), clearly signaled with a 'Read when the user picks that provider' table and inline pointers like 'references/usage-examples.md'.

5 / 5

Total

18

/

20

Passed

Description

88%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 description: third-person, specific about capabilities and providers, with an explicit 'Use when' trigger clause containing natural synonyms. The only weaknesses are a few missing natural trigger variants and slight trigger breadth that could overlap with diagramming or illustration skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities ("Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files") alongside an enumeration of eleven concrete provider APIs, giving comprehensive coverage of the skill's actions. It exceeds the 'minor gaps' level because both the actions and the provider surface are enumerated specifically.

5 / 5

Completeness

It clearly answers both questions: what it does ("AI image generation with OpenAI GPT Image 2.5, Azure OpenAI, ... APIs. Supports text-to-image, reference images, aspect ratios, and batch generation") and when to use it with a concrete trigger clause ("Use when user asks to generate, create, or draw images").

5 / 5

Trigger Term Quality

"Use when user asks to generate, create, or draw images" provides three natural verb synonyms users would say, plus "image generation" as a noun phrase. It falls short of comprehensive coverage (e.g., no "make a picture", "AI art", "illustration", or "render"), but is well above the some-keywords-missing level.

4 / 5

Distinctiveness Conflict Risk

The provider enumeration establishes a clear AI-image-generation niche with low conflict risk, but the trigger "generate, create, or draw images" is broad enough to also fire for chart, diagram, or illustration requests that other skills might better serve. Mostly distinct with minor overlap risk, not a fully clean niche.

4 / 5

Total

18

/

20

Passed

Validation

75%

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

Validation — 12 / 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

referenced_paths_exist

Referenced path issues: 12 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository

JimLiu/baoyu-skills

Path

skills/baoyu-image-gen/SKILL.md

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.