CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

image-generation

Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 content is highly actionable and operationally precise: executable examples for every common case, a complete parameter table, explicit timeout/synchronization requirements, and a clear error-recovery policy. It is token-efficient with only minor redundancy, and its structure cleanly separates usage, output, setup, and error handling, with the sole bundle script correctly referenced.

DimensionReasoningScore

Conciseness

The body is efficient and consistently conveys non-obvious operational facts (backend auto-selection, 600s timeout, synchronous invocation, output location) rather than concepts Claude already knows. Minor over-explanation could be trimmed — the "don't specify a model" guidance is repeated in the intro and Setup section, and the per-provider model lists are somewhat long — keeping it just below the lean anchor 5.

4 / 5

Actionability

Fully executable, copy-paste-ready commands are given for the common cases: basic generation, size/aspect-ratio generation, single-image editing, and multi-image fusion, plus a parameter table with types and defaults and the exact success/error JSON output shapes. This matches the anchor for complete executable guidance covering common cases.

5 / 5

Workflow Clarity

The single action is unambiguous — invoke scripts/generate.py synchronously with a JSON argument, wait for output (timeout >= 600s), parse the JSON, then display the image — and the Error Handling section provides an explicit feedback loop (on error, do not retry with the same parameters; direct the user to fix env_config, then retry). The simple-skill exception applies and no validation gap exists for this non-destructive, non-batch operation.

5 / 5

Progressive Disclosure

The body is well organized into clear sections (Usage, Parameters, Examples, Output, Setup, Error Handling, Notes) and its single reference, scripts/generate.py, is real and one level deep. Minor gap: the per-provider model lists and setup detail are inlined in a ~105-line body where a small references file could keep SKILL.md leaner, so it sits just below the well-split anchor 5.

4 / 5

Total

18

/

20

Passed

Description

83%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: it states what the skill does in one sentence and provides an explicit, keyword-rich "Use when" trigger clause covering natural user phrasings. The only weaknesses are a slightly broad "any visual content" catch-all and a few missing synonyms/file extensions that keep trigger coverage and distinctiveness just below maximal.

DimensionReasoningScore

Specificity

"Generate or edit images from text prompts" names two core actions, and "create, draw, design, or edit an image, illustration, photo, icon, poster" broadens object coverage — several specific actions with minor gaps (e.g., no variation/upscaling/restoration actions). More comprehensive than anchor 3's 1-2 actions, but short of anchor 5's full coverage.

4 / 5

Completeness

It explicitly answers "what" ("Generate or edit images from text prompts") and "when" with concrete trigger phrases ("Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content"), exactly matching the anchor-5 pattern of both clear what and explicit when. Anchor 4 would require the when-clause to be less explicit, which it is not.

5 / 5

Trigger Term Quality

"create, draw, design, or edit" plus "image, illustration, photo, icon, poster, or any visual content" are natural phrases users would say, matching good keyword coverage. A few natural terms are missing (e.g., "picture", "logo", "render") and no file extensions (".png", ".jpg") appear, so it falls short of anchor 5's comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

The image-generation niche is mostly distinct with concrete image-specific triggers, but "any visual content" is broad and could overlap with closely related skills such as chart/diagram/visualization generation. Clearer than anchor 3's generic overlap, but not the minimal-conflict precision of anchor 5.

4 / 5

Total

17

/

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.

Validation — 13 / 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

relative_links

Relative link issues: 1 suspicious

Warning

Total

13

/

16

Passed

Repository

zhayujie/CowAgent

Path

skills/image-generation/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.