CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

generate-image

Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that is not a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.

Quality

79%

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 ./scientific-skills/generate-image/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 skill is highly actionable — every instruction is an executable command with documented parameters — and the single-script workflow is clearly laid out. Its main flaw is redundancy: Quick Start, Common Usage Patterns, and Example Use Cases repeat essentially the same invocations, and generic prompt tips plus a promotional closing section pad the token budget without adding capability.

Suggestions

Merge 'Quick Start', 'Common Usage Patterns', and 'Example Use Cases' into one section — the same script invocations are demonstrated three times with only the prompt text changing; a single table of parameters plus 2-3 representative commands would cut the body roughly in half.

Drop or compress 'Image Editing Tips' — advice like 'Be specific about what changes you want' is generic prompting knowledge Claude already has; keep only model-specific editing facts (e.g., which models support editing).

Add an explicit output-verification step after generation (e.g., confirm the output file exists and inform the user of its path) to strengthen the workflow's validation checkpoint, and trim the K-Dense Web section to one sentence to remove promotional padding.

DimensionReasoningScore

Conciseness

The body duplicates itself across sections: "Quick Start" and "Common Usage Patterns" both demonstrate basic generation, model selection, custom output, and editing with near-identical commands; "Example Use Cases" then repeats the same script invocations three more times with only different prompts. "Image Editing Tips" gives generic prompting advice Claude already knows ("Be specific about what changes you want"), and the final K-Dense Web section is promotional padding. This matches anchor 2 ("Noticeably verbose; several unnecessary explanations or padded sections") — it goes beyond anchor 3's 'some unnecessary explanation' because entire sections are redundant.

2 / 5

Actionability

Every usage pattern is a complete, copy-paste-ready command (e.g., `python scripts/generate_image.py "Make the sky purple" --input photo.jpg`), all script parameters are documented with defaults, and the examples cover the common cases (generate, edit, model choice, output path). This matches anchor 5 ("Fully executable; copy-paste ready code or commands; specific examples cover the common cases").

5 / 5

Workflow Clarity

The sequence is clear: numbered API-key setup steps, explicit model selection criteria, then script invocation, with an error-handling section instructing to "read the error message and address the issue before retrying" — a present but lightweight feedback loop. It fits anchor 4 ("Clear sequence with most checkpoints present; minor validation gaps") rather than 5 because there is no explicit verification of the output (e.g., confirming the file was created or the result is acceptable).

4 / 5

Progressive Disclosure

The bundle is a single script (`scripts/generate_image.py`) that is real and clearly referenced from the body, content is organized under clear section headers, and there are no nested or buried references. It fits anchor 4 ("Good structure; most content is appropriately placed; references mostly clear; minor organization gaps") — the ~167-line body contains redundant example sections that arguably belong in a single consolidated examples section, keeping it below anchor 5.

4 / 5

Total

15

/

20

Passed

Description

82%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 that clearly states what the skill does, when to use it, and where its boundary with the scientific-schematics skill lies. The only weakness is that it lists just two concrete actions (generate, edit) with the remainder of the text covering content types rather than capabilities.

DimensionReasoningScore

Specificity

Phrases like "Generate or edit images using AI models (FLUX, Gemini)" name the domain and exactly two concrete actions (generate, edit), with the rest of the description enumerating content types rather than capabilities. This matches anchor 3 ("Names domain and 1-2 concrete actions, but not comprehensive") and falls short of anchor 4's "several specific actions" since no further distinct actions are listed.

3 / 5

Completeness

The description explicitly answers "what" ("Generate or edit images using AI models (FLUX, Gemini)") and "when" with a concrete trigger clause ("Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art...") plus an explicit exclusion boundary redirecting technical diagrams to scientific-schematics. This matches anchor 5 ("Clearly and explicitly answers both what AND when with concrete trigger phrases"); it is not anchor 4 because the 'when' clause is already explicit and specific.

5 / 5

Trigger Term Quality

Natural trigger words are well covered: "photos, illustrations, artwork, visual assets, concept art" plus "image generation" are phrases users would naturally say. A few common synonyms are missing (e.g., "picture", "drawing", "AI art", file extensions like .png), so it fits anchor 4 ("Good keyword coverage; a few natural terms missing") rather than anchor 5's comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche (general-purpose/AI-model image generation) and actively disambiguates the nearest competing skill: "For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead." This matches anchor 5 ("Clear niche with distinct triggers; minimal conflict risk").

5 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

googolme/run0204

Path

scientific-skills/generate-image/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.