CtrlK
BlogDocsLog inGet started
Tessl Logo

image-generation

Generate images from text prompts (and optionally edit/remix input images). Use when the user asks to create, generate, draw, render, or edit an image, illustration, logo, icon, diagram, or photo.

70

Quality

86%

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

82%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 lean, highly actionable skill with executable examples and clear error handling. The main improvement lever is tightening the small amount of repeated prose around response handling.

Suggestions

Consolidate the b64-vs-signed-URL handling explanation so it is stated once rather than revisited in the intro, Response, and Notes sections.

Add an explicit checkpoint to verify the saved image file exists and is non-empty before embedding it inline.

Consider moving the per-field request-body and provider tables into a short reference section or file if the skill grows, to preserve the lean overview.

DimensionReasoningScore

Conciseness

Mostly efficient with tables and executable code, but the intro paragraph and a few explanatory sentences (e.g., the base64-vs-signed-URL explanation repeated across sections) could be trimmed; not 5 due to minor over-explanation, not 3 because there is no real padding.

4 / 5

Actionability

Fully executable curl + Python example, a concrete request-body table, specific error codes (402/400/500), and a data-URL construction snippet; copy-paste ready covering the common generation, save, embed, and edit/remix cases.

5 / 5

Workflow Clarity

Clear sequence (call endpoint, save either response form, embed inline) with checkpoints for missing env vars and error surfacing; not 5 because there is no explicit validate-then-retry loop or a verify-file-saved-before-embedding checkpoint, though one is arguably unnecessary here.

4 / 5

Progressive Disclosure

Well-organized into Example/Request body/Response/Editing/Notes with no nested references and appropriately compact inline API tables; not 5 because the skill exceeds the ~50-line simple-skill threshold where the well-organized-sections exception applies.

4 / 5

Total

17

/

20

Passed

Description

90%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, well-formed description with explicit trigger guidance and good synonym coverage. The only mild gap is specificity, which lists two actions rather than a broader set.

DimensionReasoningScore

Specificity

Names the domain and two concrete actions ("Generate images from text prompts" and "edit/remix input images"), matching the anchor that lists 1-2 actions; not 4 because it does not enumerate several specific actions.

3 / 5

Completeness

Explicitly answers both what (generate images from text prompts, edit/remix) and when ("Use when the user asks to create, generate, draw, render, or edit..."), matching the anchor-5 example.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage with synonyms across both verbs ("create, generate, draw, render, or edit") and output types ("image, illustration, logo, icon, diagram, or photo"); clearly above the anchor-4 level.

5 / 5

Distinctiveness Conflict Risk

Image generation is a clear niche with distinct triggers (draw/render/illustration/logo/diagram) and minimal overlap risk with other skills.

5 / 5

Total

18

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
letta-ai/letta-code
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.