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.

68

Quality

84%

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 highly actionable, well-structured skill for a single API endpoint: complete executable examples, exact schemas, clear provider-selection guidance, and explicit error handling. The only weaknesses are minor — slight redundancy in the display/auth guidance and no explicit verification step between saving and embedding the image.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — complete curl + Python examples, compact tables for request fields and providers, no explanation of concepts Claude already knows. Minor over-explanation could be trimmed (the inline-display rules are stated twice, and the 'Do not hardcode https://api.letta.com' paragraph runs long), so it fits anchor 4 rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Fully executable, copy-paste-ready guidance: a complete curl request, a Python script handling both b64 and URL response forms, a one-liner for building input data URLs, and full request/response schemas. This covers the common cases exactly as the anchor-5 example does.

5 / 5

Workflow Clarity

The sequence is clear and explicit — generate, save locally, then embed in the reply — reinforced by an error section with concrete status codes (402/400/500) and what to do for each. It falls short of anchor 5 because there is no explicit checkpoint verifying the saved file (e.g., confirming the download succeeded or the file is a valid image) before displaying it.

4 / 5

Progressive Disclosure

Sections are well organized (Example, Request body, Response, Editing/remixing, Notes) with no nested or buried references, and no bundle files exist to navigate. At ~120 lines with the full request/response reference inlined, a modest case exists for splitting provider-specific details into a reference file, which keeps this at anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

86%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 with an explicit what/when structure and rich, natural trigger vocabulary. The main gap is that the capability list itself is narrow (only generate and edit/remix), and the diagram/icon triggers introduce mild conflict risk with adjacent visual skills.

Suggestions

Broaden the 'what' clause slightly to cover the concrete capabilities the skill actually supports, e.g. 'Generate images from text prompts (any of flux/gemini/openai providers), optionally edit or remix input images, and control size, quality, and output format' — this lifts specificity without adding fluff.

Reconsider claiming 'diagram' (and possibly 'icon') in the trigger list if other drawing/charting skills exist in the same environment, since those terms are natural conflict points; keep the trigger list to unambiguous image-creation language.

DimensionReasoningScore

Specificity

The description names the domain and 1-2 concrete actions — "Generate images from text prompts (and optionally edit/remix input images)" — but coverage is not comprehensive (no mention of provider/model choice, sizes, or batch generation). This matches the anchor-3 example ('Processes PDF files and extracts content') and falls short of anchor 4, which requires several listed specific actions.

3 / 5

Completeness

Both questions are explicitly answered: what ("Generate images from text prompts (and optionally edit/remix input images)") and when ("Use when the user asks to create, generate, draw, render, or edit an image, illustration, logo, icon, diagram, or photo"). This is structurally identical to the anchor-5 example with concrete trigger phrases, clearly above anchor 4.

5 / 5

Trigger Term Quality

"create, generate, draw, render, or edit" gives comprehensive verb-synonym coverage, and "image, illustration, logo, icon, diagram, or photo" covers the natural nouns users would say. This matches the anchor-5 pattern of synonyms plus output-type coverage; almost no natural terms are missing, so it is not a 4.

5 / 5

Distinctiveness Conflict Risk

The image-generation niche is clear with mostly distinct triggers, but "diagram" and "icon" create minor overlap risk with charting/vector-illustration skills that would also claim those terms. This fits anchor 4 (minor overlap with closely related skills) better than anchor 5's minimal-conflict claim.

4 / 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

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.