CtrlK
BlogDocsLog inGet started
Tessl Logo

nano-banana-pro

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

78

7.23x
Quality

71%

Does it follow best practices?

Impact

94%

7.23x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/nano-banana-pro/SKILL.md

The canonical home for this skill is nano-banana-pro in Hung-Reo/hungreo-openclaw

SKILL.md
Quality
Evals
Security

Quality

Content

93%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 a tight, highly actionable overview that delegates execution to a single bundled script and is well-organized for navigation. The only gap is the absence of an explicit verification checkpoint for the batch/edit operations, which keeps workflow clarity at 4.

DimensionReasoningScore

Conciseness

The body is lean: one intro line, three copy-paste commands, API-key setup, and a short Notes list, with no padding or explanation of concepts Claude already knows; every token earns its place.

5 / 5

Actionability

Three fully executable `uv run` commands cover the common cases (generate, single-image edit, multi-image composition) with real flags, plus concrete API-key setup and resolution/filename guidance.

5 / 5

Workflow Clarity

Each mode is a single unambiguous command and the use cases are clearly delineated, but there is no explicit verification checkpoint (e.g. confirm the `MEDIA:` line / saved path) for the batch multi-image and file-overwriting edit cases, leaving a minor validation gap.

4 / 5

Progressive Disclosure

The body is a concise overview pointing to one real bundled file (`{baseDir}/scripts/generate_image.py`, verified present) one level deep, with the heavy logic correctly split into the script and clear section navigation.

5 / 5

Total

19

/

20

Passed

Description

50%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.

The description states a clear capability with a distinctive product name but lacks any "Use when..." trigger guidance and offers only minimal natural-language keywords. It is functional but middling, sitting at the anchor-3 level across all dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to generate, edit, or compose images, or mentions Nano Banana Pro / Gemini 3 Pro Image."

Broaden trigger terms with natural synonyms and file extensions (e.g. "create or edit images, AI image generation, .png output").

Mention additional concrete capabilities (multi-image composition up to 14 images, 1K/2K/4K resolutions) to raise specificity above 3.

DimensionReasoningScore

Specificity

"Generate or edit images" names the image domain and two concrete actions (generate, edit), but omits other capabilities shown in the body such as multi-image composition and resolution control, so it is not comprehensive.

3 / 5

Completeness

The "what" is clear (generate/edit images via Gemini 3 Pro Image), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

"generate or edit images" supplies the core natural phrases a user would say, but there are no synonyms (create, make, AI art, pictures), file extensions (.png), or trigger variations, leaving common terms missing.

3 / 5

Distinctiveness Conflict Risk

The product name (Nano Banana Pro / Gemini 3 Pro Image) narrows the niche, but the bare action "generate or edit images" is broad and could still overlap with other image-generation skills absent a distinct trigger phrase.

3 / 5

Total

12

/

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.

Validation13 / 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

Total

13

/

16

Passed

Repository
trpc-group/trpc-agent-go
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.