nano-banana-pro

Nano Banana/Gemini image gen/edit: text/image input, 512-4K workflows.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

81%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 body is highly actionable with a clear draft→iterate→final workflow, preflight validation, and error-recovery guidance, all backed by a real, executable script. The only weakness is mild token redundancy from repeating the full command and a few verbose sections that could be tightened.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with no padding about concepts Claude already knows, but the full `uv run ... generate_image.py` command is repeated verbatim across Usage, Default Workflow, and Examples, and the filename section is somewhat verbose. It is above 2 (which would have several padded/unneeded explanations) but the command repetition keeps it from 4.	3 / 5
Actionability	Every workflow is given as complete, copy-paste-ready executable commands with all flags, the referenced scripts/generate_image.py exists and matches, and concrete examples cover generation, editing, resolution mapping, and filenames. This matches the fully executable, common-cases-covered anchor.	5 / 5
Workflow Clarity	The Default Workflow (draft 1K → iterate → final 4K) is an explicitly sequenced process, with a Preflight checklist and a Common Failures section providing error→fix feedback loops. This matches the anchor for a clear sequence with explicit validation steps and feedback loops for error recovery.	5 / 5
Progressive Disclosure	The body is well-organized into clear sections (Usage, Default Workflow, Resolution Options, API Key, Preflight, Filename, Editing, Prompt Templates, Output, Examples) and the only bundle file (scripts/generate_image.py) is referenced by path in the commands. It is above 3 (good structure, appropriately placed for a single-script skill) but below 5 because at 132 lines some material (prompt templates, resolution mapping) could optionally live in references, and there are no one-level-deep reference links to signal.	4 / 5
	Total	17 / 20 Passed

Description

53%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 is terse and names the right domain and a few capabilities, but it relies on abbreviated shorthand and omits any explicit "Use when..." trigger guidance. Adding a concrete usage-trigger clause and natural synonyms would raise completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to generate or edit images, create pictures/photos, or work with Nano Banana / Gemini image output."

Expand the abbreviated "gen/edit" into full verbs ("generate and edit images") so actions are concrete rather than shorthand.

Include natural synonyms users actually say ("create image", "AI image", "picture", "photo") alongside "Nano Banana/Gemini" to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("image gen/edit") and a couple of concrete capabilities ("text/image input", "512-4K workflows"), but the actions are abbreviated and not comprehensive. It is above score 2 (which names only the domain) because it lists generation, editing, input modalities, and resolution ranges, but below 4 because the actions are terse shorthand rather than several fully stated actions.	3 / 5
Completeness	It states what the skill does (image gen/edit with text/image input and 512-4K workflows) but has no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 3. It is not 4 because the "when" is only weakly implied rather than explicitly stated.	3 / 5
Trigger Term Quality	It includes relevant terms users would say ("image", "gen", "edit", "Nano Banana", "Gemini") but uses abbreviated forms ("gen/edit") and omits common synonyms like "create image", "AI image", "picture", or "photo". This matches the anchor for some relevant keywords with missing variations, and falls short of the comprehensive synonym coverage of score 4.	3 / 5
Distinctiveness Conflict Risk	Naming the specific "Nano Banana/Gemini" API gives it a clear niche with minimal conflict risk against unrelated skills, though the broad "image gen/edit" phrasing leaves minor overlap risk with other generic image skills. It is above 3 (which would apply if it were only broadly specific) but below 5 because it lacks an explicit trigger phrase that fully isolates it.	4 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: steipete/agent-scripts
Path: skills/nano-banana-pro/SKILL.md
Commit: 15bcfe3

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.