banner-creator

Create banners using AI image generation. Discuss format/style, generate variations, iterate with user feedback, crop to target ratio. Use when user wants to create a banner, header, hero image, cover image, GitHub banner, Twitter header, or readme banner.

1.80x

Quality

76%

Does it follow best practices?

Impact

92%

1.80x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/banner-creator/SKILL.md

Quality

Content

65%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 delivers a well-sequenced, actionable workflow with concrete commands and prompt patterns. It is weakened by missing validation/verification around batch generation (capping workflow clarity), two broken reference paths in the bundle, and duplicated ratio/size details that belong in references/formats.md alone.

Suggestions

Add a validation checkpoint after batch generation (e.g., verify banner-01..20.png exist and are non-empty before building the preview, re-run generate.py for any missing files) so the batch workflow includes a validate-and-retry loop.

Fix the bundle references: either ship examples/opc-banner-creation.md and templates/preview.html, or remove those links so every referenced path resolves to a real file.

De-duplicate the ratio/size details — keep them only in references/formats.md and link to it from Step 1, Step 5, and the Quick Reference section.

Dimension	Reasoning	Score
Conciseness	The body is efficient — no explanations of concepts Claude already knows, concrete commands throughout — but ratio/size information is repeated across Step 1, Step 5, the 'Supported Aspect Ratios' section, and references/formats.md, which could be trimmed. It fits 'efficient; minor instances of over-explanation that could be trimmed' rather than the lean every-token-earns-its-place anchor.	4 / 5
Actionability	Commands are concrete and mostly executable: generate.py/batch_generate.py invocations with flags, the crop_banner.py call with --ratio/--width, and fill-in prompt patterns. Minor gaps remain: unresolved <skill_dir>/<nanobanana_skill_dir> placeholders, a macOS-only 'open' command, and template variables that need substitution — fitting 'mostly executable guidance with minor gaps' rather than fully copy-paste ready.	4 / 5
Workflow Clarity	The six steps are clearly sequenced with user checkpoints ('Wait for user confirmation before proceeding!'), but the workflow involves batch operations (generating 20 banners, then 10-20 more) with no verification steps — no check that batch outputs exist or are valid before preview/crop. Per the rubric, missing validation in batch operations caps workflow clarity at 3 even though the sequence itself is well laid out.	3 / 5
Progressive Disclosure	The main file is a good overview and references/formats.md is real and appropriately split, but two referenced paths do not exist in the bundle (examples/opc-banner-creation.md and templates/preview.html), so navigation fails for half the referenced targets. Combined with size tables duplicated inline from formats.md, this fits 'some structure but could be better organized' rather than the good-structure anchor at 4.	3 / 5
	Total	14 / 20 Passed

Description

88%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: concrete workflow actions, an explicit 'Use when...' clause with platform-specific trigger terms, and a clear niche. The only gaps are a few missing natural trigger synonyms and slight overlap with general image-generation skills.

Dimension	Reasoning	Score
Specificity	The description lists the full workflow as concrete actions — 'Discuss format/style, generate variations, iterate with user feedback, crop to target ratio' — giving comprehensive, specific coverage rather than generic claims. It matches the anchor for multiple specific concrete actions and is clearly above the 'several specific actions; minor gaps' anchor.	5 / 5
Completeness	It explicitly answers both questions: what it does ('Create banners using AI image generation... crop to target ratio') and when to use it ('Use when user wants to create a banner, header, hero image...') with concrete trigger phrases. This matches the top anchor exactly, not the weaker-'when' anchor at 4.	5 / 5
Trigger Term Quality	Trigger terms include natural synonyms and platform variants — 'banner, header, hero image, cover image, GitHub banner, Twitter header, or readme banner' — which users would actually say. A few common variants are missing (e.g., 'social media cover', 'channel art', 'OG image'), placing it just below the comprehensive-coverage anchor.	4 / 5
Distinctiveness Conflict Risk	The banner niche is clear with distinctive platform-specific triggers, but it retains minor overlap risk with general AI image-generation skills (the underlying nanobanana-type skill) since 'banner'/'cover image' requests could plausibly route to either. This fits 'mostly distinct; minor overlap risk with closely related skills' rather than the minimal-risk anchor at 5.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: ReScienceLab/opc-skills
Path: skills/banner-creator/SKILL.md
Commit: 8cb68e3

Reviewed: 5 days 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.