goose-graphics-create-style

End-to-end skill that turns a single reference image into a published Gooseworks style — analyzes the image, drafts the slim style spec, renders a hero example plus 2-3 additional formats via Playwright, writes the `gooseworks-style.json` manifest, and publishes via `npx gooseworks styles publish` so other agents can discover it. Mirrors goose-graphics-create-format but for styles.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/design/composites/goose-graphics-create-style/SKILL.md

Quality

Content

77%

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, well-validated 8-step workflow, but it is verbose for a skill (with redundancy) and keeps all reference material inline in one long file rather than progressively disclosing it into separate bundle files.

Suggestions

De-duplicate slug-collision guidance: cover it once (Step 7) and cross-reference from Step 2 and Anti-patterns instead of re-explaining it three times.

Move stable reference material (format-dimensions table, manifest schema/constraints, description- and tag-writing guidelines) into a references/ file (e.g. STYLE-SPEC.md) with a one-level-deep link from the workflow, to shorten SKILL.md and enable progressive disclosure.

Tighten the Standard Brief and Notes sections to the essentials an agent cannot derive from the CLI, trimming any restated catalog behavior.

Dimension	Reasoning	Score
Conciseness	The ~415-line body is mostly operational and assumes Claude's competence (no basic-concept padding), but it is long with real redundancy — slug-collision handling is explained in Step 2, Step 7, and Anti-patterns, and the moodGroup list is repeated — so it is not the lean 'every token earns its place' of level 3.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance: exact CLI commands, the screenshot.js invocation with all flags, a complete manifest JSON example, a format-dimensions table, and explicit HTML rules — matching the level-3 anchor.	3 / 3
Workflow Clarity	Eight clearly sequenced steps with explicit validation checkpoints (Step 6 Visual QA, Step 2 collision check via 'styles get', CLI client-side validation), feedback loops ('If anything looks off, fix the HTML and re-render'), and checklists (the Step 1 analysis checklist, the manifest constraints), matching the level-3 anchor.	3 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a single monolithic ~415-line file with no bundle files (references/scripts/assets absent) and no one-level-deep references; substantial inline reference material (format dimensions, manifest schema, guidelines) could be split out, so it does not reach the level-3 'appropriately split' anchor.	2 / 3
	Total	10 / 12 Passed

Description

60%

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 specific and concrete about the end-to-end pipeline, but it omits an explicit 'Use when...' trigger, leans on domain jargon over natural user phrasing, and acknowledges a near-identical sibling skill, which together limit trigger quality, completeness, and distinctiveness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user has a reference image and wants to turn its aesthetic into a reusable, publishable Gooseworks style.'

Soften jargon in favor of natural terms users would say (e.g. 'design style' / 'aesthetic' alongside 'slim style spec', and drop or de-emphasize 'Playwright' from the description).

Sharpen the distinction from goose-graphics-create-format in the description itself (styles = reusable aesthetic system vs. formats = layout templates) to reduce wrong-skill triggering.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'analyzes the image, drafts the slim style spec, renders a hero example plus 2-3 additional formats via Playwright, writes the gooseworks-style.json manifest, and publishes via npx gooseworks styles publish' — matching the level-3 anchor of several specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does, but there is no explicit 'Use when...' trigger clause; the 'when' is only implied ('so other agents can discover it'), which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Contains some natural terms ('reference image', 'style', 'publish') but leans heavily on jargon users would not naturally say ('slim style spec', 'Playwright', 'gooseworks-style.json manifest'), missing common variations; not the broad coverage of level 3.	2 / 3
Distinctiveness Conflict Risk	It has a clear niche (publishing a style from a reference image) but explicitly mirrors a sibling skill ('Mirrors goose-graphics-create-format but for styles'), creating real overlap/conflict surface, so it does not reach the level-3 'unlikely to conflict' anchor.	2 / 3
	Total	9 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/design/composites/goose-graphics-create-style/SKILL.md
Commit: 8866b2a

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.