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

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%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 a dense, fully executable playbook: exact commands, a complete manifest example, dimension tables, validation gates with feedback loops, and explicit failure-mode recovery across an eight-step workflow. Its only deductions are some repetition of load-bearing rules and inline guideline sections that could be offloaded to reference files.

Dimension	Reasoning	Score
Conciseness	Nearly every line is operational (commands, flags, constraints, tables) with zero explanation of known concepts, but several load-bearing rules are restated 3-4 times (hero requirement, tweet-format rule, slug-collision flow, standard-brief mandate). These are short, contextual restatements rather than conceptual padding — score 4 ("efficient; minor instances... could be trimmed"), not 3.	4 / 5
Actionability	Fully executable throughout: exact CLI invocations with flags and values, a complete example gooseworks-style.json manifest, a per-format dimensions table, concrete HTML rules with exact CSS, and publish exit codes with recovery behavior. Copy-paste ready and covers the common cases — score 5.	5 / 5
Workflow Clarity	Eight explicitly numbered steps with pre-flight checks (catalog search, slug collision via `styles get`), a written-out analysis checklist, a dedicated Step 6 visual-QA validation gate with an explicit fix-and-re-render feedback loop, and publish exit codes for error recovery. Validation surrounds the outward-facing publish operation — score 5 ("explicit validation steps; feedback loops; checklists").	5 / 5
Progressive Disclosure	No bundle files exist; the single body is well-sectioned and navigable, and points outward one level deep via fetchable resources (`npx gooseworks styles get dot-grid-stat`, `goose-graphics/SKILL.md` §17.1, `npx gooseworks formats get`). The description/tag guidelines and format-dimensions table could be split into reference files to slim the main body — minor organization gaps, score 4.	4 / 5
	Total	18 / 20 Passed

Description

71%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 specific, action-dense, and clearly niched to the Gooseworks style-publishing workflow, with explicit disambiguation from its sibling format skill. Its main weakness is the absence of any "Use when..." trigger clause, which caps completeness at 3, plus thin natural-synonym coverage.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user has a reference image and wants to turn its aesthetic into a reusable, published Gooseworks style" — this lifts completeness from 3 to 5.

Add natural trigger synonyms users would actually say — "create a new style", "theme", "aesthetic", "look" — so description-based matching catches phrasings other than exact ecosystem jargon.

Trim the "End-to-end skill that" opener to start directly with the action ("Turns a single reference image into a published Gooseworks style...") to save tokens for the trigger clause.

Dimension	Reasoning	Score
Specificity	The description lists five concrete pipeline 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`" — comprehensively covering the workflow from input to published output, matching the score-5 anchor.	5 / 5
Completeness	The "what" is explicit and concrete, but there is no "Use when..." clause or equivalent trigger guidance — "so other agents can discover it" describes purpose, not when to invoke. Per the judging guidelines, a missing use-when clause caps completeness at 3 ("clear 'what' but 'when' missing or only weakly implied").	3 / 5
Trigger Term Quality	Good keyword coverage ("reference image", "published Gooseworks style", "publish", "discover") but natural synonyms users would say — "create a new style", "theme", "aesthetic", "look" — are missing. Matches score 4 ("good keyword coverage; a few natural terms missing"), not 5 (no synonym/variation coverage).	4 / 5
Distinctiveness Conflict Risk	Niche terms ("Gooseworks style", "gooseworks-style.json manifest") and the explicit mirror callout "Mirrors goose-graphics-create-format but for styles" disambiguate the closest sibling skill, but a request like "create a goose graphics style from this image" still overlaps that closely related skill — score 4 ("mostly distinct; minor overlap risk with closely related skills").	4 / 5
	Total	16 / 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
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: cc3e518

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.