goose-graphics

Portable visual skill pack for the Agent Skills ecosystem (Claude Code, Claude Desktop, Claude Cowork, Claude Design, Goose, Cursor, Codex). Discovers community-published styles + formats via the gooseworks CLI, runs an extract-style workflow on reference images, and exports rendered PNGs via Playwright.

Quality

63%

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

Fix and improve this skill with Tessl

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

Quality

Content

67%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 well-structured, largely actionable operational guide with a clear sequenced workflow and explicit validation checkpoints. Its main weaknesses are redundancy across sections, a delegated HTML-generation step, an inlined manifest spec, and references to bundle files that are not actually present.

Suggestions

Consolidate the repeated "list/search before assuming a slug exists" guidance and the canvas allow-list explanation into one canonical section, referencing it elsewhere.

Move the §17 manifest-format spec into a separate reference file (e.g. references/manifest-format.md) and link to it, reducing inlined content.

Add an explicit render-failure feedback loop (e.g. if Playwright/screenshot.js errors, surface the stderr, recheck the canvas slug mapping, and retry) and a short inline HTML-generation example in §13.

Dimension	Reasoning	Score
Conciseness	The body is operational and avoids explaining known concepts, but repeats the "list/search before assuming a slug exists" caveat across §3/§9/§10 and re-explains the canvas allow-list in §9/§14/§17.2, which is more than minor redundancy.	3 / 5
Actionability	Copy-paste commands (npx gooseworks styles get <slug>, the full screenshot.js invocation, npm/playwright install) and complete JSON manifests are executable, but §13 delegates HTML generation ("Follow the chosen format spec's HTML Generation phase") with no inline example.	4 / 5
Workflow Clarity	A clear 7-step sequence (§8) with per-step sections and checkpoints (§14 dimension-mismatch stop, §7 dep check, §2.1 branching), but no explicit render-failure feedback loop is given.	4 / 5
Progressive Disclosure	Structure is good with one-level-deep references clearly signaled (§18 file-reference table, inline "Read sources/unsplash.md"), but §17 inlines a large manifest spec that could be a separate file and the referenced bundle files (sources/, screenshot/, extract-style.md) are absent from the pack.	4 / 5
	Total	15 / 20 Passed

Description

58%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 gives a concrete, third-person account of what the skill does but omits any explicit when-to-use trigger guidance, capping completeness and weakening trigger-term quality. Specificity and distinctiveness are solid.

Suggestions

Append a "Use when…" clause naming concrete triggers, e.g. "Use when creating social graphics like carousels, posters, slides, or infographics, or when exporting HTML to PNG."

Add natural user-facing keywords (carousel, poster, infographic, social media graphic) alongside the technical terms to improve trigger-term quality.

Mention the publish/create-style/create-format capabilities so the action coverage is comprehensive.

Dimension	Reasoning	Score
Specificity	"Discovers community-published styles + formats via the gooseworks CLI, runs an extract-style workflow on reference images, and exports rendered PNGs via Playwright" lists several concrete actions with only minor gaps (publishing/create-format modes unmentioned).	4 / 5
Completeness	The "what" is concrete but there is no "Use when…" clause or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Terms skew technical ("gooseworks CLI", "Playwright", "extract-style workflow") and omit the natural use-case phrases a user would say ("poster", "carousel", "social media graphic"), so common variations are missing.	3 / 5
Distinctiveness Conflict Risk	The gooseworks + Playwright PNG-export pipeline carves a mostly distinct niche, though generic trigger terms ("visual", "rendered PNGs") leave minor overlap risk with screenshot/image skills.	4 / 5
	Total	14 / 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: gooseworks-ai/goose-skills
Path: skills/design/composites/goose-graphics/SKILL.md
Commit: 2523432

Reviewed: 12 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.