CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

59

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

60%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete commands, manifest specs, and a clear step sequence, but it is undercut by missing bundle files referenced for progressive disclosure and by absent validation/feedback loops in the export and publish workflows.

Suggestions

Ship the referenced bundle files (sources/unsplash.md, sources/ascii-art.md, extract-style.md, screenshot/screenshot.js, screenshot/package.json) or remove the references — pointing at non-existent files breaks progressive disclosure.

Add an explicit validation/retry checkpoint to the Screenshot step (e.g., verify PNG dimensions match the canvas slug before delivering, re-run on failure).

Trim repeated overview framing across §1, §6, and §18 and condense the invocation-mode prose to reduce token weight.

DimensionReasoningScore

Conciseness

Mostly efficient with executable commands and tables, but it includes background exposition Claude doesn't need ('This skill supports three invocation modes — all-args, partial-args, and interactive') and restates the overview repeatedly across §1, §6, and §18, which could be tightened.

2 / 3

Actionability

It provides concrete, copy-paste-ready commands throughout ('npx gooseworks styles list', the screenshot.js invocation with flag semantics, the canvas-slug mapping table) and complete manifest JSON examples, leaving little ambiguous.

3 / 3

Workflow Clarity

The seven-step interactive workflow is clearly sequenced, but it lacks explicit validation checkpoints for the destructive/batch render+overwrite export step and the publish step; feedback loops (validate -> fix -> retry) are not present, capping workflow clarity at 2.

2 / 3

Progressive Disclosure

The body references bundle files (sources/unsplash.md, sources/ascii-art.md, extract-style.md, screenshot/screenshot.js, screenshot/package.json) and a remote URL, but none of these files exist in the skill pack — references point at missing material, so navigation and structure cannot be relied on.

1 / 3

Total

8

/

12

Passed

Description

75%

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 with strong distinctiveness, but it lacks an explicit 'Use when...' trigger clause and leans on tool jargon rather than natural user language, capping completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming the scenarios (e.g., 'Use when creating social graphics, posters, carousels, or slides from a catalog of styles').

Trade some tool jargon ('gooseworks CLI', 'Playwright', 'Agent Skills ecosystem') for natural user phrasing like 'create posters, carousels, and infographics'.

DimensionReasoningScore

Specificity

It lists multiple concrete actions — 'Discovers community-published styles + formats via the gooseworks CLI, runs an extract-style workflow on reference images, and exports rendered PNGs via Playwright' — naming specific tools and operations rather than vague language.

3 / 3

Completeness

It clearly answers 'what does this do' with concrete actions, but there is no 'Use when...' clause — the 'when to use it' guidance is only implied by the listed capabilities, which caps completeness at 2 per the rubric.

2 / 3

Trigger Term Quality

It uses some natural terms a user might say ('reference images', 'rendered PNGs', 'styles', 'formats') but leans on product/tool jargon ('gooseworks CLI', 'Playwright', 'Agent Skills ecosystem', 'Claude Cowork') rather than plain user phrasing like 'make a poster' or 'create slides'.

2 / 3

Distinctiveness Conflict Risk

The niche is distinct — visual style/format rendering tied to the gooseworks catalog and Playwright PNG export — and unlikely to trigger for unrelated skills; it is clearly distinguishable.

3 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
gooseworks-ai/goose-skills
Reviewed

Table of Contents

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.