positron-abstract-svg

Create or update abstract SVG illustrations for the Positron IDE -- for use in documentation, walkthrough steps, onboarding images, and feature previews. Use this skill whenever someone asks to make, update, or redesign an SVG image for Positron docs, walkthroughs, or any visual asset representing the Positron IDE UI. Also use it when asked to make images "consistent" with existing Positron walkthrough images, or to add a new image to match an existing set. Trigger on: "make an SVG for the walkthrough", "create an abstract image for the notebook feature", "update the hero image", "make it look like the other Positron SVGs", "add a docs image for X feature".

Quality

100%

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

Quality

Content

100%

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

A high-quality skill body: actionable, token-efficient, with a sequenced workflow containing a preview/iterate feedback loop and a save-cleanup checkpoint. Detail is appropriately offloaded to real, clearly-named reference files rather than inlined.

Dimension	Reasoning	Score
Conciseness	Lean and specific throughout -- a palette table, concrete SVG snippets, and concrete constants with no padding explaining what an SVG is or other concepts Claude already knows; every section earns its tokens.	3 / 3
Actionability	Provides copy-paste-ready executable SVG (background rect, placeholder code rects, tspan syntax highlighting, codicon transform patterns), exact hex colors, font stacks, and sizing constants (520x260, 16x16, 20px/26px padding).	3 / 3
Workflow Clarity	A clear six-step numbered workflow (Gather, Plan, Sketch, Preview, Iterate, Save) with an explicit preview checkpoint and an iterate feedback loop, plus a save-step cleanup checklist for stripping renderer cruft.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview pointing to one-level-deep, well-signaled references (references/codicons.md, references/patterns.md with a snippet list, references/examples/ with named files), all verified to exist on disk.	3 / 3
	Total	12 / 12 Passed

Description

100%

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, third-person description that names concrete actions, provides explicit use-when triggers with natural quoted phrases, and occupies a clear niche. It answers both what and when without padding or over-claiming.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions -- "Create or update abstract SVG illustrations", "redesign", "add a new image to match an existing set" -- rather than vague language.	3 / 3
Completeness	Clearly answers both what ("Create or update abstract SVG illustrations for the Positron IDE") and when ("Use this skill whenever someone asks..." plus the Trigger on block) with explicit triggers.	3 / 3
Trigger Term Quality	An explicit "Trigger on:" block quotes natural phrases users would actually say ("make an SVG for the walkthrough", "update the hero image", "make it look like the other Positron SVGs").	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to Positron IDE abstract SVGs for docs/walkthroughs with distinct triggers, making collision with other skills unlikely.	3 / 3
	Total	12 / 12 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: posit-dev/positron
Path: .claude/skills/positron-abstract-svg/SKILL.md
Commit: b87c504

Reviewed: 2 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.