svg

Author and edit `.svg` files in a Grida editor session — live-canvas binding, SVG output style, and parse-error recovery. Use when creating or modifying an SVG document.

Quality

86%

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

72%

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

A lean, mostly actionable instruction-only skill with good SVG-style guidance and a parse-error recovery loop. Its weakness is the somewhat tangled, redundant "Show the result" section, which muddies the workflow and adds avoidable tokens.

Suggestions

Tighten the "Show the result" section by collapsing the overlapping caveats ("not the final validate and open step", the "do not wait for ..." list, and "do not call surface_open after every write") into a single concise rule so the workflow reads cleanly.

Reformat the new-SVG presentation flow as a short numbered sequence (write first frame → surface_open → refine) with the parse-error recovery step inline, making the checkpoints explicit instead of scattering them across conditional bullets.

Move the repeated "already mounted / do not reopen" and board/deck ownership rules into one clearly labeled bullet to remove cross-bullet redundancy.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude knows SVG, but the "Show the result" section repeats overlapping caveats ("not the final validate and open step", "do not wait for ... exhaustive validation", "do not call surface_open after every write") that could be tightened.	2 / 3
Actionability	Gives concrete, executable guidance — "Keep `xmlns=...` on the root element", "Preserve existing `viewBox`, `width`, `height`", "call `surface_open` immediately with its workspace-rooted path (for example, `/poster.svg`)" — including a specific example path.	3 / 3
Workflow Clarity	A parse-error feedback loop exists ("On `edit_file` reason=\"parse_error\" ... Re-read and fix"), but the "Show the result" sequence is presented as tangled conditional bullets rather than an ordered workflow, leaving checkpoints implicit.	2 / 3
Progressive Disclosure	Under 50 lines with no external references, organized into clear sections ("## Show the result", "## SVG style") — well-organized enough to score 3 per the simple-skills note.	3 / 3
	Total	10 / 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 concise, third-person description that names concrete capabilities and gives an explicit natural trigger, covering both what and when clearly. It is distinct to SVG work in a Grida session.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Author and edit `.svg` files", "live-canvas binding, SVG output style, and parse-error recovery" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (author/edit SVG, canvas binding, style, parse-error recovery) and when ("Use when creating or modifying an SVG document"), with an explicit trigger clause.	3 / 3
Trigger Term Quality	"Use when creating or modifying an SVG document" plus ".svg files" give good coverage of natural terms a user would say, matching the top anchor.	3 / 3
Distinctiveness Conflict Risk	Niche is clear — SVG authoring/editing within a Grida editor session — with distinct triggers unlikely to fire for unrelated skills.	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: gridaco/grida
Path: skills/svg/SKILL.md
Commit: 2e0d276

Reviewed: 3 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.