visual-edit

Open a running local app in Design overview mode as URL-backed iframe screens for visual editing, flow review, duplication, and route-state exploration. Use when the user asks to inspect, compare, or edit a real local app visually in Design.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

77%

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

A highly actionable, well-sequenced operational skill with strong verification and error-recovery guidance. Its weak spots are conciseness (length plus a few explanatory asides) and progressive disclosure (heavy inline content with no offloaded reference files).

Suggestions

Move stable reference material — full command catalogs, screenMetadata field lists, and account/sharing rules — into a references/ file linked from the relevant sections to slim the main SKILL.md.

Tighten explanatory asides like the bridge-token ordering rationale to the minimum needed to choose the correct sequence.

Consider a one-line 'Prerequisites' or 'Quick path' summary at the top so the core happy path is scannable before the detailed mechanics.

Dimension	Reasoning	Score
Conciseness	Dense and operational rather than tutorial-style, but at ~360 lines with several explanatory asides (e.g., the bridge-token ordering rationale) it could be tightened; mostly efficient with some unnecessary padding rather than the lean every-token-earns-its-place level.	2 / 3
Actionability	Provides fully executable bash commands, complete JSON payloads for open-visual-edit, exact flag guidance, and a concrete fallback sequence — copy-paste ready and well beyond the pseudocode/incomplete score-2 level.	3 / 3
Workflow Clarity	Clear numbered sequence (discover routes → open-visual-edit → start bridge) with explicit ordering rationale, plus a Verification section and error-recovery feedback loops ('if frames do not refresh, the write did not land'), matching the explicit-checkpoints anchor.	3 / 3
Progressive Disclosure	Well-organized into clear sections, but with no bundle files the entire ~360-line document is inline monolithic content; reference-like material (command catalogs, metadata fields, account rules) that could be split out is not, so it falls short of the one-level-deep-reference anchor.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 description: third-person, specific, and complete with an explicit 'Use when' trigger. Its main weakness is trigger-term naturalness, which leans on product jargon over broadly natural user phrasings.

Suggestions

Add a few natural user phrasings (e.g., 'preview my running app', 'look at my app screen-by-screen') alongside the product-specific terms to broaden trigger coverage.

Consider mentioning the localhost/running-app condition earlier so the trigger condition is immediately visible.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Open a running local app in Design overview mode as URL-backed iframe screens', 'visual editing, flow review, duplication, and route-state exploration' — matching the multiple-specific-actions anchor, well above the score-2 partial-coverage level.	3 / 3
Completeness	Explicitly states both what it does and when to use it via the 'Use when the user asks to inspect, compare, or edit a real local app visually in Design.' clause, matching the clear what-and-when-with-explicit-triggers anchor.	3 / 3
Trigger Term Quality	Contains some natural phrasings like 'inspect, compare, or edit a real local app visually' but leans on product-specific jargon ('Design', 'URL-backed iframe') and misses common user variations such as 'preview my app'; not the broad natural-keyword coverage needed for a 3.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — visual editing of a running local app in Design via URL-backed iframes — with distinct triggers unlikely to fire for unrelated skills, beyond the score-2 overlap level.	3 / 3
	Total	11 / 12 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/plugins/agent-native-design/skills/visual-edit/SKILL.md
Commit: c1ee18b

Reviewed: 4 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.