pixelbrowse

Screenshot and visually read any web page or document using pixelshot. Use instead of fetching raw HTML when you need to see what a page looks like, read visual content (charts, diagrams, infographics), check layouts, or verify UI. Triggers: "look at this page", "screenshot", "what does this site look like", "check the UI", "read this visually", "view this URL", viewing web content.

Quality

86%

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

Quality

Content

86%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.

A well-structured, highly actionable body that gives copy-paste commands and exact output paths with minimal padding. The only gap is a missing explicit recovery loop for failed/blank captures.

Suggestions

Add a short feedback loop in the Workflow for blank or half-empty captures (e.g. 'If tile_0000.jpg is blank, re-run with --wait-network-idle and a longer wait').

Trim the --wait-network-idle justification to one line; Claude already understands network-idle semantics.

Tighten the install aside ("Don't go hunting for it in project venvs") into a terse instruction to keep the tone uniform.

Dimension	Reasoning	Score
Conciseness	Mostly lean with non-obvious vision specifics (1568/2576px downscale thresholds) that earn their place; assumes Claude's competence throughout. Not 5 because the --wait-network-idle justification sentence and the "Don't go hunting for it in project venvs" aside could be trimmed; not 3 because there is no padding of concepts Claude already knows.	4 / 5
Actionability	Copy-paste-ready pixelshot commands cover the common cases (URL, parallel, wider viewport, PDF) plus an executable Pillow crop one-liner and deterministic output paths. Matches the anchor for fully executable, example-covered guidance.	5 / 5
Workflow Clarity	Clear numbered sequence with a failure checkpoint ("If it doesn't exist, the page had no content") and an install-retry loop. Not 5 because there is no explicit validate-then-retry loop for blank/half-empty captures (only prevention via --wait-network-idle); not 3 because checkpoints are present and the operation is read-only so the destructive cap does not bind.	4 / 5
Progressive Disclosure	A single self-contained file with well-organized sections (How to use, Workflow, Crop & Zoom, Tips) and no bundle files or nested references. Content is appropriately inline for a skill of this size, so the simple-skill exception applies.	5 / 5
	Total	18 / 20 Passed

Description

87%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.

A strong description that concisely states what the skill does, when to use it, and supplies a rich explicit trigger list. It carves a clear niche distinct from HTML-fetching skills.

Dimension	Reasoning	Score
Specificity	"Screenshot and visually read any web page or document", "read visual content (charts, diagrams, infographics), check layouts, or verify UI" lists several concrete actions. Not 5 because coverage is not comprehensive (no document-type actions like 'fill forms' or 'convert'); not 3 because it clearly exceeds 1-2 actions.	4 / 5
Completeness	Explicitly answers both what ("Screenshot and visually read any web page or document using pixelshot") and when (an explicit "Triggers:" clause plus "Use instead of fetching raw HTML when…"). Matches the anchor that requires concrete trigger phrases for both what and when.	5 / 5
Trigger Term Quality	"look at this page", "screenshot", "what does this site look like", "check the UI", "read this visually", "view this URL" are natural phrases users would say. Not 5 because PDF/document-specific synonyms and extensions (e.g. "read this PDF", ".pdf") are absent; not 3 because coverage is well beyond 'some relevant keywords'.	4 / 5
Distinctiveness Conflict Risk	Clear niche (pixel-based visual reading) distinguished from raw-HTML fetching via "Use instead of fetching raw HTML", with distinct screenshot/UI triggers and minimal overlap risk. Not 4 because the differentiator and triggers are explicit, not merely 'mostly distinct'.	5 / 5
	Total	18 / 20 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: StarTrail-org/PixelRAG
Path: plugin/skills/pixelbrowse/SKILL.md
Commit: c1dae49

Reviewed: 16 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.