Canonical manifest schema
plugin.json targets the official 1.0.0 schema.
Agent Plugins specification §5.2
Visual PR supplies four Skills for capturing web interfaces, annotating images with callouts, embedding before-and-after evidence in GitHub or Azure DevOps pull requests, and producing animated GIF demonstrations with variable timing.
Show
the interface change.
The reviewed package connects capture, annotation, PR embedding, and recording into one evidence workflow.
Installation
Install the plugin in an image-capable client and ensure its Playwright and PIL workflows can run in the target environment.
git clone --filter=blob:none --sparse https://github.com/github/awesome-copilot.git
cd awesome-copilot
git sparse-checkout set plugins/visual-prExplainable standards check
Official latest version: 1.0.0 (Working Draft). The value is read from the official specification and cached for one day.
This is a static package-format check, not a security audit, quality score, malware scan, or guarantee of client compatibility.
plugin.json targets the official 1.0.0 schema.
Agent Plugins specification §5.2
The plugin name “visual-pr” satisfies the 1–64 character naming rules.
Agent Plugins specification §§5.3 and 5.5
No unknown top-level manifest fields were found.
Agent Plugins specification §5.2
All present metadata and extension fields use permitted JSON types.
Agent Plugins specification §§5.2–5.6
A regular plugin.json file exists at the plugin root.
Agent Plugins specification §§4.1 and 5.1
0 immediate-child Agent Skills discovered; every SKILL.md passed required frontmatter and naming checks.
Agent Plugins specification §7.1 and Agent Skills specification
No root mcp.json is present; MCP is optional and its absence is conforming.
Agent Plugins specification §§6.2 and 7.2
Capabilities
Replace text-only descriptions of visual changes with reviewable image evidence.
Playwright and PIL workflows capture a UI, locate regions, add callouts, embed before-and-after images in PR descriptions, and create animated demonstrations. The README also describes debug heatmaps for annotation placement.
Separate Skills handle browser screenshots and PIL-based visual callouts.
Package results as before-and-after pull request evidence or animated release and documentation demos.
Practical workflow
Use Playwright to navigate the UI and capture the relevant states.
Add verified callouts and inspect debug placement output when needed.
Place images in a PR, bug report, release note, or animated demonstration.
Package contents
visual-pr declares 4 Skills, 0 MCP configurations, and 0 additional resources. The included-file links below point to the reviewed source repository.
Agent Skills
4
image-annotations, pr-screenshots, screen-recording, ui-screenshots
MCP servers
0
No runtime service
Package format
Agent Plugins
Official latest 1.0.0
Synced source content
This README snapshot is stored by Agent Plugins Hub and refreshed by the daily GitHub synchronization pipeline. Remote images and embedded content are not loaded.
This repository does not currently provide a README snapshot. The plugin instructions below remain available.
Source documentation
Rendered from the linked GitHub source. Raw HTML is disabled, scripts cannot execute, remote images are omitted, and external links open separately.
Visual PR teaches an agent to show interface changes through captured and annotated evidence. Its four Skills cover Playwright UI screenshots, PIL-based callouts, before-and-after embedding for GitHub and Azure DevOps pull requests, and variable-timing animated GIF recordings.
The README demonstrates multipurpose annotations and a debug heatmap for placement decisions. It lists visual PRs, release notes, bug reports, and documentation as use cases.
The workflow requires a model that can view images and appropriate browser and image-processing tools. Verify every annotation against the captured UI.
Continue exploring
The small official reference package for inspecting a portable manifest and migration workflow.
A portable end-to-end guide for planning, implementing, testing, and evaluating MCP servers.
A portable test-driven workflow for authoring, validating, evaluating, packaging, and improving Agent Skills.