verifier-gui
Automates runtime verification of the Silo desktop app inside safe, throwaway workspaces.
Install
mkdir -p .claude/skills/verifier-gui && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19013" && unzip -o skill.zip -d .claude/skills/verifier-gui && rm skill.zipInstalls to .claude/skills/verifier-gui
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Launch (or attach to) the Silo dev app and drive it for runtime verification through the dev automation RPC bridge — exec commands, eval DOM, capture screenshots, and create/activate/delete workspaces, terminals, editors. This is the repo's GUI evidence-capture handle for the `verify` skill. Use when verifying a change by running the real app and observing it. Always works inside a throwaway sandbox workspace, never the user's real workspaces.Key capabilities
- →Launch or attach to the Silo dev app
- →Execute commands via RPC bridge
- →Evaluate DOM elements
- →Capture screenshots of the app
- →Create, activate, and delete sandbox workspaces
How it works
The skill launches or attaches to the Silo dev app and drives it using an RPC bridge to execute commands, evaluate the DOM, and capture screenshots, all within a temporary sandbox workspace.
Inputs & outputs
When to use verifier-gui
- →Verify UI behavior at runtime
- →Capture screenshots for documentation
- →Test desktop app workflows
About verifier-gui
Controls the Silo app through an RPC bridge to execute commands, evaluate DOM, and take screenshots. Always operates within temporary workspaces to ensure state safety.
Launch (or attach to) the Silo dev app and drive it for runtime verification through the dev automation RPC bridge — exec commands, eval DOM, capture screenshots, and create/activate/delete workspaces, terminals, editors. This is the repo's GUI evidence-capture handle for the `verify` skill. Use whe
When not to use it
- →When verifying a change that does not involve running the real app
- →When the verification does not require observing the app's GUI
- →When the app is not a Tauri desktop app with a dev-only RPC bridge
Limitations
- →Requires the Silo app to be a dev build with `--features automation`.
- →Verification must occur in a sandbox workspace, not the user's real workspaces.
- →RPC `eval` operations have a hard 5-second reply timeout.
How it compares
This skill provides a programmatic and sandboxed way to interact with and verify the Silo GUI, ensuring state safety and repeatable testing, unlike manual interaction or non-GUI-based verification.
Compared to similar skills
verifier-gui side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| verifier-gui (this skill) | 0 | 1mo | Review | Advanced |
| wp-testing-core | 6 | 10mo | Review | Intermediate |
| bats-testing-patterns | 2 | 3mo | Review | Intermediate |
| orchardcore-tester | 1 | 7mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
wp-testing-core
mikkelkrogsholm
Core WordPress testing procedures and patterns for browser-based plugin testing. Use when testing WordPress plugins, logging into WordPress admin, verifying plugin activation, or navigating WordPress UI.
bats-testing-patterns
wshobson
Master Bash Automated Testing System (Bats) for comprehensive shell script testing. Use when writing tests for shell scripts, CI/CD pipelines, or requiring test-driven development of shell utilities.
orchardcore-tester
OrchardCMS
Tests OrchardCore CMS features through browser automation. Use when the user needs to build, run, setup, or test OrchardCore functionality including admin features, content management, media library, and module testing.
app-commands
growilabs
GROWI main application (apps/app) specific commands and scripts. Auto-invoked when working in apps/app.
e2e-tester
redpanda-data
Write and run Playwright E2E tests for Redpanda Console using testcontainers. Analyzes test failures, adds missing testids, and improves test stability. Use when user requests E2E tests, Playwright tests, integration tests, test failures, missing testids, or mentions 'test workflow', 'browser testing', 'end-to-end', or 'testcontainers'.
replit-load-scale
jeremylongshore
Implement Replit load testing, auto-scaling, and capacity planning strategies. Use when running performance tests, configuring horizontal scaling, or planning capacity for Replit integrations. Trigger with phrases like "replit load test", "replit scale", "replit performance test", "replit capacity", "replit k6", "replit benchmark".