topskills
Browse Skills

run

One-command app launch tailored to your project type.

Score 0(?)OfficialCodeby Anthropic
Verified for:

Install

Built into Claude Code. Invoke with /run.

Best for

Confirming a change works in the real app rather than only in tests.

About this skill

Launch the project's app to see a change working — auto-detects project type (CLI, server, TUI, Electron, browser-driven, library).

RunLaunchDev

Score breakdown

Score breakdown

rubric 1.0
Install count
0/20
Provenance
15/15
GitHub stars
0/15
Recency
10/10
Compatibility
2/10
Documentation depth
6.5/10
Install ergonomics
10/10
License
5/5
Verification freshness
5/5

Composite 0–100 score derived from 9 verifiable signals. See the rubric →

Related skills

Community

Deterministic web control. ref-based clicks/fills, no flaky selectors, parallel sessions.

BrowserAutomationAction-taking
Code
Official

Test local webapps with Playwright. Generation, run, report — end-to-end.

PlaywrightE2ETesting
Code
Community

Playwright patterns: clicks, fills, waits, retries. The do-it-right defaults.

PlaywrightAutomation
Code

Skill FAQ

About run

What is the run skill?

Launch the project's app to see a change working — auto-detects project type (CLI, server, TUI, Electron, browser-driven, library).

Which agents does run work with?

Claude Code.

How do I install run?

See the install panel on this page for the per-agent install commands.

Is run free to use?

Yes — run is open source (MIT).

Who maintains run?

run is published by Anthropic and was last updated on 2026-05-20.

What is run best for?

Confirming a change works in the real app rather than only in tests.