browser-testing
Skill80 starsChanged 7 days agoMITView on GitHub
Use when completing frontend or UI work that needs visual verification, before claiming the UI is correct
11 other projects use a version of this.
Adopted by
Most recently taken up by
- teimurjan/skillstheir own version, first seen Nov 8, 2026
- pfangueiro/claude-code-agentstheir own version, first seen Nov 8, 2026
- sw23/fp-convtheir own version, first seen Nov 8, 2026
- Univers42/harness42their own version, first seen Nov 1, 2026
- shitcoding/claude_skillstheir own version, first seen Oct 11, 2026
- DiamondLightSource/claude-sandboxtheir own version, first seen Oct 6, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- kumaran-is/claude-code-onboarding★ 35same name
- dork-labs/dorkos★ 11same name
- sw23/fp-conv★ 8same name
- pfangueiro/claude-code-agents★ 7same name
- DiamondLightSource/claude-sandbox★ 4same name
- Univers42/claude-deal-with-the-devil★ 4same name
- Univers42/harness42★ 4same name
- bhaumikmaan/claude-code-master-skills★ 3same name
- Patrity/skills★ 2same name
- teimurjan/skills★ 1same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- contributing-to-superpowersSkill
- brainstormingSkill
- diagnosing-superpowersSkill
- dispatching-parallel-agentsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- using-git-worktreesSkill
- using-superpowersSkill
- verification-before-completionSkill
- writing-plansSkill
- writing-skillsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Never claim UI work is correct without visual evidence.
- Distinctive: line 14
When to use: After implementing any UI or frontend changes, before claiming the work is correct.
- Distinctive: line 43
Evidence classification in artifacts: Use GitHub-style alerts:
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Browser Testing
Overview
Never claim UI work is correct without visual evidence. Browser automation makes verification fast and produces artifacts the user can review.
Core principle: Evidence before assertions. Screenshots and DOM inspection prove correctness; text descriptions don't.
When to use: After implementing any UI or frontend changes, before claiming the work is correct.
The Process
- Navigate to the page under test using browser automation
- Screenshot the current state — embed in walkthrough artifact
- Inspect DOM to verify structure matches expectations (correct elements, classes, attributes)
- Record a walkthrough of the key user flow (if multi-step interaction)
- Embed evidence in a walkthrough artifact with screenshots and recordings
Quick Reference
| What to verify | Tool | Output |
| Visual appearance | Screenshot |  |
| DOM structure | Inspect elements | Element presence, attributes, classes |
| User flow | Recording | Embedded video in artifact |
| Responsive layout | Screenshot at viewport | Multiple screenshots at different widths |
Common Mistakes
| Mistake | Fix |
| Not waiting for page load before screenshot | Wait for key elements to be visible |
| Checking only one viewport size | Test at desktop (1280px) and mobile (375px) minimum |
| Visual-only verification (no DOM check) | Always inspect DOM structure — visual can hide broken markup |
| Forgetting to embed evidence | Every claim needs a screenshot or recording in the artifact |
| Saying "looks correct" without proof | Take the screenshot. Embed it. Let the user judge. |
Evidence classification in artifacts: Use GitHub-style alerts:
> [!TIP]for passing checks> [!CAUTION]for failing checks> [!NOTE]for observations that need human judgment
Integration
- superpowers:verification-before-completion — browser-testing is specialized verification for UI work
- superpowers:test-driven-development — browser tests complement unit tests, they don't replace them
Slash Command
Recommend /browser to the user when UI verification is needed. /browser is the exclusive entry point to the built-in sandboxed browser subagent — it is not available via invoke_subagent and does not add browser tools to the calling agent's session. The subagent performs the testing (navigation, screenshots, recordings) and returns evidence for the walkthrough artifact.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.