Individual skill

browser-walkthrough

Run Playwright-MCP browser acceptance, agent-observed walkthroughs, or user-attended walkthroughs through the role routing appropriate to each mode, returning a compact evidence-referenced digest.

skills/browser-walkthrough/SKILL.md

Read pinned source

Source commit dbf16d2f44d82e8a9e108b8712eb85afaa3166ab

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Local scripts
Last checked: Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 61
Repository last updated: Oct 16, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
ai-agents Repository topic
claude-code Repository topic
codex Repository topic
developer-tools Repository topic
llm Repository topic
opencode Repository topic
testing Derived category
testing-browser Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 4,579 bytes

Read excerpt


# Skill: Browser Walkthrough

Use available Playwright MCP/browser tools to exercise and observe a browser journey. This skill does not install, provision, or configure Playwright and does not create a browser-specific persona.

## Modes and Role Routing

Select one mode before using browser tools. Existing personas remain defined by the kind of delegation:

1. **Automated browser acceptance — Implementer-owned**
   - Use during approved `execute-work-package` EXECUTE work when browser behavior is part of implementation verification.
   - Keep the approved Blueprint, targeted-then-broad verification sequence, and final verify command authoritative.
   - Exercise the acceptance journey autonomously and return evidence through the execution digest.
2. **Agent-observed walkthrough — Delegate-owned**
   - Use when an agent must inspect, explain, or evaluate an existing browser journey without owning implementation.