Codrive — Testing skill for Claude Code
User signals "drive it for me, I'll log in" — drive a multi-step browser flow via Playwright MCP, handing the visible browser to the user at identity gates and resuming after.
How to install Codrive
Installs to ~/.claude/skills/lefteq-claudikpublic-codrive/SKILL.md
mkdir -p ~/.claude/skills/lefteq-claudikpublic-codrive && curl -fsSL https://raw.githubusercontent.com/LEFTEQ/ClaudikPublic/HEAD/commands/codrive.md -o ~/.claude/skills/lefteq-claudikpublic-codrive/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Codrive does
disable-model-invocation: true name: codrive description: User signals "drive it for me, I'll log in" — drive a multi-step browser flow via Playwright MCP, handing the visible browser to the user at identity gates and resuming after.
Drive the browser flow in $ARGUMENTS (a URL, a parked plan, or a description) end-to-end via Playwright MCP. Empty args → drive the flow already under discussion this session; if there is none, ask what to drive.
You drive; the human is the identity. The P
Alternatives in Testing
- Flow Spec — NLSpec authoring — use when you need a structured specification from multi-AI research and consensus 2.8k ★
- Spec Driven Development — Drive Kandev feature work through spec, plan, independent tasks, implementation, QA, and verification 697 ★
- N9e Config Driven E2e — Maintain config-driven Nightingale E2E tests that convert JSON config data into UI-readable normalized values 301 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Orbits Autopilot
Run the ORBITS flow with the first four gates self-opened and logged, handing back to the person at Test. For
Claude Code Dev Workflow
A Claude Code plugin marketplace that turns a personal engineering workflow into one-click superpowers — forge
Rpi Implement
RPI Step 4 — Execute phased implementation with validation gates. Reads PLAN.md and eng.md, implements phase-b
Writing Craft
A blind tested skill for better creative writing. Nine signals three AI judges named after scoring 50 samples
Manual QA
Generate a manual QA procedure from this session's changes and walk through it interactively. The user drives
Ship And Verify
Build the Mori desktop release, prompt user to install + run targeted tests, then read JSONL log to verify the
Related Agents
QA Playwright
browser verification agent for user-visible work. exercise flows, capture screenshots, inspect console and net
QA Walker
Use to drive the built explainer (repo-root index.html) end-to-end in a real Chromium browser via Playwright,
Playwright CLI Generator
Use this agent when you need to create automated browser tests using Playwright. Examples: Context: User wants