Add CDP (Chrome DevTools Protocol) support to the existing
browser-automation skill, allowing connection to an already-running
Chrome browser via --cdp <ws-endpoint> flag.
- Rewrite CRITICAL RULES to describe principles instead of specific parameter values
- Replace old prerequisites with proper model configuration section and examples (Gemini, Qwen3-VL via OpenRouter, Doubao Seed 1.6)
- Fix incorrect MIDSCENE_MODEL_FAMILY values (gemini, qwen3-vl, doubao-vision)
- Simplify "never run in background" best practice descriptions
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove .claude-plugin/ and plugins/ directory structure
- Move skills from plugins/midscene-automation/skills/ to skills/
- Delete marketplace.json and plugin.json metadata files
- Rewrite README to follow Agent Skills format (agentskills.io)
- Add Available Skills section with per-skill descriptions and trigger phrases
- Replace Claude Code plugin install with `npx skills add`
- Fix Setup section: remove deprecated GPT-4o, add recommended models from model-strategy
- Fix How It Works: use correct per-platform CLI commands
- Rename "Web" to "Browser", "desktop" to "computer" for consistency
- Add Skill Structure section
Consolidate web, computer, android, and ios plugins into one unified
plugin so users can install all skills with a single command:
/plugin install midscene-automation@midscene-marketplace
setup.json files were static and never dynamically updated, duplicating
information already present in each skill's SKILL.md. Remove all 4
setup.json files and update references in SKILL.md and README.md.
Streamline the setup process to match agent-browse's approach:
- Remove manual pnpm install/build steps (handled by postinstall)
- Use MIDSCENE_MODEL_* environment variables instead of .env file
- Add .env.example with official Midscene configuration format
- Update documentation to show 3-step quick install
quanruzhuoxiu