liang-xiangrun Eval report.

Task wording matches this skill metadata.

• Evaluate liang-xiangrun before installing it in an agent workflow
• automation
• Browser automation workflows; Claude Code teams; builders willing to evaluate younger projects

Install handoff is available.

• npx skills add swaylq/master-skill --skill liang-xiangrun

standard package or runtime install path

• npx skills add swaylq/master-skill --skill liang-xiangrun

Good trust signals with a few areas worth checking before rollout.

• Strong shortlist
• 127 GitHub stars
• MIT

Needs review

• The skill is a role-play persona based on a real person (梁湘润) and includes a disclaimer, but the description and content may be perceived as impersonating a deceased individual. Ensure the disclaimer is always present and clear.

Usable candidate, but the agent should surface permission and audit notes before installation.

• Require human approval before installing into a real workspace.
• The skill is a role-play persona based on a real person (梁湘润) and includes a disclaimer, but the description and content may be perceived as impersonating a deceased individual. Ensure the disclaimer is always present and clear.

MIT

• MIT

no high-risk permission surface in public metadata

• Network access: medium