OpenClaw 三本说明书生成器
AdvisoryAudited by Static analysis on May 1, 2026.
Overview
No suspicious patterns detected.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Saving these files can change how the AI behaves in later sessions.
The skill is designed to write generated SOUL.md, USER.md, and AGENTS.md files after preview and user confirmation. This is expected for the purpose, but it modifies local agent configuration files.
展示文件内容，请用户确认 ... 都满意 → 写入文件，给出使用建议
Read the generated files before approving the write, and confirm the target location if existing SOUL.md, USER.md, or AGENTS.md files could be overwritten.
Personal preferences, work details, schedules, and privacy notes may be stored in files that future agents read.
The generated USER.md is meant to persist user identity, work context, preferences, and privacy boundaries for future agent use. This is aligned with customization, but it creates reusable personal context.
USER.md — 用户的身份、工作场景、沟通偏好、隐私边界
Do not include secrets, credentials, private account details, or sensitive personal information unless you are comfortable storing them locally in these manuals.
Installing recommended skills could add new capabilities or permissions not covered by this skill’s artifacts.
The skill recommends follow-on installation of other skills after generation. It does not auto-install them, but those additional artifacts are outside this review.
安装 `workspace-bootstrap` ... 安装 `scenario-sop` ... 安装 `memory-tiering`
Review each recommended skill independently before installing it.