面向法律工作者初始化或增量治理 AGENTS.md/CLAUDE.md：识别当前 AI harness，区分用户级、项目级和团队级指令，生成最小法律安全基线，安全合并受管区块，并在新会话中验证权限、保密、信息缺口和回溯行为。用户明确提到法律工作且要配置 harness、AGENTS.md、CLAUDE.md、agent 协作规则或 AI 使用基线时使用。不要用于合同审查、案件分析、文书起草、项目脚手架或 Skill 开发。
Ask your Agent
Use this Skill: https://skilld.dev/gh/cat-xierluo/legal-skills/legal-harness-init
This session only. Nothing lands on disk.
≈232 tokens on demand. Your agent reads this file only when SKILL.md points to it.
默认使用非识别性项目代号，不在 AGENTS.md 记录真实案号、当事人、金额或联系方式。
# 项目：{内部项目代号}
- 类型：{诉讼/非诉合同/知产/企业法务/法律研究/其他}
- 阶段：{当前阶段}
- 关键时点：{YYYY-MM-DD + 事项；未知则待补充}
- 隐私模式：{strict/local/team}
- 受控事实入口：{无 / .legal-context.local.md / 组织批准载体}
- 权威载体：{项目已有任务/期限/证据/决策/交付载体}项目类型只决定下一条必要问题：
用户不知道的字段写“待补充”，不要根据项目类型替用户生成答案。
Source: SKILL.md on GitHub
This skill is a security-focused configuration tool for legal professionals to initialize AI harnesses with safety baselines. It automates the creation of instruction files, detects installed AI platforms, and uses built-in validation scripts to prevent PII or credentials from being saved in configuration files.
No alerts
Risk: CRITICAL · 1 issue
Signed by skilld at aaee0f9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub yesterday.