All skills
cat-xierluo avatar

/legal-skill-evaluation

@9be736d

法律 Skill 分层质量评测工具。消费 skill-lint 的通用质量结论,再用三份测试材料、通用六维度、场景微调和律师 taste 评估法律产出,并定位最小修复单元。本技能应在审查、回归验证或发布验收法律 Skill 时使用。不要用于代替通用 Skill lint、正式法律意见或跨场景排名。

Use this Skill: https://skilld.dev/gh/cat-xierluo/legal-skills/legal-skill-evaluation

This session only. Nothing lands on disk.

evalscase-analysis-20260808semantic-casesobjective-missing.md

≈166 tokens on demand. Your agent reads this file only when SKILL.md points to it.

SEMANTIC-CASE: 分析目标缺失时不得自行选择

  • id: CASE-OBJ-MISSING
  • 触发:输入含案件材料但 deliberately 缺「分析目标」(见 materials/peer-unfamiliar.md)
  • 期望行为:候选须显式请求确认分析目标(如"请确认本轮目标是评估是否起诉 / 出具客户说明 / 形成谈判方案"),不得自行选定目标并直接产出终局结论。
  • 判定要点:
    • 产出须出现"目标/用途/请确认"类请求表述;
    • 不得在未确认目标前给出"建议起诉/不建议起诉"等终局性结论。
  • 来源:legal-case-analysis SKILL.md 核心原则——"分析目标决定输出形态"。

Source: SKILL.md on GitHub

No alerts10d3 checks · Risk SAFE
  • Gen Agent Trust Hub10d

    A comprehensive evaluation framework for legal AI skills designed to assess legal accuracy, fact faithfulness, and adherence to professional tastes. It includes Python scripts for automated quality gates, hashing, and execution probes. No malicious patterns were detected; the automated scripts are functionally aligned with the skill's primary purpose as a testing and evaluation harness.

  • Socket10d

    No alerts

  • Snyk10d

    Risk: LOW · No issues

Signed by skilld at 9be736d. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 weeks ago
version
0.8.12
author
杨卫薪律师(微信ywxlaw)
homepage
https://github.com/cat-xierluo/legal-skills

README badge

README badge for cat-xierluo/legal-skills/legal-skill-evaluation