legal-research-claims
Skill2 starsChanged 3 months agoMITView on GitHub
把法律问题或论文命题拆成可验证论点,建立论点、支持证据、反方证据和限定条件之间的映射。用户需要论证结构、证据地图或反驳检查时使用。
In this repository9 other files it gives its agents.
The file
Files
论点与证据地图
开始前完整读取并遵守 ../legal-research/references/interaction-protocol.md,先解释当前步骤,结束时说明结果、作用和下一步,不向用户粘贴原始 JSON。
阅读 references/evidence-model.md。一个 claim 只表达一个可被支持或反驳的命题。
操作
legal-research --workspace "{workspace}" claim add \
--text "{命题}" --section "{拟放置章节}"
legal-research --workspace "{workspace}" evidence add \
--claim C0001 --source S0001 --support supports \
--pinpoint "第X条/第Y页/第Z段" --quote "{短摘录}" --verified- 对每个核心命题至少登记支持材料、可能的反例或限制条件。
- 法律规范命题优先由现行有效的一手法源支撑。
- 学术原创性命题需要文献缺口证据,不能仅凭“尚未看到”。
- 因果命题的措辞不得超过研究设计能够支持的强度。
- 同一来源可支持多个 claim,但必须分别记录对应定位。
完成后运行 legal-research audit --json。CLAIM_UNSUPPORTED 是阻断问题。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

