Agent skill

Pkulaw

北大法宝官方法律检索 MCP Skill。涉及「法律」「法规」「法条」「司法解释」「判例」「案号」「类案」「合同审查」「合规清单」「裁判规则」「指导案例」「劳动争议」「民法典」「公司法」「数据合规」等关键词时使用。提供 5 个工具：法条语义检索 searcharticle、法条精确查询 getarticle、法规列表 getlawlist、案例语义检索…

AGPL-3.0Auto-check passed

Install Pkulaw

skills CLI

$ npx skills add rongxinzy/RongxinAI --skill pkulaw -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install rongxinzy/RongxinAI pkulaw --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/MCPs/pkulaw/skills .claude/skills/pkulaw && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "pkulaw" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/pkulaw/skills into .claude/skills/pkulaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pkulaw", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/pkulaw/skills

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add rongxinzy/RongxinAI --skill pkulaw -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install rongxinzy/RongxinAI pkulaw --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .agents/skills && cp -r skills-src/MCPs/pkulaw/skills .agents/skills/pkulaw && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "pkulaw" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/pkulaw/skills into .agents/skills/pkulaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pkulaw", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add rongxinzy/RongxinAI --skill pkulaw -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install rongxinzy/RongxinAI pkulaw --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/MCPs/pkulaw/skills .cursor/skills/pkulaw && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "pkulaw" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/pkulaw/skills into .cursor/skills/pkulaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pkulaw", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/rongxinzy/RongxinAI.git --path MCPs/pkulaw/skills

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add rongxinzy/RongxinAI --skill pkulaw -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install rongxinzy/RongxinAI pkulaw --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/MCPs/pkulaw/skills .gemini/skills/pkulaw && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "pkulaw" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/pkulaw/skills into .gemini/skills/pkulaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pkulaw", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install rongxinzy/RongxinAI pkulaw

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add rongxinzy/RongxinAI --skill pkulaw -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .github/skills && cp -r skills-src/MCPs/pkulaw/skills .github/skills/pkulaw && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "pkulaw" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/pkulaw/skills into .github/skills/pkulaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pkulaw", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add rongxinzy/RongxinAI --skill pkulaw -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install rongxinzy/RongxinAI pkulaw --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/MCPs/pkulaw/skills .opencode/skills/pkulaw && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "pkulaw" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/pkulaw/skills into .opencode/skills/pkulaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pkulaw", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: pkulaw
GitHub stars: 154
Token cost: ~1.7k tokens
SKILL.md length: 429 words
Files: 1
Skills in repo: 94
Repo updated: Oct 10, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

Works in 11 steps: 不凭记忆答法条 / 案号——即使你"记得"，也必须先调用工具拿到真实原文。 → 每条法律依据必须附 url（pkulaw.com 原文链接），让用户可追溯。 → 时效性强制标注——返回的 title 含 [失效] 或… → …
SKILL.md covers 一、何时使用 / 何时不用, 二、5 个可用工具, 三、参数要点 and 四、输出纪律（严格遵守）, plus 3 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pkulaw is an agent skill from rongxinzy/RongxinAI. 北大法宝官方法律检索 MCP Skill。涉及「法律」「法规」「法条」「司法解释」「判例」「案号」「类案」「合同审查」「合规清单」「裁判规则」「指导案例」「劳动争议」「民法典」「公司法」「数据合规」等关键词时使用。提供 5 个工具：法条语义检索 searcharticle、法条精确查询 getarticle、法规列表 getlawlist、案例语义检索 searchcase、案例列表（含完整判决要素）getcaselist。所有结果带 pkulaw.com 原文链接，可追溯、可复核；不构成法律意见。

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Model Context Protocol. The repository describes itself as: An all-in-one local AI Agent workspace with a fully self-developed stack. The licence is AGPL-3.0.

Example prompts

“/pkulaw”

Workflow steps

11 steps, taken from the first numbered list in SKILL.md.

不凭记忆答法条 / 案号——即使你"记得"，也必须先调用工具拿到真实原文。
每条法律依据必须附 url（pkulaw.com 原文链接），让用户可追溯。
时效性强制标注——返回的 title 含 [失效] 或 TimelinessDic 为 02 / 03 时，必须显式提示"已废止 / 已修改，仅供参考"。
效力级别排序：法律 > 行政法规 > 部门规章 > 司法解释（按 EffectivenessDic）。
新法优于旧法：同级法规并存时，按 IssueDate / ImplementDate 取最新版本；若引用旧法案例（裁判日期早于现行法生效日），必须提示"该判例适用旧法，参考价值有限"。
特别法优于一般法：例如「公司法 vs 民法典」、「劳动合同法 vs 民法典」涉及该领域时，特别法优先适用。
案例参考力度：指导案例（应当参照）> 公报案例（高度参考、无拘束力）> 普通判例（仅供参考）。引用时必须说明力度等级；引用普通判例需附"最终判决以法院裁量为准"。
裁判倾向：多条判例不一致时，按 LastInstanceCourt（审理法院）/ LastInstanceDate（裁判日期）标注差异，给出"主流裁判倾向 + 少数派观点"，不要只挑一个判例当唯一答案。
空结果不编造：工具返回为空时如实说"未在北大法宝库中检索到相关条文 / 案例"，并降级建议（关键词检索 0 命中 → 改语义检索；语义检索 0 命中 → 让用户拆词或换角度）。
数据使用边界：单次返回上限 10 条；禁止把多条 content / FullText 字段拼接成数据集；用户请求"把所有判决书原文拼给我"应礼貌拒绝并解释。
不替代律师：本服务提供资料检索与研究辅助，不构成法律意见。涉及具体案件处理 / 对外文书签发，回答末尾必须附"建议咨询执业律师"。

What it can do on your machine

Read from SKILL.md and the folder at commit 9c64865. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- mcp.pkulaw.com
- pkulaw.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pkulaw loads about 1.7k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 429 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~67
When it runs · the whole SKILL.md, loaded when a task matches: ~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from rongxinzy/RongxinAI at commit 9c64865, republished under its AGPL-3.0 licence (© rongxinzy). 429 words, ~1,744 tokens.

Download SKILL.mdSave it as .claude/skills/pkulaw/SKILL.md (or your agent's skills folder).

name: pkulaw
description: 北大法宝官方法律检索 MCP Skill。涉及「法律」「法规」「法条」「司法解释」「判例」「案号」「类案」「合同审查」「合规清单」「裁判规则」「指导案例」「劳动争议」「民法典」「公司法」「数据合规」等关键词时使用。提供 5 个工具：法条语义检索 search_article、法条精确查询 get_article、法规列表 get_law_list、案例语义检索 search_case、案例列表（含完整判决要素）get_case_list。所有结果带 pkulaw.com 原文链接，可追溯、可复核；不构成法律意见。
description_zh: 北大法宝官方法律检索 MCP Skill。涉及法律、法规、法条、司法解释、判例、案号、类案、合同审查、合规清单、裁判规则、指导案例、劳动争议、民法典、公司法、数据合规等关键词时使用。提供 5 个工具，覆盖中国法规与司法案例双库；每条结果带 pkulaw.com 原文链接，可追溯、可复核；不构成法律意见。
description_en: PKULaw official legal search MCP Skill. Use when the user mentions Chinese laws, regulations, articles, judicial interpretations, court cases, case numbers…
version: 1.1.0
author: 北京北大英华科技有限公司（北大法宝）

北大法宝·法律智能检索

接入北大法宝（pkulaw.com）权威法律知识库，覆盖宪法、法律、行政法规、地方性法规、部门规章、司法解释，以及最高人民法院与各级法院的判决书 / 裁定书 / 调解书。所有法律结论必须落到工具返回结果，禁止凭模型记忆作答。

一、何时使用 / 何时不用

应使用本 Skill 的场景

查询中国大陆现行有效或历史法规、司法解释原文
检索司法判例、类案研判、裁判规则提取
写法律意见书、合同审查、合规清单时寻找权威依据
用户引用「《XX 法》第 XX 条」需要核实原文

不应触发本 Skill 的场景

用户请求	原因	建议回复
境外法（美国、欧盟、港澳台等）	数据仅覆盖中国大陆	"本工具仅覆盖中国大陆法律；境外法请咨询涉外律师"
个人案件结果预测（"我能赢吗"）	司法裁量不可机械推断	"无法预测具体案件走向，可检索类案供参考决策"
个人征信 / 个人金融数据	非本工具数据范畴	"请使用其他征信类服务"
律师推荐 / 案件代理	非数据检索范畴	"请通过律协或正规渠道选择执业律师"
批量抽取判决书 / 法规数据集	数据使用边界	"单次最多 10 条，禁止用于模型训练或批量抽取"
实时舆情 / 新闻法律评论	非法规与判例数据	礼貌拒绝

二、5 个可用工具

工具	用途	优先选择条件
`search_article`	法条语义检索：自然语言问题 → 相关法条	用户描述事实/问题，未给出具体法律名+条号
`get_article`	法条精确查询：法律名 + 条号 → 完整条文原文	用户明确说"《X 法》第 X 条"这种引用
`get_law_list`	法规列表：关键词 → 前 10 部相关法规（含时效、效力级别、文号、发文机关）	用户要"列一下与 XX 相关的法规 / 做合规清单 / 立法追踪"
`search_case`	案例语义检索：自然语言案情 → 类案（轻量摘要 + 案号 + 法院 + 链接）	用户问"有没有类似案例 / 法院怎么判"
`get_case_list`	案例列表（深度版）：关键词 → 前 10 个判例 + 25+ 字段判决书要素（查明事实、争议焦点、裁判理由、裁判依据、裁判结果）	用户要做类案研判 / 写法律意见书 / 提取裁判要旨

工具名以连接握手后 tools/list 为准；本文档默认使用上表名称。

工具选择决策树

用户提问
   │
   ├─ 要"法律法规"？
   │     ├─ 已给法律名 + 条号 → get_article（精确取原文）
   │     ├─ 描述事实/问题想找依据 → search_article（语义检索法条）
   │     └─ 要列一批法规 / 合规清单 / 立法追踪 → get_law_list（关键词 + 元数据筛选）
   │
   └─ 要"司法案例"？
         ├─ 自然语言案情找几个类案参考 → search_case（轻量摘要）
         └─ 类案研判 / 写意见书 / 提取裁判要旨 → get_case_list（25+ 字段深度）

复杂任务（法规依据 + 类案支撑），按顺序：
  1. search_article 或 get_law_list 找法规
  2. search_case 或 get_case_list 找类案
  3. 必要时 get_article 精确取关键条文原文

三、参数要点

`search_article` —— 法条语义检索

query (string, 必填)：自然语言问题，保留用户原话，不要改写为"XX 法规"等术语，会损失语义信息。

`get_article` —— 法条精确查询

title (string, 必填)：法律名，简称或全称均可（"民法典" 或 "中华人民共和国民法典"）
number (string, 必填)：中文数字 + "第…条"（如 "第五百八十五条"）；不要传阿拉伯数字 "585"

`get_law_list` —— 法规列表（关键词）

title (string, 可选)：标题关键词
fulltext (string, 可选)：正文关键词
title 与 fulltext 至少填一个；同时填范围更精确
返回前 10 条；FullText 字段固定为 null，要单条全文请改用 get_article
重点字段：TimelinessDic（01=现行有效 / 02=废止 / 03=已修改）、EffectivenessDic（效力级别）、DocumentNO（文号）、IssueDepartment（发文机关）

`search_case` —— 案例语义检索

text (string, 必填)：自然语言案情描述
返回 case_number（案号）、court_name（审理法院）、decision_date、cause_of_action（案由）、content（摘要）、url

`get_case_list` —— 案例列表（含完整要素）

title (string, 可选)：案件标题关键词
fulltext (string, 可选)：判决书正文关键词
至少填一个；返回前 10 条，单条 25+ 字段
核心 5 字段：Ascertain（查明事实）→ ControversialFocus（争议焦点）→ Identified（裁判理由）→ RefereeBasis（裁判依据，已援引法条）→ RefereeResult（裁判结果）
CaseGrade（指导案例 / 公报案例 / 普通案例）决定参考权重

四、输出纪律（严格遵守）

不凭记忆答法条 / 案号——即使你"记得"，也必须先调用工具拿到真实原文。
每条法律依据必须附 url（pkulaw.com 原文链接），让用户可追溯。
时效性强制标注——返回的 title 含 [失效] 或 TimelinessDic 为 02 / 03 时，必须显式提示"已废止 / 已修改，仅供参考"。
效力级别排序：法律 > 行政法规 > 部门规章 > 司法解释（按 EffectivenessDic）。
新法优于旧法：同级法规并存时，按 IssueDate / ImplementDate 取最新版本；若引用旧法案例（裁判日期早于现行法生效日），必须提示"该判例适用旧法，参考价值有限"。
特别法优于一般法：例如「公司法 vs 民法典」、「劳动合同法 vs 民法典」涉及该领域时，特别法优先适用。
案例参考力度：指导案例（应当参照）> 公报案例（高度参考、无拘束力）> 普通判例（仅供参考）。引用时必须说明力度等级；引用普通判例需附"最终判决以法院裁量为准"。
裁判倾向：多条判例不一致时，按 LastInstanceCourt（审理法院）/ LastInstanceDate（裁判日期）标注差异，给出"主流裁判倾向 + 少数派观点"，不要只挑一个判例当唯一答案。
空结果不编造：工具返回为空时如实说"未在北大法宝库中检索到相关条文 / 案例"，并降级建议（关键词检索 0 命中 → 改语义检索；语义检索 0 命中 → 让用户拆词或换角度）。
数据使用边界：单次返回上限 10 条；禁止把多条 content / FullText 字段拼接成数据集；用户请求"把所有判决书原文拼给我"应礼貌拒绝并解释。
不替代律师：本服务提供资料检索与研究辅助，不构成法律意见。涉及具体案件处理 / 对外文书签发，回答末尾必须附"建议咨询执业律师"。

五、典型场景

场景 A：法律咨询（法规 + 类案）

用户："员工连续旷工三天，公司能否解除劳动合同？"

正确路径：

search_article({"query": "员工连续旷工三天公司能否解除劳动合同"}) → 取《劳动合同法》第三十九条、第四十六条等真实返回
search_case({"text": "员工连续旷工公司解除劳动合同"}) → 看裁判倾向
输出结构：结论 + 法规依据（含 url）+ 类案参考（案号+法院+url）+ 待复核点（规章制度公示送达、考勤证据等）+ 律师建议

Show full SKILL.md (176 more words)Show less

场景 B：合同条款核查

用户："合同里写『甲方可随时单方解除合同且不承担任何责任』，这条款有没有问题？"

正确路径：

search_article({"query": "单方解除合同不承担责任格式条款"}) → 找民法典格式条款规则
get_article({"title": "民法典", "number": "第四百九十六条"}) 取格式条款定义，必要时再 get_article({"title": "民法典", "number": "第四百九十七条"}) 取无效情形
输出"风险等级 + 法条原文（含 url）+ 建议修改方向"

场景 C：精确法条引用（写文书时）

用户："查一下《民法典》第一千零七十七条的完整原文。"

正确路径：

get_article({"title": "民法典", "number": "第一千零七十七条"})
完整展示 article 字段 + url；不主动解读，除非用户接着问

场景 D：合规清单（元数据筛选）

用户："列一下当前现行有效的、关于「数据安全」的中央层级法规。"

正确路径：

get_law_list({"title": "数据安全"}) → 取前 10 部
按 TimelinessDic="01"（现行有效）过滤
按 EffectivenessDic 分组（法律 / 行政法规 / 部门规章 / 司法解释）
每条附 DocumentNO（文号）+ IssueDepartment（发文机关）+ ImplementDate（实施日期）+ Url

场景 E：类案研判（写法律意见书）

用户："查询房屋租赁押金返还相关判例，对比不同法院的裁判倾向。"

正确路径：

get_case_list({"title": "租赁合同", "fulltext": "押金"}) → 取前 10 个判例 25+ 字段
按 CaseGrade 优先级排序：指导案例 → 公报案例 → 普通案例
逐条列出 Ascertain（查明事实）→ ControversialFocus（争议焦点）→ Identified（裁判理由）→ RefereeBasis（裁判依据）→ RefereeResult（裁判结果）
按 LastInstanceCourt 标注法院差异，输出"主流裁判倾向 + 少数派观点"
每条附 CaseFlag（案号）+ Url

场景 F：工具返回为空（防幻觉演练）

用户："查《银河系劳动合同管理条例》"（虚构法规）。

正确路径：

get_law_list({"title": "银河系劳动合同管理"}) → 工具返回 []
不要编造法规名 / 文号 / 条文
输出："未在北大法宝库中检索到《银河系劳动合同管理条例》。如果您指的是中国现行劳动合同相关法规，可以改问『劳动合同法相关规定』，或提供更准确的法规名称重试。"

六、认证说明（OAuth 2.1 + PKCE）

本 Connector 通过 MCP OAuth 2.1 Authorization Code + PKCE + RFC 7591 Dynamic Client Registration 授权（与 qcc-company 同款）。WorkBuddy 首次连接时自动打开浏览器跳转 cas.pkulaw.com，用户用 mcp.pkulaw.com 账号登录授权后自动回拉，用户无需手动填写 Token；过期会用 refresh token 自动续期。

若用户报 401 / 403：

在 mcp.pkulaw.com → 我的应用 → 订阅 5 个底层 MCP 服务（法规-关键词 / 法规-语义 / 案例-关键词 / 案例-语义 / 精准法条-关键词）
或在 WorkBuddy 连接器页面点 "重新连接" 触发授权流程

七、数据来源与免责声明

数据来源：北大法宝（pkulaw.com），北京北大英华科技有限公司自有版权数据库
数据范围：中国大陆宪法、法律、行政法规、地方性法规、部门规章、司法解释 + 最高人民法院与各级法院公开判决书 / 裁定书 / 调解书；不含港澳台地区与外国法
数据时效：实时同步北大法宝主库；废止 / 已修改法规在 TimelinessDic 字段标注
免责声明：本服务提供法律资料检索与研究辅助，不构成法律意见。具体案件处理请咨询执业律师，或前往 pkulaw.com 核实最新版本

Files

Just SKILL.md in MCPs/pkulaw/skills of rongxinzy/RongxinAI.

Open the folder on GitHubat commit 9c64865

Compare with similar skills

Pkulaw next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pkulaw compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Pkulaw this skillrongxinzy/RongxinAI	154	—	~1.7k	Automated safety check: Pass	AGPL-3.0	yesterday
MCP Server Builderanthropics/skills	180k	63 repos	~2.3k	Automated safety check: Pass	Apache-2.0	yesterday
MCP Server BuildershareAI-lab/learn-claude-code	78k	4 repos	~1.2k	Automated safety check: Pass	MIT	12 days ago
MCP Integration for Pluginsanthropics/claude-plugins-official	38k	11 repos	~3.1k	Automated safety check: Pass	Apache-2.0	today
Figma use_figma Plugin API Ruleswarpdotdev/warp	65k	4 repos	~4.4k	Automated safety check: Pass	AGPL-3.0	today
Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills	8.5k	6 repos	~3.2k	Automated safety check: Notes	Apache-2.0	1 mo ago

Similar skills

MCP Server Builder
anthropics/skills
Official
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
180k GitHub starsUsed in 63 repos~2.3k tokens
Agent WorkflowsAuto-check passed
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
78k GitHub starsUsed in 4 repos~1.2k tokens
Agent WorkflowsAuto-check passed
MCP Integration for Plugins
anthropics/claude-plugins-official
Official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
38k GitHub starsUsed in 11 repos~3.1k tokens
Agent WorkflowsAuto-check passed
Figma use_figma Plugin API Rules
warpdotdev/warp
Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.
65k GitHub starsUsed in 4 repos~4.4k tokens
Frontend & DesignAuto-check passed
Stitch to Remotion Walkthrough Videos
google-labs-code/stitch-skills
Official
Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.
8.5k GitHub starsUsed in 6 repos~3.2k tokens
Media & CreativeAuto-check: notes
MCP Development
coollabsio/coolify
A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.
63k GitHub starsUsed in 1 repo~949 tokens
Frontend & DesignAuto-check passed

Questions about Pkulaw

What does Pkulaw do?

How do I install Pkulaw in Claude Code?

Run `npx skills add rongxinzy/RongxinAI --skill pkulaw -a claude-code`. Or copy the skill folder (MCPs/pkulaw/skills in rongxinzy/RongxinAI) into .claude/skills/pkulaw in your project. Claude Code loads it when a task matches its description.

How do I install Pkulaw in Codex?

Run `npx skills add rongxinzy/RongxinAI --skill pkulaw -a codex`. Or copy the skill folder (MCPs/pkulaw/skills in rongxinzy/RongxinAI) into .agents/skills/pkulaw in your project. Codex loads it when a task matches its description.

Can I use Pkulaw in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rongxinzy/RongxinAI --skill pkulaw -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pkulaw, .gemini/skills/pkulaw, .github/skills/pkulaw and .opencode/skills/pkulaw in your project.

What does Pkulaw need to run?

SKILL.md names no scripts, command-line tools or credentials: Pkulaw is instructions for the agent only.

Does Pkulaw access the network?

SKILL.md names 2 domains. As links in the text: mcp.pkulaw.com and pkulaw.com. This is read from the text; nothing was executed.

Is Pkulaw safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pkulaw use?

Pkulaw is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pkulaw use?

About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pkulaw?

Skills that share tags, products or a category with Pkulaw: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pkulaw?

rongxinzy (a GitHub organization) maintains it in rongxinzy/RongxinAI, which has 154 GitHub stars. The repository holds 94 skills in this directory. The repository was last updated on October 10, 2026.

Source: rongxinzy/RongxinAI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Pkulaw

Facts

At a glance

What it does

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

北大法宝·法律智能检索

一、何时使用 / 何时不用

应使用本 Skill 的场景

不应触发本 Skill 的场景

二、5 个可用工具

工具选择决策树

三、参数要点

search_article —— 法条语义检索

get_article —— 法条精确查询

get_law_list —— 法规列表（关键词）

search_case —— 案例语义检索

get_case_list —— 案例列表（含完整要素）

四、输出纪律（严格遵守）

五、典型场景

场景 A：法律咨询（法规 + 类案）

场景 B：合同条款核查

场景 C：精确法条引用（写文书时）

场景 D：合规清单（元数据筛选）

场景 E：类案研判（写法律意见书）

场景 F：工具返回为空（防幻觉演练）

六、认证说明（OAuth 2.1 + PKCE）

七、数据来源与免责声明

Files

Compare with similar skills

Similar skills

More from rongxinzy/RongxinAI

Related

Questions about Pkulaw

`search_article` —— 法条语义检索

`get_article` —— 法条精确查询

`get_law_list` —— 法规列表（关键词）

`search_case` —— 案例语义检索

`get_case_list` —— 案例列表（含完整要素）