CSlawyer1985/legal-skillhub / skills/appeal-docs-generator
appeal-docs-generator
Verified民事二审上诉文本成套生成技能。上传一审判决书后,以民诉法为尺子逐条审查原审判决是否错误(期限/主体程序/诉请判项比对/三段论/说理/新要素六诊),结合元典连接器检索现行有效法条与类案,并做一次「当事人是否已逐条确认事实认定错误、有无新证据」的事实核对互动,最终一次生成民事上诉状、二审证据清单、支持上诉请求的法条与类案检索报告、二审授权委托书、所函、二审接待笔录、待确认事实清单等全套文本。上诉状严格套用德恒格式母版(黑体18pt居中标题/仿宋14pt正文/1.5倍行距),格式100%保留。另提供 scan 轻出口,只做上诉可行性评估与上诉费测算,不出全套文书。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 25.4 KB |
| _meta.json | config | 114 B |
| references/templates-b64.json | config | 148.9 KB |
| references/yuandian_tools_guide.md | markdown | 2.2 KB |
| references/上诉状填充字段表.md | markdown | 4.6 KB |
| references/二审风险告知要点.md | markdown | 2.2 KB |
| references/元典检索姿势.md | markdown | 4.1 KB |
| references/判决书解剖清单.md | markdown | 8.4 KB |
| references/当事人事实核对清单.md | markdown | 4.0 KB |
| references/所函模板.md | markdown | 1.2 KB |
| references/授权委托书模板.md | markdown | 1.7 KB |
| references/接待笔录模板.md | markdown | 4.1 KB |
| references/文件清单及盖章指引模板.md | markdown | 3.3 KB |
| references/检索报告模板.md | markdown | 3.1 KB |
| references/模板与排版规范.md | markdown | 5.5 KB |
| references/民诉法审查尺子表.md | markdown | 9.1 KB |
| scripts/appeal_fee_calc.py | script | 6.3 KB |
| scripts/build_pending_facts_docx.py | script | 6.9 KB |
| scripts/deadline_check.py | script | 5.0 KB |
| scripts/fill_appeal_docx.py | script | 9.8 KB |
| scripts/generate_file_list.py | script | 7.8 KB |
| scripts/render_docx.py | script | 8.6 KB |
| scripts/restore_templates.py | script | 5.7 KB |
references/元典检索姿势.md
View on GitHub<!-- Maintained by Lu Lingyan, Deheng (Wuxi) Law Firm. -->
# 元典检索姿势(上诉理由的"迅速且合理"靠这一层)
> 元典 MCP 是本技能的核心引擎,**不是可选项**。四个用途按顺序调用,前三步产出《支持上诉请求的法条与类案检索报告》。
> 工具参数速查见 `yuandian_tools_guide.md`。
---
## 第 1 步 · 法规时效性核验
目的:一审援引的法条是否现行有效?是否已被修改或废止?——这是"大前提真实性检验"的落地。
| 动作 | 工具 | 要点 |
|---|---|---|
| 取条文原文 | `yuandian_rh_ft_detail` | 传 `fgmc`(法规名)+ `ftnum`(条号);可传 `refer_date` 定位判决作出时生效的版本,用来判断"当时有效、现在已改"的情形 |
| 关键词找条文 | `yuandian_rh_ft_search` | 传 `keyword` + `fgmc` 缩小范围 |
输出:每条被一审援引的法条 → 效力状态(现行有效/已被修改/已废止)+ 原文 + 元典链接。
> ⚠️ **必须把条文原文抓下来**。只写"第××条"不写原文的报告,等于没做。
---
## 第 2 步 · 找更贴合的法条(**★ 本技能的翻盘动作**)
目的:同一组事实往往对应多个请求权基础。一审选了 A 条,可能 B 条更贴合、对我方更有利——这就是二审改判的入口。
做法:
1. 用 `yuandian_law_vector_search` 输入本案事实的自然语言描述(不带法律结论),取回条文候选(`return_num` 建议 10–15)
2. 用 `yuandian_rh_ft_search` 按关键词补充:把一审援引条文的构成要件词逐一代入,找相邻条文
3. 对候选逐条判断:
- 该条的构成要件与本案事实的吻合度
- 一审为何没援引?是遗漏,还是有意排除但未说理?
- 若改按该条,结论对我方是否更有利
4. 形成「替代路径」清单:选/不选,各写一句理由
> 逐字稿里的"法律要件再造""请求权基础重构""依托法学理论破局",落在这就是这一动作。
---
## 第 3 步 · 类案检索(穷尽三个来源)
| 顺序 | 库 | 工具 | 用法 |
|---|---|---|---|
| 1 | 普通案例库 | `yuandian_rh_ptal_search` | `ajlb` 填「民事案件」;`qw` 全文关键词;`ay` 案由 |
| 2 | 权威案例库 | `yuandian_rh_qwal_search` | `source` 筛「指导性案例/典型案例/参考案例/公报案例」——优先引用 |
| 3 | 语义兜底 | `yuandian_case_vector_search` | 用自然语言描述案件事实(覆盖前两库) |
案例详情用 `yuandian_rh_case_details`,**必须同时传 `type`(ptal / qwal)与 `ah`(案号)**。
**类案筛选标准**(不合格的不进报告):
- 审级:二审/再审改判的案例优先;同院或上级法院优先
- 争点:争点必须与本案同源,不是案由相同就算
- 结论:能推出"同类事实下应如何处理"的裁判要旨
- 时效:5 年内优先,法律修订前的案例须核对是否仍适用
输出:案号 + 法院 + 裁判要旨 + 与本案的可比点(审级/案由/争点/结论)+ 支持我方哪一项上诉请求。
> **只给结论不给案号的**"类案",一律不得进报告。
---
## 第 4 步 · 企业信息补全(当事人为公司时)
`yuandian_rh_enterpriseSearch` → 取 ID → `yuandian_rh_enterpriseBaseInfo` 补全名称、住所地、法定代表人及职务(用于上诉状当事人栏)。
需要评估对方履行能力时另用 `yuandian_rh_enterpriseExecutedPerson`(失信被执行人)。
---
## 降级模式(连接器未连接时)
不阻断生成,但必须:
1. 所有法条引用标注:`⚠️ 未经法规库核验,须执业律师逐条复核`
2. 《检索报告》降级为「法条线索清单」,明确写明未做时效性核验
3. 在交付回复与文件清单中提示律师补做检索
---
## 检索式留痕(写进报告第五节)
每次检索都记下:检索日期 · 工具 · 检索式(关键词/查询语)· 命中数 · 采用数 · 未获支持的部分。
「未获支持的部分」必须如实写——没有类案支持某项上诉请求,本身就是要告诉律师的信息。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |