Case Progress logo

Case Progress

Community
cat-xierluo
case-progress

案件进度与状态台账管理。案件 case.yaml 的唯一写入引擎(新增任务、推进任务、登记期限、更新案件阶段、校验、存量迁移),Agent 会话的进度加载与写回契约,以及案件进度监控对账。当用户或 Agent 需要"更新案件进度/推进任务/登记期限/更新案件阶段/同步案件状态/校验或迁移案件数据/查看案件结构化状态"时使用。不要用于:看板展示与周研判(用 case-dashboard)、案件建档初始化(用 new-case)。

Overview

Publishercat-xierluo
Repositorylegal-skills
Skill namecase-progress
Stars
722
Forks
109
Bundled files
4
LicenseCC-BY-NC
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by cat-xierluo on GitHub. Read the source before you install it.

Installation

Install the Case Progress AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/cat-xierluo/legal-skills/tree/main/skills/case-progress
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git /tmp/legal-skills
mkdir -p .claude/skills
cp -r /tmp/legal-skills/skills/case-progress .claude/skills/case-progress
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Case Progress in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Case Progress on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Case Progress is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

case-progress - 案件进度与状态管理(办案进度台账)

状态:v0.1.0 骨架。设计真值见消费项目 SuitAgent docs/case-dashboard与数据真值方案.md(v1.5,决策 #045/#046)。

职责

功能形式
状态写入scripts/case_store.py CLI:show / list / add-task / set-status / add-deadline / set-stage / set-fields / validate / migrate / render(audit / report 留 M6)
视图渲染render <短码>:生成 案件视图.md + 案件视图.html(00 目录,一页纸派生视图,勿手改);每次写入自动刷新已存在的视图文件——无需 hooks 即保持新鲜
会话契约references/contract.md:Agent 会话开始 show 加载状态 + 按 context 指针读叙事文档;结束经 CLI 写回,禁止手改 yaml
列表写入陷阱(set-fields)set-fields 的列表是整体替换而非追加:传 {"任务": [新增一条]} 会把该列表原有的全部条目冲掉。schema 校验(每行需 source)拦不住"漏传其余条目"——新条目若恰好带合法 source,校验直接通过、数据已被清空。追加一条前必须先 show/读出该列表全量,把原条目 + 新条目一起传入;写入后立刻复核条数与关键 id,异常从备份恢复
项目管理/progress 命令:自然语言驱动任务/期限/阶段操作,明确操作直路由本 CLI,语义复杂转入下方"工作流收尾状态同步"流程
数据契约references/schema.md:case.yaml v4.0 字段字典——唯一权威版本,其他 skill 只引用不复制
监控对账M6(远期):audit 子命令 + hooks 挂点(PostToolUse 记账 / Stop·SubagentStop 结账 / SessionStart 预警)

开发红线

  1. 路径解算禁止 __file__.resolve()(符号链接安装会穿透回本仓库):项目根用 cwd 向上发现(找到含 6 位数字开头案件目录的祖先)或 --root / SUITAGENT_ROOT 指定。
  2. 单一写入实现:一切对 case.yaml 的写入必须经本引擎——schema 校验 → 行级 source 保护(永不覆写 source: user 行;"已结案"仅手工标记,永不自动推断)→ flock → 临时文件 + os.replace 原子替换。
  3. schema 唯一权威:字段字典只在本 skill 维护;case-dashboard 等消费方引用版本号,不复制内容。
  4. 运行时数据绝不入 skill 目录(本仓库公开):case.yaml、.audit.jsonl 等全部落消费项目案件目录。
  5. 被调方式:其他 skill(如 case-dashboard 的 server)经 subprocess 调用本 CLI,禁止跨 skill Python import。
  6. 统计 yaml 列表条数必须按顶级键切片:case.yaml 里 案件时间线 之外还有 法定期限、开庭与听证、工时记录 等多个日期列表,跨列表 grep -c "^- 日期: " 得到的数字与目标列表无关(曾把"没丢数据"误判成"丢了 40 多条",又靠它掩盖了真丢 7 条)。用 case_store.py show <短码> 或从顶级键截到下一个非缩进行统计。写入前 cp case.yaml /tmp/case.yaml.bak 留底,可一键回滚。

目录结构

scripts/      case_store.py(CLI + 库 + audit)—— M2 实现
references/   schema.md(v4.0 字段字典)、contract.md(会话契约)—— M3a 起充实

工作流收尾状态同步(主 Agent 直执行,skill 间协作,不派 subagent)

消费项目复合工作流(被告应诉、证据质证等七场景)在 Reporter 之后、或用户说"同步案件进度/根据新文书更新案件"时,主 Agent 按以下流程直接执行:

  1. 加载状态:show <案件短码>
  2. 盘点产出:列出本次工作流涉及的 02–11 目录新文件;读关键文件(判决书/传票/新文书)提取事件要素
  3. 映射判断:产出 → 语义变更(新任务 / 任务完成 / 新期限 / 阶段推进 / 时间线事件)
  4. CLI 写回:add-task / set-status / add-deadline / set-stage(AI 身份,不带 --actor user)
  5. 工时记录(必做):log-work <短码> <时长|auto|?> <本次工作摘要> [--task] [--file 产出文书] [--type]——AI 协作完成的每项工作(文书起草/研究/分析/整理)都边完成边记录:内容与关联文书/任务自动携带。时长三态:用户明示实际值(如"花了一下午"→4h)优先;未明示传 auto——按工作类型取参考默认(出庭 2h 为底线)(参考默认:文书·研究 1h,核查·沟通·整理 0.5h,出庭 2h 为实务底线;类型可从内容推断——AI 生成快但律师核查/修改的真实成本计入,可按实际上下调整);? 仅在用户明确不想估时使用
  6. 校验与汇报:validate 通过后输出变更清单与待确认项

执行纪律:永不手改 yaml;期限需含起算日与法律依据,不确定列入待确认项不臆造;人工覆盖保护(source=user 行只提示不改写、已结案永不设置、锁定阶段不改写);输出简短 Markdown 变更清单,不产出文件。

与周边的关系(案件生命周期接力)

  • new-case:创建案件目录与初始 case.yaml(v4.0 模板),本 skill 的数据生产上游
  • case-dashboard:视图层,经本 CLI 读写,只消费不另写
  • 主 Agent(skill 间协作):工作流收尾的状态同步由主 Agent 按上述流程直接执行,不依赖 subagent(架构决策:skill 协作为主,消费项目后续可能整体淘汰 subagent 派发)
  • DataRules.md(消费项目 .claude/rules/):会话契约的规则层,指向本 skill

路线图

M2 写入引擎 → M3a v4.0 数据模型 → M3b 轻量写回入口 → M4 存量迁移 → M6 hooks 监控(远期)。详见 TASKS.md 与消费项目方案。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Case Progress AI skill do?

案件进度与状态台账管理。案件 case.yaml 的唯一写入引擎(新增任务、推进任务、登记期限、更新案件阶段、校验、存量迁移),Agent 会话的进度加载与写回契约,以及案件进度监控对账。当用户或 Agent 需要"更新案件进度/推进任务/登记期限/更新案件阶段/同步案件状态/校验或迁移案件数据/查看案件结构化状态"时使用。不要用于:看板展示与周研判(用 case-dashboard)、案件建档初始化(用 new-case)。

Why use Case Progress on TypingMind?

Because you install it once and use it with any model. Case Progress is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Case Progress in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cat-xierluo/legal-skills/tree/main/skills/case-progress. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Case Progress?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Case Progress?

As many as you like. As long as a model supports skills, you can use Case Progress with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Case Progress AI skill free?

Yes. It is published on GitHub by cat-xierluo under the CC-BY-NC license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇