Position Thesis Monitor logo

Position Thesis Monitor

Community
AlphaMao1
position-thesis-monitor

将新闻、电话会、年报与日线行情和技术面变化送入统一的 Jev 监控流程,检查投资假设、解释证据冲突并按需复核。用于建立持仓监控、研究变化、检查风险或历史回放。

Overview

PublisherAlphaMao1
RepositoryAlphaMao_Skills
Skill nameposition-thesis-monitor
Stars
131
Forks
33
Bundled files
28
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.

  • 28 bundled files

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

  • Open source

    Published by AlphaMao1 on GitHub. Read the source before you install it.

Installation

Install the Position Thesis Monitor 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/AlphaMao1/AlphaMao_Skills/tree/main/skills/position-thesis-monitor
  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/AlphaMao1/AlphaMao_Skills.git /tmp/AlphaMao_Skills
mkdir -p .claude/skills
cp -r /tmp/AlphaMao_Skills/skills/position-thesis-monitor .claude/skills/position-thesis-monitor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Position Thesis Monitor 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 Position Thesis Monitor 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 Position Thesis Monitor 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.

持仓论点监控

帮助用户知道:原来的判断现在由什么证据支撑,哪里发生变化,下一步需要验证什么。Jev 是正常监控路径的必需语义模型;程序负责采集、计算、状态和预算,当前宿主的强模型负责建档、研究复核、解释与监控计划修订。

使用 TypeSafe 官方 Skill 设计或修改 Jev 问题与接入;部署包未安装该 Skill 时,按 Jev 问题设计 的官方文档入口读取当前 API 合同。不要把 Jev 降为旧流程的可选打分插件。

选择本次工作

  • 首次建立或修改判断:读 建档与监控计划。允许只有标的、没有完整论点的 Thin Start。
  • 日常扫描、年报到来或新增证据:读 执行与状态,调用 scripts/ptm.py。批量判断由代码组织,不由强模型逐条预写摘要。
  • 处理复核队列、回答变化或给出提醒:读 研究闭环。强模型完成指定问题并回填证据,不把 Jev 标签直接当投资结论。
  • 历史回放或模拟:读 回放与验收,先冻结起点和论点,再推进信息时间。
  • 选择来源或进入云端运行:读 来源与运行宿主。实际部署与可运行代码分别报告。

A:建立可执行的观察计划

用用户原话、决策机制、兑现窗口和失败条件建立少量稳定 ID 的论点。将每条论点转为可观察条件、原生更新周期、来源与相关实体、Jev 问题和补证路径。状态必须区分用户原话、用户确认、Agent 推断与模拟设定。

用户确认投资含义、行动条件、费用和数据范围。已授权范围内的问题措辞、分块和同类来源维护不逐项重新询问。已有充分材料就直接编制计划;缺失信息只问影响目标或正确性的部分。

普通用户可以只给一个标的:先用 hypotheses: [] 建立开放重大变化扫描,后续再逐步补论点。没有 thesis 不妨碍明确行动条件和官方披露监控。

B:持续证据处理

使用一条处理链、两类输入。资料面由程序提取原文与来源;行情面由程序计算日线收益、回撤、趋势、量能和相对表现。两者都形成证据事件,调用 Jev、写入同一假设信号和研究队列。行情不是仅供提醒的旁路,没新闻也不停止处理。

行情常态调用 Jev 判断趋势状态、变化性质、共同/个别市场运动,以及各假设受到的支持或压力;指标缺失返回缺口,不伪造基准或历史。数学与确定性极端风险条件由代码负责。详细协议见 统一证据流。

  1. 按来源计划取得新增材料;正式公告先读元数据,之后获取可定位正文。保留原文及采集记录。
  2. 调用 ingest 持久化证据,成功后才提交来源水位。失败来源单独记录,不能把空文本当成功。
  3. 调用 run:程序完整分块正文。先批量判断各论点的适用范围和证据性质,仅对通过的论点发起第二轮方向与反证问题。范围不符的题目根本不问方向;范围不确定的材料保留待补证,不把跳过编成模型回答。
  4. 程序先保存每个分块的原始回答,聚合到原事件和原生报告周期。相同事件重新扫描不重新调用;失败从已保存分块续跑。
  5. 正式定期报告独立建立复核义务。Jev 失败不撤销已保存事件、成功水位或已有复核任务。
  6. 对候选缺口,按计划内预算补正文、附件或指定一手来源,再处理新增证据。新增来源、开放式新机制由宿主研究处理;不要为了等第二份证据而让候选永久停滞。
  7. 使用 cycle 合并资料事件、行情观察和来源状态。程序汇合两类信号,识别一致、压力、冲突或缺口;同一标的同一监控日合并成一个研究任务。发布前的价格不能当作发布后的市场反应。
  8. 检查行动条件、预期窗口、未完成复核与来源健康。无实质变化时只记录,不强制报告;单靠行情也可以产生需要深入的问题。

后台观察量与用户可见核心指标分开;取消固定 6–12 项作为语义观察上限。按取数、语义调用、研究和用户注意力分别预算。兼容复核按原事件合并;重要事项预算不足时保留待处理义务。

C:研究与反馈

GPT 不重复每一项日线技术判断。它处理 Jev 识别但尚未解释的问题:为何两类证据冲突、是不是漏了消息、市场预期/估值或风险承受是否变化,以及应怎样更新投资判断。严重行情不得以“无新闻、论点不新鲜”停止研究;这些是任务要解决的缺口。

直接的市场/价格路径假设,可在计划明确配置 market_role: direct 与 auto_assessment: true 时按可信判断更新 supported/challenged。其他经营假设受到市场压力时进入待重估,不能把价格方向直接写成新收入或新毛利率事实。

领取 Review Job 后,阅读其证据与必要全文,检查口径、先前基线、反例及量级,完成任务要求的检查。行情和一致预期没有可靠来源就标缺口;普通事件不强制做估值和交易论证。

复核完成需回填可在原文定位的引用、事实/推断区分、受影响论点、下一观察点和通知内容。程序验证证据引用及领取权限,但这些验证不能替代强模型对结论含义的判断。

修正事实评价不会自动改写用户的命题。改变用户信念、Kill Rule 或行动意图需取得确认;改变观察问题或补证方法则作为计划修订保存和回放。对一次错误先定位输入、候选、问题、模型、代码或来源问题,再做对应修改。

输出给用户

每日记录必须回答:今天实际输入什么 → 程序/Jev 各做了什么 → 是否深入及原因 → 已完成的复核结果或明确阻塞 → 各假设前后状态 → 系统下一步与用户是否需行动。用 day 命令从实际记录导出;Jev 未调用就写未调用,未深入就不编复核结果。假设状态未变但新证据增加,也要区分。

演示先给起点的投资逻辑,再按日期展示这条链。测试分数、费用、反事实和技术修复移到附录,不与日常使用主线混排。历史输入不完整时一次说明覆盖范围,不声称已扫描全市场。

需要注意时,先给发生的事实与时点,再解释对哪一步判断有影响、当前还不能判断什么、下一次看什么。默认短通知链接到完整证据记录。

日常无变化默认不推送;用户要求每日回执时返回一两句。来源故障明确说明覆盖缺口。模拟提醒明确标“回放”,不发送成真实当前告警。

必须保持的边界

  • 输入时间以公开可知时间为准,不把报告期末或公司内部获知时间当成公众已知时间。
  • 概率是具体问题的模型输出,不是论点真实性、投资胜率或用户信心。
  • 可能发生的风险、已经发生的事实、管理层指引和日程通知分别处理。
  • 转载、多个分块、同季度反复扫描都不能增加独立证据或跨期次数。
  • 不自动下单。行动条件只产生关注与复核。
  • Key 仅从运行环境或工作区 .secrets/typesafe.env 读取;用检查命令确认状态,不读取或展示原值。
  • 回放 workspace 与 live workspace 分开;模拟命题不能直接升级为真实用户确认。
  • pilot 表示链路试运行;只有来源、持久状态、宿主定时、研究执行与通知均实际验证后才能声称持续监控启用。

运行入口

Python 3.11+,核心运行器使用标准库。PTM_WORKSPACE 或显式 --workspace 指向工作数据目录,源码目录不存放持仓、key、数据库或日志。

text
python scripts/ptm.py --workspace <持久工作区> plan <计划.json>
python scripts/ptm.py --workspace <持久工作区> ingest <case-id> <证据.json> --as-of <时点>
python scripts/ptm.py --workspace <持久工作区> run <case-id> --as-of <时点>
python scripts/ptm.py --workspace <持久工作区> cycle <case-id> <两类输入.json> --as-of <时点>
python scripts/ptm.py --workspace <持久工作区> status <case-id>
python scripts/ptm.py --workspace <持久工作区> day <case-id> --date <日期>

先运行 python -B -m unittest discover -s tests 验证本次实现,再以真实来源回放检验行为。具体参数、恢复和结果协议见执行参考;测试与回放不放入正式定时任务。

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 Position Thesis Monitor AI skill do?

将新闻、电话会、年报与日线行情和技术面变化送入统一的 Jev 监控流程,检查投资假设、解释证据冲突并按需复核。用于建立持仓监控、研究变化、检查风险或历史回放。

Why use Position Thesis Monitor on TypingMind?

Because you install it once and use it with any model. Position Thesis Monitor 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 Position Thesis Monitor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AlphaMao1/AlphaMao_Skills/tree/main/skills/position-thesis-monitor. 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 Position Thesis Monitor?

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 Position Thesis Monitor?

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

Is the Position Thesis Monitor AI skill free?

It is published on GitHub by AlphaMao1. Check the repository for licensing terms. 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 👇