investment-research
Skill1 starsChanged 3 months agoMITView on GitHub
Research companies, industries and investment theses, or analyze market sensitivity, correlation, concentration and portfolio stress using attributable evidence and aligned return data. Use for fundamental research, supply-chain questions, thesis reviews or systematic-risk analysis; not for a simple quote, portfolio bookkeeping or trade execution.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- Madkyotiger/investment-ostheir own version, first seen Nov 1, 2026
- JasmineNy/codex-skills-portfoliotheir own version, first seen Oct 20, 2026
- poorvith-mp/skills-financetheir own version, first seen Oct 11, 2026
- qihangzhang-272/agent-skill-librarytheir own version, first seen Oct 2, 2026
- shashu10/personal-finance-skillstheir own version, first seen Sep 28, 2026
- Jinx-1120/skillstheir own version, first seen Jul 29, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- edinetdb/ai-berkshire-jp★ 8same name
- qihangzhang-272/agent-skill-library★ 2same name
- shashu10/personal-finance-skills★ 2same name
- Jinx-1120/skills★ 1same name
- Madkyotiger/investment-os★ 1same name
- poorvith-mp/skills-finance★ 1same name
- JasmineNy/codex-skills-portfolio★ 0same name
- TimCodes/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository28 other files it gives its agents.
- add-commentSkill
- agent-supervisorSkill
- ai-seoSkill
- anti-goalsSkill
- bestwaySkill
- codebase-renderSkill
- competitor-profilingSkill
- copywritingSkill
- decision-reviewSkill
- directory-submissionsSkill
- explain-and-saveSkill
- happy-featSkill
- i-have-adhdSkill
- launchSkill
- learning-new-languageSkill
- lock-decisionsSkill
- moleSkill
- onboardingSkill
- open-source-reviewSkill
- pmSkill
- product-marketingSkill
- product-startupSkill
- prototype-treeSkill
- read-sessionSkill
- reverse-engineer-marketingSkill
- socialSkill
- understandSkill
- update-harnessSkill
The file
Files
Investment Research
一条投资研究流程，按问题选择证据和计算。公司研究检查业务、产业与论点；风险研究检查基准敏感度、共同风险和组合暴露。同一问题可以结合两者，不分独立技能、日常简版或深度版，也不要求用户先选模式。
一条工作流程
- 确定问题与期限。 确认研究对象、市场、截至日期、判断期限和已有同主题结论，优先复核而非重复建档。风险计算还须明确基准及选择理由、币种和区间。市场问题不索要持仓；组合问题只使用用户提供或宿主已确认的数据和权重，注明确认日期。只有缺项会改变结论时才追问。
- 取得并核查数据。 在 AgentSpace 先读工作区根的
knowledge/Invest/Reference/Agent行情数据工作流.md，沿用其选源、时效和有限回退规则，只检查本次所需能力。每个重要数字保留原始来源、观察日期或报告期、单位与币种；新闻、社交信号和图表不能代替基本面、合格收益序列或完整市场筛选。其它工作区沿用宿主来源规则，不能声称已通过 AgentSpace 校验。 - 建立解释并计算。 公司结论用披露、财务和业务证据；估值比较须有同口径同行，产业链、技术或供需分析按问题扩展。Beta、相关性、集中度或情景计算先读
resources/data-contract.md和resources/beta-methods.md，对合格的日度总回报序列使用scripts/analyze.py，不让模型心算。报告实际样本、区间、回报口径、基准、标准误或置信区间、R²和遗漏数据。多因子或非线性产品不能强塞进单因子脚本。 - 检验反方与限制。 分开事实、估算、假设、推断和缺项，检查能推翻核心论点的证据。涉及风险估计时，检查基准与区间敏感性、权重变化、异步市场、残差风险和样本不足。静态权重估计不是账户实际历史业绩，Beta 不是涨跌概率或明日预测；不编造数字、主观概率或来源。
- 结论与复核。 回答原问题，给支持证据、主要反方、适用条件、失效条件和复核期限。缺项只限制依赖它的结论；核心证据不足时列出具体缺项，不输出无依据的推荐或暴露值。可检验预测事先记录方向或条件、观察标的、基准、期限及判定方法，保留原判断和错判，不能事后换口径。研究质量、风险估计、方向判断和交易盈亏分开评估；没有基准、成本和足够样本，不声称有稳定 Alpha。
已有授权内的只读查询和本地计算直接执行。新安装、登录、购买或扩大私有访问范围按宿主规则处理；缺工具不自动变成安装任务。本技能不读取券商账户、不交易、不自动对冲。操作建议交给投资总流程结合真实持仓、预算、风险和期限处理，不把研究评级或风险估计直接变成买卖指令。
按问题读取资料
- 问题含糊：
references/stages/clarify.md。 - 证据组织与取数：
references/stages/source-map.md、resources/data-rigor.md；具体字段缺失再读resources/source-recipes.md对应条目。 - 产业链或瓶颈：
references/stages/chain-trace.md。 - 论点及反证：
references/stages/thesis-audit.md。 - 宏观状态：
references/stages/market-regime.md。 - 风险暴露：
references/stages/factor-exposure.md。 - 相关与集中：
references/stages/correlation-risk.md。 - 压力情景：
references/stages/stress-test.md、resources/scenario-library.md。 - 组合综合检查：
references/stages/portfolio-audit.md。 - 完成交付前：
references/stages/report-quality.md。
只读相关模块。resources/research-tool-stack.md、resources/data-providers/ 是能力参考，不是每次执行的前置清单；其安装、格式与旧运行建议不覆盖本入口和宿主授权、数据规则。阶段模板仅是需要时的字段参考，不要求每次生成所有文件。
可重复运行的风险计算
输入契约和命令见 resources/data-contract.md。scripts/analyze.py 仅用 Python 标准库，离线读取已准备的 JSON，输出计算及逐项数据限制，不联网、不读账户、不安装依赖。
支持单基准 OLS、HC1 标准误、95% 渐近区间、滚动 Beta、共同区间相关矩阵、显式固定权重组合和单基准情景近似。默认至少 60 个共同回报区间、252 区间滚动窗口；不足时不伪造结果。这些是计算约定，不是策略有效性证明。多因子、自动全市场取数、基金实时估值、风险平价和实盘执行不在此脚本能力内。
记录与交付
默认中文 Markdown，正式报告是唯一正文。资料、计算输入和必要复现记录放宿主指定目录；在 AgentSpace 使用 finance/data/research/<topic>/，正式研究按根规则进入 knowledge/Invest/Research/。持仓和日报仍沿用投资总流程，不新建第二套记录。
用户明确要 HTML 时，才读取 resources/report-visual-system.md、resources/citation-system.md 以及适合问题的 templates/report.html 或 templates/beta-report.html。HTML 不是另一套研究流程，不能用可视化掩盖数据缺失。
需要记录过程时使用统一的 templates/run-log.md；论点预测按 templates/thesis-card.md 记录。复核区分未到期、条件未触发、无法评估、支持与否定，不把未触发计为成功。
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.