用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/Changhochien/financial-services-hermes --skill model-update命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | model-update |
| description | Use when financial-services work requires model Update. |
| version | 0.1.0 |
| author | Changhochien |
| license | MIT |
| platforms | ["linux","macos","windows"] |
| metadata | {"hermes":{"tags":["equity-research","financial-services","research"],"related_skills":[]}} |
description: Update financial models with new data — quarterly earnings, management guidance, macro changes, or revised assumptions. Adjusts estimates, recalculates valuation, and flags material changes. Use after earnings, guidance updates, or when assumptions need refreshing. Triggers on "update model", "plug earnings", "refresh estimates", "update numbers for [company]", "new guidance", or "revise estimates".
Determine the update trigger:
Update the model with reported actuals:
| Line Item | Prior Estimate | Actual | Delta | Notes |
|---|---|---|---|---|
| Revenue | ||||
| Gross Margin | ||||
| Operating Expenses | ||||
| EBITDA | ||||
| EPS | ||||
| [Key metric 1] | ||||
| [Key metric 2] |
Segment Detail (if applicable):
Balance Sheet / Cash Flow Updates:
Based on the new data, adjust forward estimates:
| Old FY Est | New FY Est | Change | Old Next FY | New Next FY | Change | |
|---|---|---|---|---|---|---|
| Revenue | ||||||
| EBITDA | ||||||
| EPS |
Key Assumption Changes:
Recalculate valuation with updated estimates:
| Valuation Method | Prior | Updated | Change |
|---|---|---|---|
| DCF fair value | |||
| P/E (NTM EPS × target multiple) | |||
| EV/EBITDA (NTM EBITDA × target multiple) | |||
| Price Target |
Estimate Change Summary:
Rating / Price Target:
This skill was packaged from pi-financial-services source path plugins/vertical-plugins/equity-research/skills/model-update for the Hermes financial-services profile. Use institutional data connectors first when available, cite sources, and stage outputs for qualified human review.