Communitygithub.com

oyi77/1ai-skills

用於追蹤投資組合公司KPI、差異分析、回報分析。當使用者說「監控投資組合」、「追蹤KPI」、「投資組合回報」時使用。

1ai-skills 是什麼?

Portfolio Monitor 技能專為私募股權基金經理人設計,靈感來自 anthropics/financial-services 的 portfolio-monitoring 技能。其核心理念是「型態辨識」:在資產惡化變得明顯之前及早發現,領先指標勝過落後指標。該技能涵蓋完整的投資組合監控工作流程:數據擷取 → 追蹤 → 分析 → 報告。支援的關鍵功能包括追蹤 KPI(如營收增長、毛利率、EBITDA 利潤率)、計算內部報酬率(IRR)和現金回報倍數(MOIC)、進行差異分析並提供行動建議,以及生成包含基金層級指標、公司亮點和行動項目的投資組合報告。此技能可整合 FactSet、S&P Global 及 PitchBook 等 MCP 伺服器進行數據基準比對,並建議搭配 financial/model-builder、financial/statement-auditor 及 trading/black-edge 等技能使用。

相容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/oyi77/1ai-skills/tree/HEAD/financial/portfolio-monitor

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

投資組合監控器!

角色:

私募股權基金經理人 — 靈感來自 anthropics/financial-services 的 portfolio-monitoring 技能。精通 KPI 追蹤、回報分析及差異監控。

核心理念: 投資組合監控就是型態辨識。在資產惡化變得明顯之前及早發現——領先指標勝過落後指標。

概述

追蹤投資組合公司 KPI、監控與核保條件的差異,並計算回報(IRR、MOIC)。處理完整工作流程:擷取 → 追蹤 → 分析 → 報告。

反合理化解釋表

合理化解釋現實情況
「邊做邊想就好」結構化方法能節省時間並減少錯誤。遵循本技能的工作流程,而非即興發揮。
「我已經懂這個主題了」熟悉會讓人走捷徑。使用檢查清單確認你沒有遺漏關鍵步驟。
「這不適用於我的情況」這裡的模式在不同情境下皆可通用。調整而非跳過——底層原則依然成立。
「再多一個工具就能解決問題」增加複雜性很少能填補流程缺口。先掌握核心工作流程。

使用時機

觸發詞句:

  • "投資組合監控"

  • "月度投資組合回顧(所有公司)"

  • "季度董事會會議(核保 vs"

  • "IRR/MOIC 計算(基金報告)"

  • 月度投資組合回顧(所有公司)

  • 季度董事會會議(核保 vs 實際)

  • IRR/MOIC 計算(基金報告)

  • 差異分析(KPI vs 目標)

  • 投資組合公司比較(同業基準比對)

  • 退出準備(回報分析)

何時不應使用:

  • 單一公司深入分析(使用 financial/meeting-prep)
  • 盈餘分析(使用 financial/earnings-viewer)
  • 建立 DCF 模型(使用 financial/model-builder)
  • 交易策略(使用 trading/alphaear-strategy)

實作:

實作遵循階段性方法:追蹤 KPI、計算回報、分析差異、產生投資組合報告。

階段 1:KPI 追蹤

投資組合 KPI:

kpi_dashboard = {
    "revenue_growth": {"target": "25%", "actual": "32%", "variance": "+7% ✅"},
    "gross_margin": {"target": "65%", "actual": "61%", "variance": "-4% 🔴"},
    "ebitda_margin": {"target": "20%", "actual": "18%", "variance": "-2% 🔴"},
    "headcount": {"target": 150, "actual": 135, "variance": "-15 ⚠️"},
    "burn_rate": {"target": "$500K", "actual": "$650K", "variance": "+$150K 🔴"}
}

階段 2:回報分析

IRR/MOIC 計算:

returns = {
    "company_a": {
        "invested": 15000000,  # $15M
        "realized": 25000000,  # $25M distributions
        "unrealized": 35000000,  # $35M fair value
        "irr": 0.28,          # 28% IRR
        "moic": 4.0,          # 4.0x MOIC
        "holding_period": 3.5    # years
    },
    "company_b": {
        "invested": 10000000,
        "realized": 0,
        "unrealized": 18000000,
        "irr": 0.22,
        "moic": 1.8,
        "holding_period": 2.0
    }
}

階段 3:差異評論

差異分析:

variances = {
    "revenue": {
        "variance_pct": "+7%",
        "explanation": "Enterprise deals closed faster than underwritten",
        "action": "Raise FY guidance +5%"
    },
    "gross_margin": {
        "variance_pct": "-4%",
        "explanation": "New product line margin 45% vs. 65% core",
        "action": "Price optimization study"
    },
    "burn": {
        "variance_pct": "+30%",
        "explanation": "Hired 15 ahead of plan for Q3 launch",
        "action": "Monitor headcount vs. roadmap"
    }
}

階段 4:投資組合報告

報告結構:

# 投資組合報告 — Q1 2026

## 基金層級指標
| 指標 | 數值 | 目標 | 狀態 |
|---------|-------|--------|--------|
| NAV | $480M | $450M | +$30M ✅ |
| IRR | 24% | 20% | +4% ✅ |
| MOIC | 2.1x | 2.0x | +0.1x ✅ |
| DPI | 0.8x | 0.7x | +0.1x ✅ |

## 公司亮點

按 IRR、MOIC 及差異排名的最佳表現公司與觀察清單公司。

### ✅ 最佳表現者
1. **Co A** — IRR 28%, MOIC 4.0x(超標)
2. **Co D** — IRR 25%, MOIC 2.5x(符合計畫)

### 🔴 觀察清單
1. **Co B** — IRR 22%, 燒錢率 +30%(行動:成本審查)
2. **Co F** — IRR 12%, 營收 -5%(行動:策略審查)

## 行動項目
1. Co B:Q2 前提出成本優化計畫
2. Co F:安排策略審查會議
3. Co A:加碼分析(再加 $10M?)

常見合理化解釋

合理化解釋現實情況
「KPI 很無聊,跳過追蹤」KPI 能提前 18 個月以上預測退出機會
「IRR 沒問題,跳過差異分析」差異 = 早期預警,在問題惡化前及早發現
「投資組合很小,跳過報告」<5 家公司 = 更高集中風險,更應加強監控
「每季度一次就夠了」每月監控能在燒錢問題致命前及時發現

紅旗警戒

  • IRR < 15% 持續 3 年以上(表現不佳)
  • MOIC < 1.5x 於退出年度(投資失敗)
  • 燒錢率 > 核保水準 2 倍(現金跑道風險!)
  • 營收增長 < 10%(停滯)
  • 毛利率 < 50%(定價問題)
  • 2 間以上公司列入觀察清單(投資組合風險 > 30%)

驗證

完成投資組合審查後,確認:

  • KPI 已追蹤:所有公司,每間至少 5 項指標
  • IRR/MOIC:計算正確(Excel 公式已驗證)
  • 差異:> 2% 的差異均有解釋及行動項目
  • 最佳表現者:已識別(至少標示 2 間)
  • 觀察清單:已識別(至少標示 2 間)
  • 回報:DPI / RVPI / TVPI 均已計算
  • 報告已產生:3-5 頁,包含摘要
  • 行動項目:至少 3 項具體行動,指定負責人及日期

整合點:

跨技能參考:

  • financial/model-builder — 用於投資組合公司的 DCF 更新
  • financial/statement-auditor — 用於 LP 報告
  • trading/black-edge — 用於不利消息監控
  • references/trading-checklist.md — 用於投資組合風險驗證

MCP 伺服器整合:

  • FactSet MCP — 用於公開同業基準比對
  • S&P Global MCP — 用於行業表現
  • PitchBook MCP — 用於私募市場倍數

載入 references/trading-checklist.md 以取得完整的交易檢查清單(策略、風險、執行、投資組合)。


交叉參考: 如需全面的多資產財務分析、風險管理及機構級框架,請參閱 financial/all-in-one-finance(16 個模組)及 financial/wolf-finance(22 個模組)。

流程

  1. 分析任務需求
  2. 運用領域專業知識
  3. 驗證輸出品質

Individual skills in this repo

This repo contains 12 individual skills — each has its own dedicated page.

oyi77/1ai-skills

Turn a weekly changelog .md into a finished branded changelog video using HyperFrames. Use when the user provides a changelog/digest markdown and wants the weekly video, or says 'changelog video'. Self-contained — fonts, background, lexicon, and scripts ship in the skill. Produces square 1080, ~45-60s videos with animated brand mock-UIs.

oyi77/1ai-skills

The transition technique catalog for HyperFrames videos — five velocity-matched SEAMS (zoom-through, inverse zoom-through, cut-the-curve, waterfall cut, rack-focus blur-cut) plus in-scene techniques (waterfall entry, nudge curve). Covers partial-travel velocity matching, Z scale-sign rule, size-scaled blur, the 10/65/25 slide ratio, and the 2-3 transition budget. Read before authoring any transition, text-beat handoff, or kinetic text entry.

oyi77/1ai-skills

Add captions/subtitles to talking-head or launch videos using HyperFrames. Use when the user wants embedded captions, verbatim caption rails, or cinematic text behind the subject. Covers the drop/rail/embed caption model, the overlay law (captions are NOT a reserved band), matte occlusion for embedded climaxes, and word-timestamp alignment from TTS output.

oyi77/1ai-skills

Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video using HyperFrames. Use when the user wants a topic explainer, concept breakdown, how-to, or listicle with no product/website to capture. Every visual is invented per scene (typography, abstract graphics, diagrams, data-viz). Not a video built from a website (use hyperframes-product-launch-video).

oyi77/1ai-skills

The fallback HyperFrames workflow for anything that doesn't fit other skills — longer multi-scene pieces, brand/sizzle reels, title cards, static loops, freeform compositions. Input- and length-agnostic. Also the home of companion mode (co-create with the full toolbox). Use when no other HyperFrames skill matches, or when the user wants a freeform video.

oyi77/1ai-skills

Create short, unnarrated, design-led motion graphics (~under 10s) using HyperFrames. Use when the user wants kinetic type, stat/chart hits, logo stings, lower-thirds, animated tweets/headlines, or transparent overlay motion graphics. MP4 or transparent overlay output. Teaches seek-safe keyframe authoring and the 2-3 transition budget rule.

oyi77/1ai-skills

Turn a music track into a beat-synced HyperFrames video — lyric, slideshow, or kinetic promo. Use when the user provides an audio file, a video to pull audio from, or a mood brief for generated music. Music drives pacing. Teaches beat-map extraction, section-based scene planning, and audio-reactive visuals.

oyi77/1ai-skills

Create product launch videos from a URL, brief, or script using HyperFrames (HTML→MP4). Use when the user wants a product launch video, site tour, social clip featuring a product's own visuals, or marketing/promoting a product. Up to ~3 min (sweet spot 30-90s). Teaches the HyperFrames production loop: plan → write HTML → wire seekable animations → add media → lint → preview → render.

oyi77/1ai-skills

The Video Production Manager — manages ALL video production under 1ai-content. Delegates to HyperFrames, Remotion, AI video, and FFmpeg based on the task. Has memory via 1ai-hub brain, follows 1ai-rules, and reports to Content Director. Use when the user says 'make a video', 'create video', 'edit video', 'video strategy', or needs any video production work.

oyi77/1ai-skills

Agent skill at content/video/gen/SKILL.md

oyi77/1ai-skills

Use when go-to-market planning — launch sequencing, channel strategy, audience building, PR outreach. Use when planning product launches, building launch checklists, or coordinating multi-channel campaigns.

oyi77/1ai-skills

Use when portfolio manager — capital allocation, risk management, and performance metrics tracking for trading strategies.

相關技能