Agent skill

Dcf

by daloopa in daloopa/investing

Discounted cash flow valuation with sensitivity analysis. An agent skill from daloopa/investing.

Apache-2.0Auto-check passedBusiness, Finance & HR

Install Dcf

skills CLI
$ npx skills add daloopa/investing --skill dcf -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install daloopa/investing dcf --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/daloopa/investing.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/dcf .claude/skills/dcf && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
dcf
GitHub stars
489
Token cost
~2.5k tokens
SKILL.md length
1,096 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
Apache-2.0

At a glance

Discounted cash flow valuation with sensitivity analysis. An agent skill from daloopa/investing.

  • Works in 10 steps: Company Lookup → Market Data → Historical Financials from Daloopa → …
  • Tasks that involve Financial modeling
  • SKILL.md covers 1. Company Lookup, 2. Market Data, 3. Historical Financials from… and 4. Calculate WACC, plus 8 more sections
  • Reaches daloopa.com

What it does

Dcf is an agent skill from daloopa/investing. Discounted cash flow valuation with sensitivity analysis

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Business, Finance & HR, covering Financial modeling. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Financial modeling

Example prompts

  • “/dcf”

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Company Lookup
  2. Market Data
  3. Historical Financials from Daloopa
  4. Calculate WACC
  5. Terminal Value
  6. Compute Implied Valuation
  7. Sensitivity Analysis
  8. Consensus Sanity Check (if available)
  9. Sanity Checks & Self-Challenge
  10. Save Report

What it can do on your machine

Read from SKILL.md and the folder at commit e2dd01d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • daloopa.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dcf loads about 2.5k tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 1,096 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from daloopa/investing at commit e2dd01d, republished under its Apache-2.0 licence (© daloopa). 1,096 words, ~2,453 tokens.

Download SKILL.mdSave it as .claude/skills/dcf/SKILL.md (or your agent's skills folder).
name
dcf
description
Discounted cash flow valuation with sensitivity analysis
argument-hint
TICKER

Build a discounted cash flow (DCF) valuation for the company specified by the user: $ARGUMENTS

Before starting, read ../data-access.md for data access methods and ../design-system.md for formatting conventions. Follow the data access detection logic and design system throughout this skill.

Follow these steps:

1. Company Lookup

Look up the company by ticker using discover_companies. Capture:

  • company_id
  • latest_calendar_quarter — anchor for all period calculations below (see ../data-access.md Section 1.5)
  • latest_fiscal_quarter
  • Firm name for report attribution (default: "Daloopa") — see ../data-access.md Section 4.5

2. Market Data

Get market-side inputs for {TICKER} (see ../data-access.md Section 2 for how to source market data in your environment):

  • Current price, market cap, shares outstanding, beta
  • 10Y Treasury yield (risk-free rate for WACC)

If market data is unavailable, use reasonable defaults: beta=1.0, risk-free rate=4.5%, and note the assumptions.

3. Historical Financials from Daloopa

Calculate 8 quarters backward from latest_calendar_quarter. Pull:

  • Revenue
  • Operating Income
  • Net Income
  • Diluted EPS
  • Operating Cash Flow
  • Capital Expenditures
  • Free Cash Flow (compute as OCF - CapEx, label "(calc.)")
  • Depreciation & Amortization
  • Tax expense and pre-tax income (for effective tax rate)
  • Interest expense (for cost of debt)
  • Total debt (short + long term)
  • Cash and equivalents
  • Shares outstanding

Also pull segment revenue and any available guidance series.

4. Calculate WACC

Cost of Equity (CAPM):

  • Risk-free rate (Rf) = 10Y Treasury from market data
  • Equity risk premium (ERP) = 5.5% (standard assumption)
  • Beta from market data (or 1.0 default)
  • Cost of equity = Rf + Beta × ERP

Cost of Debt:

  • If interest expense and total debt available: Cost of debt = Interest Expense / Average Total Debt
  • After-tax cost of debt = Cost of debt × (1 - effective tax rate)
  • If not available, use 5.0% pre-tax as default

Capital Structure:

  • Market cap for equity weight
  • Total debt for debt weight
  • WACC = (E/V) × Re + (D/V) × Rd × (1-t)

Show all inputs and the resulting WACC clearly.

5a. KPI-Driven Revenue Build (Preferred)

Before projecting top-down, attempt a bottoms-up revenue build using operational KPIs. This produces a significantly more defensible DCF — a top-down trend decay is a guess; a bottoms-up KPI build is analysis.

Discover segment and KPI data: Pull segment revenue breakdown + segment-specific KPIs for the target company. Use the sector taxonomy to know what to search for:

  • SaaS/Cloud: ARR, net revenue retention, RPO/cRPO, customers >$100K, cloud gross margin
  • Consumer Tech: DAU/MAU, ARPU, engagement metrics, installed base, paid subscribers
  • E-commerce/Marketplace: GMV, take rate, active buyers/sellers, order frequency
  • Retail: same-store sales, store count, average ticket, transactions
  • Telecom/Media: subscribers, churn, ARPU, content spend
  • Hardware: units shipped, ASP, attach rate, installed base
  • Financial Services: AUM, NIM, loan growth, credit quality metrics, fee income ratio
  • Pharma/Biotech: pipeline stage, patient starts, scripts, market share
  • Industrials/Energy: backlog, book-to-bill, utilization, production volumes, reserves

Build bottoms-up projections per segment: For each segment with KPI data, project revenue using unit economics:

  • Hardware segments: projected units × projected ASP
  • Subscription segments: projected subscribers × projected ARPU (net of churn)
  • Marketplace segments: projected GMV × projected take rate
  • Services/recurring: apply growth rate informed by retention metrics and customer adds

Sum segment projections to get total revenue for each of 5 years. Show the build clearly so the reader can challenge individual segment assumptions.

Fall back to top-down if KPIs aren't available. If segment KPIs are sparse or unavailable, use the top-down approach in Section 5b instead, but note explicitly that the model is less reliable without bottoms-up drivers.

5b. Top-Down FCF Projections (Fallback)

Build 5-year FCF projections. If a projection engine is available (see ../data-access.md Section 5), use it. Otherwise, project manually:

  • Revenue: Use management guidance for near-term, then decay toward 3% long-term growth
  • FCF Margin: Use trailing average, adjust for any clear trends
  • FCF = Projected Revenue × Projected FCF Margin

Show all assumptions clearly — this is the most judgment-intensive part. If using this fallback instead of the KPI-driven build (Section 5a), note the limitation.

6. Terminal Value

Calculate terminal value using perpetuity growth method:

  • Terminal FCF = Year 5 FCF × (1 + terminal growth rate)
  • Terminal Value = Terminal FCF / (WACC - terminal growth rate)
  • Default terminal growth rate: 2.5-3.0% (should not exceed long-term GDP growth)
  • Discount terminal value to present
Show full SKILL.md (434 more words)Show less

7. Compute Implied Valuation

  • Sum of PV of projected FCFs + PV of terminal value = Enterprise Value
  • Equity Value = Enterprise Value - Net Debt
  • Implied Share Price = Equity Value / Shares Outstanding
  • Compare to current market price: upside/downside %

Also compute:

  • Implied EV/EBITDA (Enterprise Value / Trailing EBITDA)
  • Implied P/E (Equity Value / Trailing Net Income)
  • Terminal value as % of total value (flag if > 80% — this means the DCF is very sensitive to terminal assumptions)

8. Sensitivity Analysis

Build a sensitivity table varying two key inputs:

WACC (rows): Base WACC ± 2% in 0.5% increments (7 rows) Terminal Growth Rate (columns): 1.5% to 4.0% in 0.5% increments (6 columns)

Each cell = implied share price at that WACC/growth combination. Highlight the base case cell and the current market price for reference.

Also show a secondary sensitivity: Revenue Growth vs FCF Margin if data supports it.

9. Consensus Sanity Check (if available)

If consensus estimates are available (see ../data-access.md Section 3):

  • Compare your projected revenue/EPS path to consensus for the next 1-2 years
  • Note where your DCF assumptions diverge from Street expectations
  • If your implied price is significantly above/below consensus target, explain why

If consensus data is not available, skip this check.

10. Sanity Checks & Self-Challenge

Flag any issues:

  • If implied price is >2x or <0.5x current price, note that the DCF produces an extreme result and examine assumptions
  • If terminal value is >85% of total value, the model is highly sensitive to terminal assumptions
  • If WACC < risk-free rate or > 15%, the capital structure inputs may be off
  • Compare implied multiples to historical trading range

Challenge your own assumptions — don't anchor to the current price:

  • Build the DCF from fundamentals first, THEN compare to market price. Don't work backwards from the current price to justify assumptions.
  • If your base case revenue growth assumes continuation of recent trends, stress-test: what if growth mean-reverts to the industry average? What if the current cycle peaks?
  • Explicitly state what has to go right for the bull case implied price and what has to go wrong for the bear case.
  • If the DCF only "works" with aggressive terminal growth or unrealistically low WACC, say so — the stock may simply be expensive on fundamentals.

11. Save Report

Save to reports/{TICKER}_dcf.html using the HTML report template from ../design-system.md. Write the full analysis as styled HTML with the design system CSS inlined. This is the final deliverable — no intermediate markdown step needed.

Structure the report with these sections:

<h1>{Company Name} ({TICKER}) — DCF Valuation</h1>
<p>Generated: {date}</p>

<h2>Summary</h2>
<table>
| Metric | Value |
| Current Price | $XXX |
| Implied Share Price | $XXX |
| Upside / Downside | +X.X% / -X.X% |
| WACC | X.X% |
| Terminal Growth | X.X% |
| Terminal Value % of Total | XX% |
</table>

<h2>WACC Calculation</h2>
<table>
| Component | Value | Source |
| Risk-Free Rate | X.X% | FRED 10Y Treasury |
| Equity Risk Premium | 5.5% | Standard assumption |
| Beta | X.XX | Market data |
| Cost of Equity | X.X% | CAPM |
| Cost of Debt (after-tax) | X.X% | Interest/Debt × (1-t) |
| Equity Weight | XX% | Market cap |
| Debt Weight | XX% | Total debt |
| **WACC** | **X.X%** | |
</table>

<h2>Historical Free Cash Flow (8 Quarters)</h2>
<table>
| Metric | Q1 | Q2 | ... | Q8 |
{OCF, CapEx, FCF, FCF Margin — with Daloopa citations}
</table>

<h2>FCF Projections (5 Years)</h2>
<table>
| Metric | Year 1 | Year 2 | Year 3 | Year 4 | Year 5 |
{Revenue, FCF Margin, FCF — with assumptions noted}
</table>

<h2>Valuation Bridge</h2>
<table>
| Component | Value |
| PV of Projected FCFs | $XXX |
| PV of Terminal Value | $XXX |
| Enterprise Value | $XXX |
| Less: Net Debt | ($XXX) |
| Equity Value | $XXX |
| Shares Outstanding | XXX |
| **Implied Share Price** | **$XXX** |
</table>

<h2>Sensitivity Table: WACC vs Terminal Growth</h2>
<table>
| WACC \ Growth | 1.5% | 2.0% | 2.5% | 3.0% | 3.5% | 4.0% |
{matrix of implied share prices, base case bolded}
</table>
<p>Current market price: $XXX for reference.</p>

<h2>Key Assumptions & Risks</h2>
<ul>{List all key assumptions and what could invalidate them}</ul>

<h2>Sanity Checks</h2>
<ul>{Implied multiples vs historical, terminal value concentration, etc.}</ul>

All financial figures must use Daloopa citation format: <a href="https://daloopa.com/src/{fundamental_id}">$X.XX million</a>

Tell the user where the HTML report was saved.

Summarize: implied price vs current price, key upside/downside drivers, and the biggest sensitivity.

© daloopa, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/dcf of daloopa/investing.

Open the folder on GitHubat commit e2dd01d

Compare with similar skills

Dcf next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Dcf compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dcf this skilldaloopa/investing489—~2.5kAutomated safety check: PassApache-2.0
Creating Financial ModelsChen-zexi/open-ptc-agent7294 repos~1.3kAutomated safety check: PassMIT
Equity Researcherlzwme/finance-quant-skills4351 repos~4.9kAutomated safety check: PassNone
Equity ResearchrollingSirius/equity-research-skill452—~1.5kAutomated safety check: PassMIT
SaaS Metrics Coachrongxinzy/RongxinAI1542 repos~1.3kAutomated safety check: PassMIT
Startup Financial Modelingnicepkg/auto-company19212 repos~2.8kAutomated safety check: PassNone

Similar skills

  • Creating Financial Models

    Chen-zexi/open-ptc-agent

    This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

    729 GitHub starsUsed in 4 repos~1.3k tokens
    Business, Finance & HRAuto-check passed
  • Equity Researcher

    lzwme/finance-quant-skills

    机构级投研报告生成技能。覆盖中国A股、港股、美股上市公司。输出模式:1)投资速览:3-5页,含公司概览、核心财务指标、估值倍数、投资逻辑与风险因素;2)深度研报:≥25页,含行业分析、产业链图谱、三表模型、DCF估值、情景分析与敏感性测试。触发条件:1)直接请求:分析/看看/研究/调研/介绍一下 + 公司名或股票;2)投资询问:你怎么看/能不能买/值得投吗/帮我看看/扒一扒 +…

    435 GitHub starsUsed in 1 repo~4.9k tokens
    Business, Finance & HRAuto-check passed
  • Equity Research

    rollingSirius/equity-research-skill

    撰写机构级个股投资研究报告(二级市场深度研究)。Use whenever the user wants to research, analyze, or value a specific publicly-traded stock — e.g.

    452 GitHub stars~1.5k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • SaaS Metrics Coach

    rongxinzy/RongxinAI

    SaaS financial health advisor. An agent skill from rongxinzy/RongxinAI.

    154 GitHub starsUsed in 2 repos~1.3k tokens
    Business, Finance & HRAuto-check passed
  • Startup Financial Modeling

    nicepkg/auto-company

    This skill should be used when the user asks to "create financial projections", "build a financial model", "forecast revenue", "calculate burn rate", "estimate runway", "model cash flow", or…

    192 GitHub starsUsed in 12 repos~2.8k tokens
    Business, Finance & HRAuto-check passed
  • Stock Value Analyzer

    FunnyKun/stock-value-analyzer

    基于邱国鹭《投资中最简单的事》方法论的股票价值分析器(v2.0 双层架构)。通过"三好原则"(好行业、好公司、好价格)系统评估一只股票是否值得投资。v2.0 在原定性框架之上注入一套可量化、可复现的硬模型层——反向 DCF 反解市场隐含增速、情景概率加权估值、EPV 盈利能力价值、分行业估值路由、杜邦三/五因子分解、ROIC vs WACC、Piotroski F-Score、Beneish…

    140 GitHub stars~3.3k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed

More from daloopa/investing

All 22 skills in this repo
  • Capital Allocation

    daloopa/investing

    Deep dive into capital deployment, buybacks, dividends, and shareholder yield

    489 GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Comp Sheet

    daloopa/investing

    Build an industry comp sheet Excel model with deep operational KPIs

    489 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Comps

    daloopa/investing

    Trading comparables analysis with peer multiples and implied valuation

    489 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Earnings Flash

    daloopa/investing

    Rapid first-read earnings flash for a given company. An agent skill from daloopa/investing.

    489 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Guidance Tracker

    daloopa/investing

    Track management guidance accuracy over time for a given company

    489 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Inflection

    daloopa/investing

    Auto-detect biggest acceleration/deceleration inflections across all metrics

    489 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

Questions about Dcf

What does Dcf do?

Discounted cash flow valuation with sensitivity analysis. An agent skill from daloopa/investing. Dcf is an agent skill from daloopa/investing.

When should I use Dcf?

Dcf fits situations like: tasks that involve Financial modeling.

How do I install Dcf in Claude Code?

Run `npx skills add daloopa/investing --skill dcf -a claude-code`. Or copy the skill folder (.claude/skills/dcf in daloopa/investing) into .claude/skills/dcf in your project. Claude Code loads it when a task matches its description.

How do I install Dcf in Codex?

Run `npx skills add daloopa/investing --skill dcf -a codex`. Or copy the skill folder (.claude/skills/dcf in daloopa/investing) into .agents/skills/dcf in your project. Codex loads it when a task matches its description.

Can I use Dcf in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add daloopa/investing --skill dcf -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dcf, .gemini/skills/dcf, .github/skills/dcf and .opencode/skills/dcf in your project.

What does Dcf need to run?

SKILL.md names no scripts, command-line tools or credentials: Dcf is instructions for the agent only.

Does Dcf access the network?

SKILL.md names 1 domain. In commands or code: daloopa.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Dcf safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Dcf use?

Dcf is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dcf use?

About 2.5k tokens (SKILL.md is roughly 9.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Dcf?

Skills that share tags, products or a category with Dcf: Creating Financial Models (Chen-zexi/open-ptc-agent, 729 stars), Equity Researcher (lzwme/finance-quant-skills, 435 stars), Equity Research (rollingSirius/equity-research-skill, 452 stars) and SaaS Metrics Coach (rongxinzy/RongxinAI, 154 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dcf?

daloopa (a GitHub organization) maintains it in daloopa/investing, which has 489 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 7, 2026.

Source: daloopa/investing on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.