quick-dcf — Claude Code skill: DCF and installation
This Claude Code skill builds a quick DCF for a public company from deskstack data. It presents the assumptions and waits for approval before creating the workbook.
MIT ★ 86 updated 2026-11-16
/plugin marketplace add joaquimmj/deskstack
/plugin install deskstack@deskstackWhat quick-dcf does
The skill runs the DCF workflow from analyst with preset inputs: three filed years, a five-year forecast, and end-of-year discounting. Growth tapers from the latest filed year toward about 3%; margins and reinvestment use their three-year averages. WACC is derived from the 10-year risk_free_rate, beta, and ERP in valuation_inputs.
The agent shows an assumptions table and waits for approval before building the workbook, then runs a self-check. Every number must be cited, and the document ends with “Draft for human review. Not investment advice.” After the check, the skill offers /associate and /vp-review as review steps.
What it helps with
- build a DCF for a public company
- forecast cash flows with preset assumptions
- derive WACC from the risk-free rate, beta, and ERP
- run a self-check on the completed workbook
Example prompts for the agent
- Build a quick DCF for <company>.
- Prepare a DCF for <company> and show me the assumptions first.
- Create the DCF for <company>, then run the self-check.
How to install quick-dcf
1Plugin marketplace
/plugin marketplace add joaquimmj/deskstack/plugin install deskstack@deskstackThis installs the whole deskstack plugin with all its skills
2Skills CLI (Vercel)
npx skills add joaquimmj/deskstack --skill quick-dcf -a claude-code3Manually: put the files in place
~/.claude/skills/quick-dcf/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/quick-dcf/
1Skills CLI (Vercel)
npx skills add joaquimmj/deskstack --skill quick-dcf -a codex2Manually: put the files in place
.agents/skills/quick-dcf/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add joaquimmj/deskstack --skill quick-dcf -a cursor2Manually: put the files in place
.cursor/skills/quick-dcf/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install joaquimmj/deskstack plugins/deskstack/skills/quick-dcf2Manually: put the files in place
.github/skills/quick-dcf/SKILL.md1Skills CLI (Vercel)
npx skills add joaquimmj/deskstack --skill quick-dcf -a gemini-cli2Platform CLI
gemini skills install https://github.com/joaquimmj/deskstack --path plugins/deskstack/skills/quick-dcfManually: put the files in place
.devin/skills/quick-dcf/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about quick-dcf
How do I install quick-dcf in Claude Code?
Run /plugin marketplace add joaquimmj/deskstack, then /plugin install deskstack@deskstack.
What does quick-dcf do?
It runs the analyst DCF workflow for a public company, pauses for approval of the assumptions, then builds and checks the workbook. It also offers /associate and /vp-review.
What does quick-dcf need to work?
It uses the analyst workflow, deskstack data, and the conventions skill to cite figures.
Source text
SKILL.md · MIT
--- name: quick-dcf description: One-shot quick DCF for a public company with cited deskstack data: builds the workbook with the analyst skill's defaults, then suggests /associate and /vp-review. argument-hint: "<company>" --- # Quick DCF Run the `analyst` skill's DCF workflow with these defaults: - 3 filed years, 5 projected years, end-of-year discounting; - growth fading from the last filed year toward ~3%; - margins and reinvestment at their 3-year averages; - WACC from `risk_free_rate` (10y) + beta × ERP (`valuation_inputs`). **Show the assumptions table and wait for the user's OK before building.** Then build, run the self-check, and offer the review steps (`/associate`, `/vp-review`). Follow the `conventions` skill: cite every number, and end with "Draft for human review. Not investment advice."
© Joaquim · MIT · joaquimmj/deskstack