Agent skill

Sensitivity Analysis

by revfactory in revfactory/harness-100

A specialized skill providing sensitivity analysis and scenario table construction methodology for financial models.

Apache-2.0Auto-check passedBusiness, Finance & HR

Install Sensitivity Analysis

skills CLI
$ npx skills add revfactory/harness-100 --skill sensitivity-analysis -a claude-code

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

GitHub CLI
$ gh skill install revfactory/harness-100 sensitivity-analysis --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/revfactory/harness-100.git skills-src && mkdir -p .claude/skills && cp -r skills-src/en/53-financial-modeler/.claude/skills/sensitivity-analysis .claude/skills/sensitivity-analysis && 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
sensitivity-analysis
GitHub stars
1.3k
Token cost
~1.2k tokens
SKILL.md length
326 words
Files
1
Skills in repo
464
Repo updated
First seen
Licence
Apache-2.0

At a glance

A specialized skill providing sensitivity analysis and scenario table construction methodology for financial models.

  • Works in 4 steps: Select 5-8 key assumption variables → Vary each variable by +/-20% (or a… → Calculate the variation in the result… → …
  • Tasks that involve Financial modeling
  • SKILL.md covers Target Agent, 1-Way Sensitivity Analysis, 2-Way Sensitivity Analysis… and 3-Scenario Analysis…, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Sensitivity Analysis is an agent skill from revfactory/harness-100. A specialized skill providing sensitivity analysis and scenario table construction methodology for financial models. Used by the scenario-planner agent when designing Bear/Base/Bull scenarios and analyzing key variable impact. Automatically applied in contexts such as 'sensitivity analysis', 'scenario analysis', 'sensitivity table', 'tornado chart', 'Monte Carlo'. However, statistical software (R, Python) execution and real-time simulation are outside the scope of this skill.

Its SKILL.md is about 1.2k 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. It works with Python. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Financial modeling

Example prompts

  • “sensitivity analysis”
  • “scenario analysis”
  • “sensitivity table”
  • “/sensitivity-analysis”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Select 5-8 key assumption variables
  2. Vary each variable by +/-20% (or a reasonable range)
  3. Calculate the variation in the result metric (enterprise value, IRR, etc.)
  4. Arrange horizontal bars in descending order of variation magnitude

What it can do on your machine

Read from SKILL.md and the folder at commit 8e8d35c. 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 (its code samples are markdown).

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

  • Network

    No URLs in SKILL.md.

    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

Sensitivity Analysis loads about 1.2k tokens when it runs. Until then it costs about 125 tokens; SKILL.md has 326 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~125
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 revfactory/harness-100 at commit 8e8d35c, republished under its Apache-2.0 licence (© revfactory). 326 words, ~1,185 tokens.

Download SKILL.mdSave it as .claude/skills/sensitivity-analysis/SKILL.md (or your agent's skills folder).
name
sensitivity-analysis
description
A specialized skill providing sensitivity analysis and scenario table construction methodology for financial models. Used by the scenario-planner agent when designing Bear/Base/Bull scenarios and analyzing key variable impact. Automatically applied in contexts such as 'sensitivity analysis', 'scenario analysis', 'sensitivity table', 'tornado chart', 'Monte Carlo'. However, statistical software (R, Python) execution and real-time simulation are outside the scope of this skill.

Sensitivity Analysis — Sensitivity Analysis Methodology

A specialized skill that enhances the scenario analysis capabilities of the scenario-planner agent.

Target Agent

  • scenario-planner — Bear/Base/Bull scenarios, sensitivity table construction

1-Way Sensitivity Analysis

Vary one variable while holding all others constant and observe changes in the result.

Tornado Chart Construction Method
  1. Select 5-8 key assumption variables
  2. Vary each variable by +/-20% (or a reasonable range)
  3. Calculate the variation in the result metric (enterprise value, IRR, etc.)
  4. Arrange horizontal bars in descending order of variation magnitude
                    Enterprise Value Change
Revenue Growth  ████████████████████████   Most Sensitive
Operating Margin ██████████████████
WACC            ████████████████
Perpetual Growth █████████████
CAPEX/Revenue    ███████████
NWC/Revenue      ████████                   Least Sensitive
Key Variable Selection Guide
Financial Model Type1st Priority2nd Priority3rd Priority
SaaSRevenue Growth RateNRR/ChurnCAC
ManufacturingUtilization RateRaw Material PriceFX Rate
RetailGMV Growth RateTake RateShipping Cost
BiotechClinical Success RateMarket SizeDrug Price

2-Way Sensitivity Analysis (Data Table)

Matrix varying two variables simultaneously:

markdown
### Enterprise Value ($M) — Revenue Growth vs WACC

|              | WACC 8% | WACC 9% | WACC 10% | WACC 11% | WACC 12% |
|-------------|---------|---------|----------|----------|----------|
| Growth 10%  |   52    |   46    |   41     |   37     |   34     |
| Growth 15%  |   68    |   59    |   52     |   46     |   41     |
| Growth 20%  |   87    |   74    |   64     |   56     |   49     |
| Growth 25%  |  109    |   91    |   78     |   67     |   59     |
| Growth 30%  |  135    |  111    |   93     |   80     |   70     |

Color Coding Rules:

  • Above current enterprise value = Green (Investment attractive)
  • 80-100% of current enterprise value = Yellow (Watch)
  • Below 80% of current enterprise value = Red (Warning)

3-Scenario Analysis (Bear/Base/Bull)

Scenario Definition Framework
CategoryBear (Pessimistic)BaseBull (Optimistic)
Probability Weight20-25%50-60%20-25%
Revenue GrowthBottom 25% benchmarkMedianTop 25% benchmark
MarginMaintain or declineGradual improvementTarget achieved
Market EnvironmentEconomic slowdown, intensified competitionStatus quoBoom, market expansion
Per-Scenario Key Assumptions Table
markdown
| Assumption | Bear | Base | Bull | Basis |
|-----------|------|------|------|-------|
| Revenue Growth Y1 | 10% | 25% | 40% | Industry distribution |
| Revenue Growth Y3 | 5% | 15% | 30% | Convergence assumption |
| Operating Margin Y5 | 8% | 15% | 22% | Benchmark |
| Customer Churn | 5% | 3% | 1.5% | Peer data |
| CAPEX/Revenue | 12% | 8% | 6% | Economies of scale |
Probability-Weighted Value
Weighted Enterprise Value = P(Bear) x V(Bear) + P(Base) x V(Base) + P(Bull) x V(Bull)

Break-Even Analysis

Key Questions

"At what level must an assumption deteriorate for the investment to fail?"

Analysis ItemFormulaMeaning
Revenue BEPFixed Costs / Contribution Margin RatioMinimum required revenue
Customer BEPFixed Costs / (ARPU x Margin)Minimum required customers
Growth Rate BEPGrowth rate where NPV = 0Minimum required growth
IRR BEPDiscount rate where NPV = 0Internal rate of return

Output Format Requirements

Required Deliverables
  1. Tornado Chart — Variable sensitivity ranking
  2. 2-Way Tables — Cross-analysis of top 2 variables (minimum 2)
  3. 3-Scenario Summary — Bear/Base/Bull key assumptions + results
  4. Probability-Weighted Value — Final estimate
  5. Break-Even Points — Per key variable break-even
  6. Implications — Risk management recommendations for the most sensitive variables

© revfactory, 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 en/53-financial-modeler/.claude/skills/sensitivity-analysis of revfactory/harness-100.

Open the folder on GitHubat commit 8e8d35c

Compare with similar skills

Sensitivity Analysis 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.

Sensitivity Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sensitivity Analysis this skillrevfactory/harness-1001.3k—~1.2kAutomated safety check: PassApache-2.0
Dcf ModelWind-Alice/AliceMarket1283 repos~12kAutomated safety check: PassNone
Dcf ModelLuciole-Studio/Misaka-Agent1252 repos~12kAutomated safety check: PassApache-2.0
Cap Table Waterfalldavepoon/buildwithclaude3.6k—~1.1kAutomated safety check: PassMIT
Financial Modeldavepoon/buildwithclaude3.6k—~1.1kAutomated safety check: PassMIT
Three-Statement Model Builderginlix-ai/LangAlpha1.8k—~5.4kAutomated safety check: PassApache-2.0

Similar skills

  • Dcf Model

    Wind-Alice/AliceMarket

    Real DCF (Discounted Cash Flow) model creation for equity valuation.

    128 GitHub starsUsed in 3 repos~12k tokens
    Business, Finance & HRAuto-check passed
  • Dcf Model

    Luciole-Studio/Misaka-Agent

    Build discounted cash flow valuation workbooks in Excel. An agent skill from Luciole-Studio/Misaka-Agent.

    125 GitHub starsUsed in 2 repos~12k tokens
    Business, Finance & HRAuto-check passed
  • Cap Table Waterfall

    davepoon/buildwithclaude

    Model cap table dilution, SAFE conversion, and exit waterfall across scenarios.

    3.6k GitHub stars~1.1k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Financial Model

    davepoon/buildwithclaude

    Run deterministic financial models for startup valuation and SaaS health analysis.

    3.6k GitHub stars~1.1k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Builds or repairs an integrated income statement, balance sheet and cash flow model in Excel with live formulas, supporting schedules, scenarios and a Checks sheet.

    1.8k GitHub stars~5.4k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Runs a staged deep analysis of a single stock on China A-share, Hong Kong and US markets, ending in an HTML report with valuation models and investor-panel scores.

    7.1k GitHub stars~9.1k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check: notes

More from revfactory/harness-100

All 464 skills in this repo
  • Anti Bot Analyzer

    revfactory/harness-100

    A skill for analyzing website anti-bot defense mechanisms and developing legitimate evasion strategies.

    1.3k GitHub stars~1.1k tokensUpdated 6 mo ago
    Auto-check passed
  • API Error Design Patterns

    revfactory/harness-100

    Reference for designing how an API reports failures: structured error codes, response shapes, client-friendly messages, an error catalog and retry or fallback advice.

    1.3k GitHub stars~1.6k tokensUpdated 6 mo ago
    Auto-check passed
  • API Security Checklist

    revfactory/harness-100

    Walks a backend-dev agent through OWASP API Top 10 checks, authentication and authorization patterns, and defense code during API design.

    1.3k GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Arg Parser Generator

    revfactory/harness-100

    Methodology for systematically designing and generating CLI tool argument parser structures.

    1.3k GitHub stars~1.2k tokensUpdated 6 mo ago
    Auto-check passed
  • Audience Segmentation

    revfactory/harness-100

    Audience segmentation skill used by the analyst and curator agents.

    1.3k GitHub stars~1.3k tokensUpdated 6 mo ago
    Auto-check passed
  • Audio Storytelling

    revfactory/harness-100

    Audio storytelling skill used by the podcast scriptwriter and show note editor.

    1.3k GitHub stars~1.6k tokensUpdated 6 mo ago
    Auto-check passed

Works with

Questions about Sensitivity Analysis

What does Sensitivity Analysis do?

A specialized skill providing sensitivity analysis and scenario table construction methodology for financial models. Sensitivity Analysis is an agent skill from revfactory/harness-100. A specialized skill providing sensitivity analysis and scenario table construction methodology for financial models.

When should I use Sensitivity Analysis?

Sensitivity Analysis fits situations like: tasks that involve Financial modeling.

How do I install Sensitivity Analysis in Claude Code?

Run `npx skills add revfactory/harness-100 --skill sensitivity-analysis -a claude-code`. Or copy the skill folder (en/53-financial-modeler/.claude/skills/sensitivity-analysis in revfactory/harness-100) into .claude/skills/sensitivity-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Sensitivity Analysis in Codex?

Run `npx skills add revfactory/harness-100 --skill sensitivity-analysis -a codex`. Or copy the skill folder (en/53-financial-modeler/.claude/skills/sensitivity-analysis in revfactory/harness-100) into .agents/skills/sensitivity-analysis in your project. Codex loads it when a task matches its description.

Can I use Sensitivity Analysis 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 revfactory/harness-100 --skill sensitivity-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sensitivity-analysis, .gemini/skills/sensitivity-analysis, .github/skills/sensitivity-analysis and .opencode/skills/sensitivity-analysis in your project.

What does Sensitivity Analysis need to run?

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

Does Sensitivity Analysis access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sensitivity Analysis 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 Sensitivity Analysis use?

Sensitivity Analysis 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 Sensitivity Analysis use?

About 1.2k tokens (SKILL.md is roughly 4.7k 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 Sensitivity Analysis?

Skills that share tags, products or a category with Sensitivity Analysis: Dcf Model (Wind-Alice/AliceMarket, 128 stars), Dcf Model (Luciole-Studio/Misaka-Agent, 125 stars), Cap Table Waterfall (davepoon/buildwithclaude, 3.6k stars) and Financial Model (davepoon/buildwithclaude, 3.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sensitivity Analysis?

revfactory (a GitHub user) maintains it in revfactory/harness-100, which has 1,290 GitHub stars. The repository holds 464 skills in this directory. The repository was last updated on March 22, 2026.

Source: revfactory/harness-100 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.