Agent skill

Relative Valuation

by Yijia-Xiao in Yijia-Xiao/FinanceHarness

Value an equity against its peers — peer-median trading multiples applied to the company's metrics for an implied range, cross-read against its own valuation ratios.

Apache-2.0Auto-check passedBusiness, Finance & HR

Install Relative Valuation

skills CLI
$ npx skills add Yijia-Xiao/FinanceHarness --skill relative-valuation -a claude-code

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

GitHub CLI
$ gh skill install Yijia-Xiao/FinanceHarness relative-valuation --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/Yijia-Xiao/FinanceHarness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/financeharness/skills/relative-valuation .claude/skills/relative-valuation && 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
relative-valuation
GitHub stars
196
Token cost
~446 tokens
SKILL.md length
195 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Value an equity against its peers — peer-median trading multiples applied to the company's metrics for an implied range, cross-read against its own valuation ratios.

  • Works in 4 steps: Identify the peer set.… → The company's own multiples.… → Comps. data_equity_comps with the peer… → …
  • Tasks that involve Financial modeling
  • SKILL.md covers Workflow and Principles
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Relative Valuation is an agent skill from Yijia-Xiao/FinanceHarness. Value an equity against its peers — peer-median trading multiples applied to the company's metrics for an implied range, cross-read against its own valuation ratios.

Its SKILL.md is about 450 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 and Trading and backtesting. The repository describes itself as: FinanceHarness: Autonomous Financial Deep Research Framework. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Financial modeling
  • Tasks that involve Trading and backtesting

Example prompts

  • “/relative-valuation”

Workflow steps

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

  1. Identify the peer set. data_equity_reference to classify the company
  2. The company's own multiples. data_equity_ratios for its P/E,
  3. Comps. data_equity_comps with the peer tickers — peer-median multiples
  4. Read it. Is the name rich or cheap versus peers, and is the gap

What it can do on your machine

Read from SKILL.md and the folder at commit 1163c5e. 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

    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

Relative Valuation loads about 446 tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 195 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~446

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 Yijia-Xiao/FinanceHarness at commit 1163c5e, republished under its Apache-2.0 licence (© Yijia-Xiao). 195 words, ~446 tokens.

Download SKILL.mdSave it as .claude/skills/relative-valuation/SKILL.md (or your agent's skills folder).
name
relative-valuation
description
Value an equity against its peers — peer-median trading multiples applied to the company's metrics for an implied range, cross-read against its own valuation ratios.
tags
equity, valuation, comps, relative-valuation, multiples
requires_tools
data_equity_reference, data_equity_ratios, data_equity_comps

Relative valuation

Where a name trades versus comparable companies, and whether that's deserved.

Workflow

  1. Identify the peer set. data_equity_reference to classify the company (sector/industry); choose genuine comparables — similar business, scale, and growth/margin profile, not just same-sector names.
  2. The company's own multiples. data_equity_ratios for its P/E, EV/EBITDA, EV/revenue, P/S, plus the leverage/returns context that justifies a premium or discount.
  3. Comps. data_equity_comps with the peer tickers — peer-median multiples applied to the company's metrics give an implied value-per-share range vs the current price. Report the medians, implied values, and range it returns directly; they're already computed, so there's no need to re-derive them.
  4. Read it. Is the name rich or cheap versus peers, and is the gap warranted by superior growth, margins, or returns? State the implied range and the call.

Principles

  • Peer choice drives the answer — name the comparables and why they fit; a bad peer set makes a precise-looking range meaningless.
  • A premium or discount is only a finding once you tie it to fundamentals (growth, margins, returns) — otherwise it's just a number.
  • Relative value complements, not replaces, an intrinsic (DCF) view — say which you're giving and pair them when it matters.

© Yijia-Xiao, 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 financeharness/skills/relative-valuation of Yijia-Xiao/FinanceHarness.

Open the folder on GitHubat commit 1163c5e

Compare with similar skills

Relative Valuation 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.

Relative Valuation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Relative Valuation this skillYijia-Xiao/FinanceHarness196—~446Automated safety check: PassApache-2.0
Backtest Execution ModelingHKUDS/Vibe-Trading35k—~2.9kAutomated safety check: PassMIT
Market Microstructure AnalysisHKUDS/Vibe-Trading35k—~3.1kAutomated safety check: PassMIT
Advanced Options StrategiesHKUDS/Vibe-Trading35k—~2kAutomated safety check: PassMIT
Options Strategy BacktestingHKUDS/Vibe-Trading35k—~2kAutomated safety check: PassMIT
Forecastingericrisco/rsc-harness180—~2.8kAutomated safety check: PassMIT

Similar skills

  • Backtest Execution Modeling

    HKUDS/Vibe-Trading

    Adds realistic execution assumptions to backtests: fixed, linear and square-root slippage, delayed fills, VWAP and TWAP logic and market-impact cost estimates; never for live orders.

    35k GitHub stars~2.9k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Measures spreads, order-flow toxicity (VPIN, Kyle's lambda) and liquidity (Amihud, Roll) to improve cost estimates and execution, including China A-share auction and block trade mechanics.

    35k GitHub stars~3.1k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Advanced Options Strategies

    HKUDS/Vibe-Trading

    Covers volatility-surface modeling (SABR, local volatility), dynamic Greeks management, calendar spreads, skew and volatility arbitrage, and market-making basics for options.

    35k GitHub stars~2k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Backtests multi-leg option strategies by synthesizing Black-Scholes prices from the underlying, simulating PnL, Greeks exposure and expiration for crypto and equity options.

    35k GitHub stars~2k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Forecasting

    ericrisco/rsc-harness

    A skill your agent uses when projecting history forward — sales, demand, units, revenue, signups, traffic — into a defensible number with an error band: method by data shape, rolling-origin…

    180 GitHub stars~2.8k tokensUpdated 2 days ago
    Data & AnalyticsAuto-check passed
  • 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 3 repos~1.3k tokens
    Business, Finance & HRAuto-check passed

More from Yijia-Xiao/FinanceHarness

  • Dcf Valuation

    Yijia-Xiao/FinanceHarness

    Estimate a public equity's intrinsic value with a discounted-cash-flow model — pull fundamentals, set a discount rate via CAPM/WACC, project free cash flow, and discount it.

    196 GitHub stars~508 tokensUpdated 1 mo ago
    Auto-check passed
  • Equity Deep Dive

    Yijia-Xiao/FinanceHarness

    A thorough single-equity deep dive — read the recent qualitative picture from the web, then ground it in fundamentals and health ratios, an intrinsic DCF with a sensitivity range, a…

    196 GitHub stars~643 tokensUpdated 1 mo ago
    Auto-check passed
  • Consensus Check

    Yijia-Xiao/FinanceHarness

    Summarize the sell-side view on an equity — analyst price targets, forward EPS/revenue estimates and ratings — and corroborate it against recent guidance and estimate revisions from the web.

    196 GitHub stars~374 tokensUpdated 1 mo ago
    Auto-check passed
  • Ticker Snapshot

    Yijia-Xiao/FinanceHarness

    Quick structured overview of a single public equity — identity, sector, market cap, valuation ratios, current price, recent trend.

    196 GitHub stars~253 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Relative Valuation

What does Relative Valuation do?

Value an equity against its peers — peer-median trading multiples applied to the company's metrics for an implied range, cross-read against its own valuation ratios. Relative Valuation is an agent skill from Yijia-Xiao/FinanceHarness. Value an equity against its peers — peer-median trading multiples applied to the company's metrics for an implied range, cross-read against its own valuation ratios.

When should I use Relative Valuation?

Relative Valuation fits situations like: tasks that involve Financial modeling; tasks that involve Trading and backtesting.

How do I install Relative Valuation in Claude Code?

Run `npx skills add Yijia-Xiao/FinanceHarness --skill relative-valuation -a claude-code`. Or copy the skill folder (financeharness/skills/relative-valuation in Yijia-Xiao/FinanceHarness) into .claude/skills/relative-valuation in your project. Claude Code loads it when a task matches its description.

How do I install Relative Valuation in Codex?

Run `npx skills add Yijia-Xiao/FinanceHarness --skill relative-valuation -a codex`. Or copy the skill folder (financeharness/skills/relative-valuation in Yijia-Xiao/FinanceHarness) into .agents/skills/relative-valuation in your project. Codex loads it when a task matches its description.

Can I use Relative Valuation 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 Yijia-Xiao/FinanceHarness --skill relative-valuation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/relative-valuation, .gemini/skills/relative-valuation, .github/skills/relative-valuation and .opencode/skills/relative-valuation in your project.

What does Relative Valuation need to run?

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

Does Relative Valuation 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 Relative Valuation 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 Relative Valuation use?

Relative Valuation 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 Relative Valuation use?

About 446 tokens (SKILL.md is roughly 1.8k 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 Relative Valuation?

Skills that share tags, products or a category with Relative Valuation: Backtest Execution Modeling (HKUDS/Vibe-Trading, 35k stars), Market Microstructure Analysis (HKUDS/Vibe-Trading, 35k stars), Advanced Options Strategies (HKUDS/Vibe-Trading, 35k stars) and Options Strategy Backtesting (HKUDS/Vibe-Trading, 35k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Relative Valuation?

Yijia-Xiao (a GitHub user) maintains it in Yijia-Xiao/FinanceHarness, which has 196 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on August 22, 2026.

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