New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Comps

by daloopa in daloopa/investing

Trading comparables analysis with peer multiples and implied valuation

Apache-2.0Auto-check passedBusiness, Finance & HR

Install Comps

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

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

GitHub CLI
$ gh skill install daloopa/investing comps --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/comps .claude/skills/comps && 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
comps
GitHub stars
489
Token cost
~2.5k tokens
SKILL.md length
1,122 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
Apache-2.0

At a glance

Trading comparables analysis with peer multiples and implied valuation

  • Works in 10 steps: Company Lookup → Identify Peer Group → Target Company Fundamentals → …
  • Tasks that involve Trading and backtesting
  • SKILL.md covers 1. Company Lookup, 2. Identify Peer Group, 3. Target Company Fundamentals and 4. Stock Prices & Valuation…, plus 7 more sections
  • Reaches daloopa.com

What it does

Comps is an agent skill from daloopa/investing. Trading comparables analysis with peer multiples and implied valuation

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 Trading and backtesting. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Trading and backtesting

Example prompts

  • “/comps”

Workflow steps

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

  1. Company Lookup
  2. Identify Peer Group
  3. Target Company Fundamentals
  4. Stock Prices & Valuation Multiples
  5. Peer Fundamentals from Daloopa
  6. Build Comps Table
  7. Implied Valuation
  8. Consensus Forward Estimates (if available)
  9. Premium/Discount Analysis
  10. Save Report

What it can do on your machine

Read from SKILL.md and the folder at commit f46f350. 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

Comps loads about 2.5k tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 1,122 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~19
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 f46f350, republished under its Apache-2.0 licence (© daloopa). 1,122 words, ~2,476 tokens.

Download SKILL.mdSave it as .claude/skills/comps/SKILL.md (or your agent's skills folder).
name
comps
description
Trading comparables analysis with peer multiples and implied valuation
argument-hint
TICKER

Build a trading comparables analysis 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. Identify Peer Group

Based on the company's business model, sector, size, and competitive landscape, identify 5-10 comparable companies. Consider:

  • Direct competitors in the same market
  • Business model peers (similar revenue model even if different sector)
  • Size peers (similar market cap range)
  • Growth profile peers (similar growth rate)

Prioritize relevance over size matching. A direct competitor at a different scale is more useful than a similar-sized company in a different industry.

List the peer tickers and briefly justify each selection (1 sentence).

3. Target Company Fundamentals

Calculate 4 quarters backward from latest_calendar_quarter. Pull from Daloopa for the target company:

  • Revenue (compute trailing 4Q total)
  • EBITDA (compute trailing 4Q; if not available, use Op Income + D&A, label "(calc.)")
  • Net Income (trailing 4Q)
  • Diluted EPS (trailing 4Q sum)
  • Free Cash Flow (trailing 4Q; compute as OCF - CapEx, label "(calc.)")
  • Revenue YoY growth (most recent quarter)
  • Operating Margin (most recent quarter)
  • Net Margin (most recent quarter)

4. Stock Prices & Valuation Multiples

Use get_stock_prices (see ../data-access.md Section 1.7) to pull current prices for the target AND all peers in a single batch call — pass all company_ids together with dates = 3 most recent calendar days.

Compute valuation multiples by combining stock prices with the fundamentals pulled in Sections 3 and 5:

  • Market Cap = Close price × Diluted shares outstanding
  • Enterprise Value = Market Cap + Total Debt - Cash (from Daloopa balance sheet if available)
  • P/E (trailing) = Market Cap / Net Income (trailing 4Q)
  • EV/EBITDA = EV / EBITDA (trailing 4Q)
  • P/S = Market Cap / Revenue (trailing 4Q)
  • P/B = Market Cap / Total Equity
  • FCF Yield = FCF (trailing 4Q) / Market Cap
  • Dividend Yield = Dividends Paid (trailing 4Q) / Market Cap

For beta, PEG ratio, and forward multiples, use infra scripts, consensus data, or web search (see ../data-access.md Sections 2-3).

If a peer isn't in Daloopa (no company_id), fall back to ../data-access.md Section 2 resolution order for market data. If a peer ticker fails (delisted, no data), drop it and note why.

5. Peer Fundamentals from Daloopa

For each peer that is available in Daloopa:

  • Look up the company
  • Calculate 4 quarters backward from latest_calendar_quarter. Pull revenue, operating income, net income for those periods.
  • Compute revenue growth YoY, operating margin, net margin

For peers not in Daloopa, rely on market data multiples only (see ../data-access.md Section 2) and note the data source limitation.

5.5. Peer Operational KPIs

For each company (target + all peers available in Daloopa), discover and pull company-specific operational KPIs. Use the sector taxonomy below 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

Pull the same 4 calendar quarters for each peer. Not all peers will have the same KPIs — build a sparse matrix and note which are comparable across the group vs company-specific.

Add KPI columns to the comps table in Section 6 where comparable metrics exist (e.g., subscriber growth, ARPU, units alongside P/E and EV/EBITDA). This shows whether valuation premiums are supported by operational outperformance.

6. Build Comps Table

Create the main comparables table with these columns: | Company | Ticker | Mkt Cap | EV | P/E | Fwd P/E | EV/EBITDA | P/S | Rev Growth | Op Margin | Net Margin | FCF Yield |

Sort by market cap descending. Include:

  • Peer median row
  • Peer mean row
  • Target company row (highlighted / separated)
  • Target's percentile rank within the peer group for each metric
Show full SKILL.md (439 more words)Show less

7. Implied Valuation

Apply peer group median and mean multiples to the target's fundamentals:

MethodologyPeer Median MultipleTarget MetricImplied Value
P/EXX.Xx$X.XX EPS$XXX
EV/EBITDAXX.Xx$XXX EBITDA$XXX
P/SXX.Xx$XXX Revenue$XXX
FCF YieldX.X%$XXX FCF$XXX

For each:

  • Implied Enterprise Value = Multiple × Target's Metric
  • Implied Equity Value = EV - Net Debt (for EV-based multiples) or direct (for equity multiples)
  • Implied Share Price = Equity Value / Shares Outstanding

Compute range (min to max implied price) and central tendency.

8. Consensus Forward Estimates (if available)

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

  • Add NTM (next twelve months) revenue and EPS estimates for target and each peer
  • Compute forward P/E and forward EV/EBITDA using consensus NTM estimates
  • Note where the target's forward multiples sit vs the peer group
  • Flag any peers with significant estimate revision trends

If consensus data is not available, use trailing multiples only and note the limitation.

9. Premium/Discount Analysis

Assess whether the target trades at a premium or discount to peers:

  • For each multiple, show target vs peer median as a % premium/discount
  • Consider whether a premium/discount is justified based on:
    • Growth differential (higher growth = deserves premium)
    • Margin differential (higher margins = deserves premium)
    • Market position (leader vs challenger)
    • Risk profile

Be honest about whether the premium is truly justified:

  • A company can deserve a premium and still be overvalued if the premium has stretched too far beyond fundamentals. Quantify: how much growth differential is needed to justify the current premium? Is the company delivering that?
  • If the stock trades at a significant premium but growth is decelerating toward peer levels, flag the derating risk explicitly.
  • Don't default to "premium is justified because it's the market leader" — that's already in the price. What justifies the premium expanding or sustaining from here?
  • Reference KPI outperformance as justification (or lack thereof). Example: "AAPL trades at 34x P/E vs peer median 28x — premium partly justified by +14% Services growth vs peer median +8%, but Wearables decline (-2.2% YoY) is a drag peers don't have." If the target's KPIs are in line with or worse than peers, the premium is harder to defend.

10. Save Report

Save to reports/{TICKER}_comps.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}) — Comparable Companies Analysis</h1>
<p>Generated: {date}</p>

<h2>Summary</h2>
{2-3 sentences: Where does the company trade relative to peers? Is it cheap or expensive and why?}

<h2>Peer Group Selection</h2>
<table>
| Peer | Ticker | Rationale |
{table with justification for each peer}
</table>

<h2>Comparables Table</h2>
<table>
| Company | Ticker | Mkt Cap | P/E | Fwd P/E | EV/EBITDA | P/S | Rev Growth | Op Margin |
{full comps table with target highlighted}
| **Peer Median** | | | XX.Xx | XX.Xx | XX.Xx | XX.Xx | X.X% | X.X% |
| **Peer Mean** | | | XX.Xx | XX.Xx | XX.Xx | XX.Xx | X.X% | X.X% |
| **{TICKER}** | | | **XX.Xx** | **XX.Xx** | **XX.Xx** | **XX.Xx** | **X.X%** | **X.X%** |
</table>

<h2>Target vs Peer Premium/Discount</h2>
<table>
| Multiple | Target | Peer Median | Premium/Discount |
{table showing where target is rich/cheap}
</table>

<h2>Implied Valuation</h2>
<table>
| Methodology | Multiple | Target Metric | Implied Price | vs Current |
{table with implied values}
</table>

<table>
| **Valuation Range** | **Low** | **Median** | **High** |
| Implied Price | $XXX | $XXX | $XXX |
| vs Current Price | -X% | +X% | +X% |
</table>

<h2>Premium/Discount Justification</h2>
{Analysis of whether current premium/discount is warranted}

<h2>Peer Operational KPIs</h2>
<table>
| KPI | {TICKER} | Peer 1 | Peer 2 | ... | Peer Median |
{KPI comparison table — sparse where data unavailable, footnoted}
</table>

<h2>Key Observations</h2>
<ul>{3-5 bullet points on relative valuation, standout metrics, peer group dynamics, KPI differentiation}</ul>

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

Tell the user where the HTML report was saved.

Highlight: where the stock trades relative to peers (premium/discount), the implied valuation range, and the most relevant multiple for this company.

© 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/comps of daloopa/investing.

Open the folder on GitHubat commit f46f350

Compare with similar skills

Comps 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.

Comps compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Comps this skilldaloopa/investing489—~2.5kAutomated safety check: PassApache-2.0
Tushare Datazillionare/zillionare3182 repos~2.3kAutomated safety check: PassNone
Tradingview MCPatilaahmettaner/tradingview-mcp4.9k—~1.3kAutomated safety check: PassMIT
Digital Oraclekomako-workshop/digital-oracle867—~5.9kAutomated safety check: PassMIT
Polyclawchainstacklabs/polyclaw3601 repos~2kAutomated safety check: PassApache-2.0
Markdownfacioquo/stock-indicators-dotnet1.2k—~812Automated safety check: PassApache-2.0

Similar skills

  • Tushare Data

    zillionare/zillionare

    面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求，转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。

    318 GitHub starsUsed in 2 repos~2.3k tokens
    Business, Finance & HRAuto-check passed

  • Tradingview MCP

    atilaahmettaner/tradingview-mcp

    AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and…

    4.9k GitHub stars~1.3k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed

  • Digital Oracle

    komako-workshop/digital-oracle

    Answer prediction questions using market trading data, not opinions.

    867 GitHub stars~5.9k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed

  • Polyclaw

    chainstacklabs/polyclaw

    Trade on Polymarket via split + CLOB execution. An agent skill from chainstacklabs/polyclaw.

    360 GitHub starsUsed in 1 repo~2k tokens
    Business, Finance & HRAuto-check passed

  • Markdown

    facioquo/stock-indicators-dotnet

    Format and lint Markdown in this repository against GitHub Flavored Markdown and its markdownlint-cli2 configuration — headers, lists, code fences, callouts (VitePress containers on docs-site pages…

    1.2k GitHub stars~812 tokensUpdated today
    Business, Finance & HRAuto-check passed

  • Openmobius Skill

    MobiusQuant/OpenMobius-skill

    Provides multi-school trading Q&A, chart/OHLCV analysis, annotation, and fresh-market workflows covering ICT/SMC, ChanLun, Wyckoff, Price Action, Order Flow, VSA, and Elliott Wave.

    695 GitHub stars~7.2k tokensUpdated 1 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 2 mo ago
    Auto-check passed

  • Comp Sheet

    daloopa/investing

    Build an industry comp sheet Excel model with deep operational KPIs

    489 GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed

  • Dcf

    daloopa/investing

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

    489 GitHub stars~2.5k tokensUpdated 2 mo ago
    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 2 mo ago
    Auto-check passed

  • Guidance Tracker

    daloopa/investing

    Track management guidance accuracy over time for a given company

    489 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed

  • Inflection

    daloopa/investing

    Auto-detect biggest acceleration/deceleration inflections across all metrics

    489 GitHub stars~1.5k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Comps

What does Comps do?

Trading comparables analysis with peer multiples and implied valuation. Comps is an agent skill from daloopa/investing.

When should I use Comps?

Comps fits situations like: tasks that involve Trading and backtesting.

How do I install Comps in Claude Code?

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

How do I install Comps in Codex?

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

Can I use Comps 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 comps -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/comps, .gemini/skills/comps, .github/skills/comps and .opencode/skills/comps in your project.

What does Comps need to run?

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

Does Comps 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 Comps 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 Comps use?

Comps 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 Comps use?

About 2.5k tokens (SKILL.md is roughly 9.9k 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 Comps?

Skills that share tags, products or a category with Comps: Tushare Data (zillionare/zillionare, 318 stars), Tradingview MCP (atilaahmettaner/tradingview-mcp, 4.9k stars), Digital Oracle (komako-workshop/digital-oracle, 867 stars) and Polyclaw (chainstacklabs/polyclaw, 360 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Comps?

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 July 22, 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.