Token导航 LogoToken导航

Agent Skill · 研究检索

peer-comparison(同行比较)

peer-comparison 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

peer-comparison 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 65,745。

总安装 275周安装 11GitHub Stars 4下载 89核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:peer-comparison(同行比较)
来源仓库:https://github.com/tradeinsight-info/investment-analysis-skills
仓库路径:skills/peer-comparison
安装命令:
npx skills add https://github.com/tradeinsight-info/investment-analysis-skills --skill peer-comparison
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/tradeinsight-info/investment-analysis-skills --skill peer-comparison

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

peer-comparison 支持企业财务指标与行业基准的横向对比分析。适用于投资研究、竞品评估与业务健康度诊断场景。可提取营收增长率、利润率与市场占比等关键数据进行可视化呈现。数据来源需注明出处,避免使用非公开或过时信息作为结论依据。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/peer-comparison

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/tradeinsight-info/investment-analysis-skills -…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

peer-comparison 怎么安装?

在终端执行 npx skills add https://github.com/tradeinsight-info/investment-analysis-skills --skill pee…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

peer-comparison 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

peer-comparison 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

peer-comparison 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

peer-comparison 用的人多吗?

公开数据是累计安装 275 次,近一周安装 11 次,下载 89 次,GitHub 4 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

peer-comparison 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
peer-comparison

同行比较 · 本页

2754需要联网未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Peer Comparison

Purpose

Compare a target company against its closest public-market peers across a standardized set of financial, profitability, and valuation metrics. Identify the peer set dynamically, fetch comparable data for each company, and present a side-by-side table that highlights where the target outperforms or underperforms relative to its competitive group. Provide brief interpretive commentary so the user can quickly understand the target's relative positioning.

Data Fetching Process

Consult ${CLAUDE_PLUGIN_ROOT}/skills/_shared/references/data-sources.md for full source details and fallback behavior.

Peer Identification

  1. Determine the target company. Resolve the ticker to a CIK by fetching https://www.sec.gov/files/company_tickers.json using the sec-fetch skill (see data-sources.md). Cache the CIK and official company name.
  2. Identify peers. If the user explicitly provides a list of comparison companies, use those. Otherwise, identify three to five closest public competitors through the following process:

- Use WebSearch to query "{company name} competitors publicly traded" or "{company name} peer companies stock market." - Cross-reference results with the company's 10-K Item 1 (Business) section, which often names competitors. - Prefer peers that share the same primary SIC code or GICS sub-industry classification. - Prefer peers with market capitalizations within a reasonable range (0.25x to 4x the target's market cap) to ensure meaningful comparison. If the target is a mega-cap, include at least one large-cap peer and note the size differential. - Exclude private companies, foreign-listed companies without US ADRs (unless specifically requested), and companies in unrelated industries that happen to have similar names.

  1. Confirm the peer set. List the selected peers with their tickers and brief business descriptions. If the user did not specify peers, present the proposed set and proceed unless the composition is clearly unsuitable.

Data Collection

  1. Fetch comparison data for each company. For the target and each peer, collect the following metrics. Use the source priority matrix from the data-sources reference. Primary approach — Stock Analysis ratios page: https://stockanalysis.com/stocks/{ticker}/financials/ratios/ Fetch the ratios page for each company. Extract the most recent annual values for all available metrics. Secondary approach — SEC EDGAR XBRL API: https://data.sec.gov/api/xbrl/companyfacts/CIK{10-digit-CIK}.json Extract raw financial figures and compute ratios manually when Stock Analysis data is unavailable or incomplete. Tertiary approach — EDGAR frames endpoint for cross-company single-metric comparison: https://data.sec.gov/api/xbrl/frames/us-gaap/{concept}/{unit}/CY{year}.json Use when comparing a single metric across many companies simultaneously.
  2. Fetch supplementary valuation data. For market-cap-dependent ratios (P/E, EV/EBITDA, P/FCF), fetch current price data from Stock Analysis: https://stockanalysis.com/stocks/{ticker}/ Alternatively, use WebSearch to confirm current market capitalization and enterprise value figures.

Analysis Steps

Comparison Metrics Table

Assemble the following metrics for the target and all peers. Present them in a single side-by-side table:

Metric CategoryMetricComputation / Source
ScaleRevenue (TTM)Most recent four quarters summed, or latest annual
GrowthRevenue Growth (YoY)Current year revenue / prior year revenue minus one
ProfitabilityGross MarginGross profit / revenue
ProfitabilityOperating MarginOperating income / revenue
ProfitabilityNet MarginNet income / revenue
ReturnsReturn on Equity (ROE)Net income / average stockholders' equity
ReturnsReturn on Invested Capital (ROIC)NOPAT / average invested capital
ValuationPrice-to-Earnings (P/E)Market cap / net income, or share price / diluted EPS
ValuationEV/EBITDAEnterprise value / EBITDA
ValuationPrice-to-Free-Cash-Flow (P/FCF)Market cap / free cash flow
LeverageDebt-to-Equity (D/E)Total debt / stockholders' equity
Cash GenerationFree Cash Flow MarginFree cash flow / revenue
Shareholder ReturnDividend YieldAnnual dividend per share / share price

If a metric is unavailable for a specific peer (e.g., the company does not pay dividends), enter "N/A" rather than omitting the column. Use trailing-twelve-month (TTM) figures when available; otherwise, use the most recent fiscal year.

Relative Positioning

After building the table, analyze the target's position:

  • Rank the target within the peer group for each metric. Note where the target ranks first (best), last (worst), or in the middle.
  • Identify standout strengths. Highlight metrics where the target is in the top quartile of the peer group. Explain why these strengths matter (e.g., "highest operating margin indicates superior cost control or pricing power").
  • Identify relative weaknesses. Highlight metrics where the target is in the bottom quartile. Provide context (e.g., "lowest revenue growth but highest margin may indicate a mature, cash-generative business rather than a deteriorating one").
  • Valuation vs. fundamentals. Compare the target's valuation multiples to its fundamental performance. Note if the target trades at a premium or discount relative to peers, and assess whether the premium or discount is justified by superior or inferior fundamentals.

Commentary

Provide a brief narrative (three to five sentences at summary depth) covering:

  • Overall competitive positioning of the target within its peer group.
  • The one or two most significant advantages the target holds.
  • The one or two most significant areas where the target lags.
  • Whether the current valuation appears reasonable, stretched, or compressed relative to the peer set and why.

Sector-Specific Adjustments

Adapt the comparison table to include sector-relevant metrics when the peer set belongs to a specific industry:

  • SaaS / Software: Add Rule of 40 (revenue growth rate plus FCF margin), net revenue retention if disclosed.
  • Banking / Financial Services: Replace gross margin with net interest margin (NIM). Add Tier 1 capital ratio and return on tangible common equity (ROTCE). Replace EV/EBITDA with price-to-tangible-book.
  • REITs: Add funds from operations (FFO), price-to-FFO, and occupancy rate. Replace net margin with FFO margin.
  • Retail: Add same-store sales growth and revenue per square foot if available.
  • Energy: Add production growth, reserve replacement ratio, and lifting cost per barrel if available.

Depth Handling

Consult ${CLAUDE_PLUGIN_ROOT}/skills/_shared/references/output-format.md for standard formatting rules.

  • Summary depth (default). Present the comparison table with the 13 core metrics, the target column visually highlighted (bold or marked with an asterisk), and a three-to-five sentence commentary. Omit sector-specific metrics unless the sector is obvious and the data is readily available.
  • Detailed depth. Expand the table to include sector-specific metrics, add a second table showing three-year trends for growth and margin metrics across all peers, include a relative valuation scatter discussion (P/E vs. growth, EV/EBITDA vs. margin), and extend commentary to a full paragraph per metric category.

Output

Follow the output structure defined in ${CLAUDE_PLUGIN_ROOT}/skills/_shared/references/output-format.md. Begin with the standard header using "Peer Comparison" as the analysis type. Present the main comparison table with the target company's column marked (e.g., bold ticker or asterisk) so it is immediately identifiable. Include source links for each peer's data after the table. Close with the standard disclaimer.

Format the comparison table as:

MetricTARGET*Peer 1Peer 2Peer 3Peer 4
Revenue ($B)XX.XXX.XXX.XXX.XXX.X
Revenue GrowthXX.X%XX.X%XX.X%XX.X%XX.X%
..................

Mark the best value in each row with an upward indicator and the worst with a downward indicator where directionality is clear (higher is better for margins; lower is better for leverage).

平台分布

Codex

33.93%
按下载量换算30

Claude

30.63%
按下载量换算27

Cursor

18.97%
按下载量换算17

Gemini CLI

10.36%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills