LightAgent is a lightweight Python framework for building AI agents with tools, memory, guardrails, tracing, workflows, and collaboration between multiple agents. It supports developers who want reusable agent capabilities and OpenAI-compatible streaming interfaces.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add wanxingai/LightAgent --skill comparable-company-analysisgit clone --depth 1 https://github.com/wanxingai/LightAgentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wanxingai/lightagent/comparable-company-analysis)<a href="https://agentmods.dev/skills/wanxingai/lightagent/comparable-company-analysis"><img src="https://agentmods.dev/badge/skills/wanxingai/lightagent/comparable-company-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wanxingai/lightagent/comparable-company-analysis"><img src="https://agentmods.dev/badge/skills/wanxingai/lightagent/comparable-company-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.03032 |
| Opus 5 | $0.00023 | $0.01516 |
| Sonnet 5 | $0.00009 | $0.00606 |
| Haiku 4.5 | $0.00005 | $0.00303 |
Grade A, and why
comparable-company-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
可比公司分析 - 上市公司同业对标分析框架
针对目标上市公司，从业务剖析、可比公司筛选、对比分析、财务数据对比四个维度输出结构化可比公司分析报告。
输入参数
| 字段 | 是否必填 | 说明 |
|---|---|---|
| 目标公司 | 必填 | 如"中际旭创"、"宁德时代"、"药明康德" |
| 分析维度 | 选填 | 如"全面分析"、"仅财务对比"、"仅业务对标"，不填则默认全面分析 |
数据获取流程
Step 1: 业务剖析数据获取
1. 调用 yiyanxuangu MCP 获取目标公司基本信息：
get_stock_basic_info(stock_code="目标公司代码")
获取公司所属行业、概念板块、主营业务描述
2. 调用 yiyanxuangu MCP 获取目标公司财务数据：
get_stock_financial_data(stock_code="目标公司代码")
获取最新一期营收、净利润、毛利率、各业务线收入（如有）
3. 调用 万行-news API（太一数据/万行数据 MCP web_search），关键词组合：
- "[目标公司] 业务 产品 收入 拆分" (近6个月) — 获取业务结构
- "[目标公司] 核心竞争力 护城河" (近1年) — 获取竞争力分析
- "[目标公司] 研报 深度 分析" (近3个月) — 获取券商研报观点
Step 2: 可比公司筛选
1. 调用 万行-news API，搜索可比公司：
- "[目标公司] 竞争对手 可比公司" (近1年)
- "[目标公司] 同业 竞品 对标" (近1年)
- "[目标公司所在行业] 龙头 上市公司 排名" (近6个月)
2. 调用 yiyanxuangu MCP 验证可比公司代码：
get_stock_basic_info(stock_code="可比公司1代码,可比公司2代码,...")
确保所有可比公司为A股上市公司，获取最新行业分类
3. 筛选5-10家A股上市可比公司，按业务相关性排序
Step 3: 可比公司对比分析
1. 调用 万行-news API，获取各可比公司业务进展：
- "[可比公司名] 业务 进展 订单 产能 出货量" (近6个月)
- "[可比公司名] 新产品 新技术 客户" (近3个月)
2. 调用 yiyanxuangu MCP 获取各可比公司财务数据：
get_stock_financial_data(stock_code="可比公司1代码,可比公司2代码,...")
获取最新一期年度累计财务数据（营收、净利、毛利率、ROE等）
Step 4: 财务数据对比
1. 确保所有可比公司财务数据已获取，如有缺失则单独调用：
get_stock_financial_data(stock_code="缺失公司代码")
2. 整理对比表格，包含：
- 营收规模及增速
- 净利润及增速
- 毛利率、净利率
- ROE、ROA
- 估值指标（PE、PB）
报告模板
# [目标公司名称] 可比公司分析报告
**目标公司**：[公司全称]（[股票代码]）
**所属行业**：[申万/中信行业分类]
**报告类型**：可比公司分析（买方视角）
**生成时间**：[YYYY-MM-DD HH:MM]
---
## 一、业务剖析
[用一句话概括目标公司核心竞争力，如"XX公司是国内XX领域龙头，凭借XX技术/渠道/规模优势，在XX细分市场占据XX%份额。"]
**[业务板块1名称]**：[首句加粗提炼重点。包含业务当前状态（营收、占比）、核心驱动力、竞争力、市场前景等，引用数据或事实支撑。论述自然流畅，避免模板化起手式。]
**[业务板块2名称]**：[同上结构，区分成熟业务与新兴业务，但不显式标注"成熟/新兴"。]
**[业务板块3名称]**：[如有，同上。]
---
## 二、可比公司筛选
**[业务分类1]可比公司**：[首句加粗提炼重点。以直接竞争者为主，可辅以战略相似者。列出该业务线的主要A股上市竞争对手，简述竞争格局。]
**[业务分类2]可比公司**：[同上。以细分赛道对标者为主，关注产业链环节、技术及客户验证情况。]
### 可比公司表格
| 分类 | 公司名称 | 公司代码 | 可比业务 | 相关业务进展（需带业务数据或事件佐证，禁止列举财务数据） |
| ---- | -------- | -------- | -------- | -------------------------------------------------------- |
| [如"光模块"] | [公司A] | [代码] | [细分业务] | [如"其800G光模块2025年出货量达XX万只，已切入北美头部云厂商供应链"] |
| [如"光模块"] | [公司B] | [代码] | [细分业务] | [如"1.6T光模块已完成客户验证，预计2026年Q2开始批量交付"] |
| [如"光芯片"] | [公司C] | [代码] | [细分业务] | [如"EML光芯片月产能突破XX万只，良率提升至XX%"] |
| ... | ... | ... | ... | ... |
> 注：相关业务进展必须包含具体业务数据（如出货量、产能、市占率）或事件（如产品发布、客户签约、技术突破），禁止填写财务数据（如营收、利润、毛利率）。
---
## 三、可比公司对比分析
### 可比公司对比表格
| 公司名称 | 维度对比 |
| -------- | -------- |
| **[公司A]** | **业务对标**：<br>• [可比点1，如"双方在800G光模块市场占有率均位于国内前三，2025年合计份额超60%。"]<br>• [可比点2，如"均布局1.6T下一代产品，预计2026年进入量产阶段。"]<br>**竞争焦点**：<br>• [关键点1，如"目标公司在硅光技术路线上领先，而该公司在传统EML方案上成本控制更优。"] |
| **[公司B]** | **业务对标**：<br>• [可比点1]<br>• [可比点2]<br>**竞争焦点**：<br>• [关键点1] |
| **[公司C]** | **业务对标**：<br>• [可比点1]<br>• [可比点2]<br>**竞争焦点**：<br>• [关键点1] |
| ... | ... |
---
## 四、财务数据对比
### 可比公司财务对比表格
| 公司名称 | 公司代码 | 营收（亿元） | 营收增速 | 净利润（亿元） | 净利增速 | 毛利率 | 净利率 | ROE | PE（TTM） | PB |
| -------- | -------- | ------------ | -------- | -------------- | -------- | ------ | ------ | --- | --------- | -- |
| **[目标公司]** | [代码] | [数值] | [X%] | [数值] | [X%] | [X%] | [X%] | [X%] | [X] | [X] |
| [公司A] | [代码] | [数值] | [X%] | [数值] | [X%] | [X%] | [X%] | [X%] | [X] | [X] |
| [公司B] | [代码] | [数值] | [X%] | [数值] | [X%] | [X%] | [X%] | [X%] | [X] | [X] |
| [公司C] | [代码] | [数值] | [X%] | [数值] | [X%] | [X%] | [X%] | [X%] | [X] | [X] |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
> 注：财务数据为最新一期年度累计数据（如2025年年报或2026年Q3）。PE/PB为最新交易日数据。
### 财务对比分析
**规模对比**：[分析营收/净利润规模梯队，目标公司所处位置]
**盈利能力对比**：[分析毛利率、净利率、ROE差异及原因]
**成长性对比**：[分析营收/净利增速差异，谁更具成长弹性]
**估值对比**：[分析PE/PB估值分位，目标公司相对可比公司是溢价还是折价，是否合理]
---
## 五、综合结论
| 维度 | 结论 |
| ---- | ---- |
| **行业地位** | [目标公司在行业中的竞争地位：龙头/追赶者/细分冠军] |
| **核心优势** | [1-2个核心竞争优势] |
| **主要短板** | [1-2个相对可比公司的短板] |
| **估值判断** | [相对可比公司，当前估值是否合理/高估/低估] |
| **投资启示** | [从可比公司视角看，目标公司的投资价值与风险] |
---
**数据来源**：yiyanxuangu MCP、万行新闻（太一数据/万行数据）
**免责声明**：本报告仅供投研参考，不构成投资建议。市场有风险，投资需谨慎。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 216 lines · 46 tokens per session scan A 88e565b2dd66
comparable-company-analysis is a skill published in the GitHub repository wanxingai/LightAgent (1,218 stars, last pushed 4d ago), licensed Apache-2.0. It adds 46 tokens to every session and 3,032 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
risk-scoring
Score how concentrated and risky a portfolio is on a 0-100 scale from its position weights. Use when the user asks how risky their portfolio is, whether it is too concentrated, or for a diversification check.
valuation
Estimate whether a stock looks cheap or expensive using a price-to-earnings (P/E) based fair-value method. Use when the user asks if a stock is over- or under-valued, or for a fair-value / target price.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
python-package-management
Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
verify-samples-tool
How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.