Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/stophobia/deerflow2.0-enhancednpx agentmods add skills/stophobia/deerflow2.0-enhanced/company-researchWrote 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/stophobia/deerflow2.0-enhanced/company-research)<a href="https://agentmods.dev/skills/stophobia/deerflow2.0-enhanced/company-research"><img src="https://agentmods.dev/badge/skills/stophobia/deerflow2.0-enhanced/company-research/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/stophobia/deerflow2.0-enhanced/company-research"><img src="https://agentmods.dev/badge/skills/stophobia/deerflow2.0-enhanced/company-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00113 | $0.02116 |
| Opus 5 | $0.00056 | $0.01058 |
| Sonnet 5 | $0.00023 | $0.00423 |
| Haiku 4.5 | $0.00011 | $0.00212 |
Grade A, and why
company-research 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 11d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
企业综合调研技能 (Company Research)
综合多数据源的企业背景调研技能，适用于尽职调查、合作伙伴评估、投资分析、市场研究等场景。
概述
本技能通过整合多个数据源对企业进行全面调研：
- 工商信息（注册信息、股东结构、主要人员）
- 财务数据（融资历史、营收状况）
- 法律风险（诉讼记录、被执行信息）
- 舆情监测（媒体报道、社交口碑）
- 竞品分析（市场份额、功能对比）
- 行业趋势（市场规模、发展预测）
使用场景
当用户提及以下内容时激活：
- "企业调研"、"公司背景调查"
- "尽职调查"、"DD"
- "合作伙伴评估"、"供应商审核"
- "投资分析"、"投资尽调"
- "市场研究"、"行业分析"
- "竞争对手分析"、"竞品分析"
- "背景核实"、"高管履历"
核心能力
1. 工商信息采集
- 企业工商注册信息查询
- 股东结构与股权分布
- 主要人员与组织架构
- 变更历史记录
- 分支机构与关联公司
2. 财务状况分析
- 融资历史与投资方
- 营收与盈利状况
- 税务信息
- 银行信用评估
- 并购重组历史
3. 法律风险调查
- 诉讼记录查询
- 被执行人信息
- 失信被执行人
- 行政处罚记录
- 经营异常记录
- 股权冻结信息
4. 舆情监测
- 媒体报道收集
- 社交媒体口碑
- 行业评价分析
- 负面信息预警
- 危机事件追踪
5. 竞品分析（当需要时）
- 竞品识别与列表
- 产品功能对比矩阵
- 定价策略分析
- 市场定位对比
- 优劣势总结
6. 行业研究（当需要时）
- 市场规模数据
- 行业发展趋势
- 政策环境分析
- 准入壁垒评估
- 增长驱动因素
调研方法论
Phase 1: 目标确认
明确调研目标：
- 调研目的是什么？（投资/合作/采购/招聘...）
- 需要调研到什么深度？
- 有什么特定关注点？
Phase 2: 信息收集
优先级顺序：
- 官方数据源（工商、财报、官网）
- 权威第三方（天眼查、企查查、启信宝）
- 新闻媒体报道
- 行业报告
- 社交媒体评价
- 用户评价
常用数据源：
# 工商信息
天眼查、企查查、国家企业信用信息公示系统
# 财务数据
年报、财报、融资披露
# 法律信息
中国裁判文书网、中国执行信息公开网
# 舆情信息
百度新闻、Google News、微博、雪球
# 行业数据
艾瑞咨询、易观分析、IDC、Gartner
Phase 3: 分析整理
对收集的信息进行分类整理：
- 事实性信息 - 可验证的数据
- 推断性信息 - 基于证据的合理推测
- 评估性信息 - 需要标注置信度
Phase 4: 报告生成
生成结构化调研报告，包括：
- 执行摘要（结论先行）
- 企业概况
- 股权结构
- 财务状况
- 法律风险评估
- 舆情分析
- 竞品/行业分析（如适用）
- 风险评级
- 调研依据
- 附录
报告输出格式
格式要求
- 语言：根据
output_locale设置（默认zh_CN） - 格式：Markdown → HTML（使用 md2html.py 转换）
- 标题：使用企业全称
- 数据标注：所有数据必须标注来源和置信度
- 日期：报告生成日期
置信度标注
| 等级 | 标注 | 说明 |
|---|---|---|
| 高 | 🟢 高置信 | 官方来源，多源验证 |
| 中 | 🟡 中等置信 | 可靠来源，单一验证 |
| 低 | 🔴 低置信 | 非官方，推测性质 |
风险评级
| 等级 | 标注 | 建议 |
|---|---|---|
| 低风险 | ✅ 绿灯 | 可正常合作 |
| 中风险 | ⚠️ 黄灯 | 需进一步核实 |
| 高风险 | 🔴 红灯 | 建议谨慎合作 |
数据真实性协议
严格遵守：
- 所有数据必须有明确来源
- 无法确认的数据标注"未确认"
- 模拟数据标注"模拟数据"
- 推测性内容标注"推测"
- 禁止编造数据
使用工具
调研阶段
web_search- 搜索企业信息web_fetch- 获取详细页面feishu_search_doc_wiki- 搜索内部文档feishu_bitable_app_table_record- 查询内部数据（如有）
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.
- 11d ago First seen · 278 lines · 113 tokens per session scan A 6fab73b4c4a6
company-research is a skill published in the GitHub repository stophobia/deerflow2.0-enhanced (754 stars, last pushed 5mo ago), licensed MIT. It adds 113 tokens to every session and 2,116 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…