Agent skill

Luopan Company Research

by zhangxiaoqiang1991 in zhangxiaoqiang1991/luopan

罗盘的公司研究子模式。研究具体上市或非上市公司的财务增长、商业模式、 竞争生态位、治理与组织信号,并分别生成投资初筛和求职初筛。

MITAuto-check passedSales & Support

Install Luopan Company Research

skills CLI
$ npx skills add zhangxiaoqiang1991/luopan --skill luopan-company-research -a claude-code

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

GitHub CLI
$ gh skill install zhangxiaoqiang1991/luopan luopan-company-research --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/zhangxiaoqiang1991/luopan.git skills-src && mkdir -p .claude/skills && cp -r skills-src/modes/company .claude/skills/luopan-company-research && 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
luopan-company-research
GitHub stars
389
Token cost
~998 tokens
SKILL.md length
171 words
Files
25 (incl. scripts, references)
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

罗盘的公司研究子模式。研究具体上市或非上市公司的财务增长、商业模式、 竞争生态位、治理与组织信号,并分别生成投资初筛和求职初筛。

  • Works in 7 steps: 识别公司和研究模式 → 选择数据路线 → 建立共享事实底座 → …
  • Tasks that involve Sales call preparation
  • SKILL.md covers 目标, 交互原则, 工作流 and 报告最小结构, plus 3 more sections
  • Runs Python scripts from its folder

What it does

Luopan Company Research is an agent skill from zhangxiaoqiang1991/luopan. 罗盘的公司研究子模式。研究具体上市或非上市公司的财务增长、商业模式、 竞争生态位、治理与组织信号,并分别生成投资初筛和求职初筛。 由罗盘根 SKILL.md 在用户询问某公司怎么赚钱、发展怎样、值不值得投资、 值不值得投递或加入时路由到此。

Its SKILL.md is about 1000 tokens, which your agent loads only when the skill is triggered. The skill folder holds 28 other files, including scripts and reference files (for example `agents/openai.yaml`, `examples/example_report.json` and `references/audience-routing.md`).

It sits in Sales & Support, covering Sales call preparation. The repository describes itself as: 行业研究 + 公司研究路由器:看清行业的钱与权力,判断公司是否值得投资或加入. The licence is MIT.

When your agent uses it

  • Tasks that involve Sales call preparation

Example prompts

  • “/luopan-company-research”

Requirements

  • Python 3

Workflow steps

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

  1. 识别公司和研究模式
  2. 选择数据路线
  3. 建立共享事实底座
  4. 运行判断引擎
  5. 对抗验证
  6. 生成统一报告
  7. 生成选择题卡片

What it can do on your machine

Read from SKILL.md and the folder at commit 499eb43. 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

    Ships 2 files in scripts/ (Python, from the files we listed), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • xiaohongshu.com
    • x.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

Luopan Company Research loads about 998 tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 36 tokens; SKILL.md has 171 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~998
With references · SKILL.md plus every file in references/, read only if the agent opens them
~13k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from zhangxiaoqiang1991/luopan at commit 499eb43, republished under its MIT licence (© zhangxiaoqiang1991). 171 words, ~998 tokens.

Download SKILL.mdSave it as .claude/skills/luopan-company-research/SKILL.md (or your agent's skills folder). This skill also uses 24 other files; get the full folder from GitHub.
name
luopan-company-research
description
罗盘的公司研究子模式。研究具体上市或非上市公司的财务增长、商业模式、 竞争生态位、治理与组织信号,并分别生成投资初筛和求职初筛。 由罗盘根 SKILL.md 在用户询问某公司怎么赚钱、发展怎样、值不值得投资、 值不值得投递或加入时路由到此。

公司研究

目标

不输出公司百科,而是用可追溯事实回答两个相互独立的问题:

  • 在当前价格和风险下,该公司是否值得继续作为投资对象研究;
  • 对求职者而言,该公司是否值得继续投递,或某个具体业务/岗位/Offer 是否值得加入。

共享事实底座,但禁止将投资与求职合成一个总分。

交互原则

  1. 用户只提供公司名且没有用途线索时,只追问一道三选一:投资为主、求职为主、投资与求职并重;不要求其复述商业模式或填写问卷。
  2. 用户选择后直接研究。用途不明时不得自动猜测、不得默认双主线,也不得先做完再让用户纠正。投资与求职并重只在用户明确选择时使用。
  3. 求职信息不足时先给公司级或业务级结果,再邀请用户补充岗位和 Offer;不将补充信息设为首次使用门槛。
  4. 报告结尾给出 3–5 个基于当前结论的可继续追问方向。

工作流

1. 识别公司和研究模式

确认公司全称、品牌/法人/母子公司关系、上市状态、上市地、证券代码和研究基准日。法律注册地与实际经营总部不同时必须并列说明,例如“港交所上市主体,注册地为开曼群岛,实际经营总部位于深圳”;不得用注册地暗示主要经营地。只有同名实体会导致显著不同结果且无法自行确认时,才询问一个简短消歧问题。

将任务标记为:一般公司了解、投资、求职或双模式。读取并严格执行 references/audience-routing.md:已有明确意图时直接开始;用途不明时必须先让用户在投资为主、求职为主、投资与求职并重中选择。不得用公司属性、品牌印象、搜索热度或 Agent 评分代替用户选择。

2. 选择数据路线

读取 references/data-routing.md,按美股 SEC 申报主体、A 股、港股、其他上市市场或非上市公司路由。多地上市时明确本次证券标的和估值币种。

3. 建立共享事实底座

读取 references/evidence-standard.md 和 references/language-and-sources.md。搜集公司身份与披露质量、财务与资本配置、商业模式与单位经济、行业生态位与竞争优势、管理层与治理、组织/业务/岗位信号。默认输出中文:有同等权威的官方中文材料时优先中文;只有外文一手材料时中文转述并保留原始链接和原文标题,不为中文化牺牲证据等级。

对每条核心数据保留时间、币种、单位、口径、证据链接、页码/章节和是否为计算值。非上市公司无可验证披露时,禁止补全精确营收、利润和增速。

4. 运行判断引擎

投资结论必须将公司质量与当前交易条件分开。求职结论必须标明它是公司级初筛、业务级判断还是 Offer 级判断。

5. 对抗验证

以最强反方视角检查:

  • 是否把管理层叙事当成事实;
  • 是否把相关当成因果;
  • 是否混用财年、币种、会计口径或母子公司;
  • 是否用单一毛利率、增速、估值或人员信号推出强结论;
  • 是否存在能推翻当前判断的反证;
  • 投资与求职结论是否被不当互相替代。

修正报告后再输出,不在最终报告中假装没有矛盾或信息局限。

6. 生成统一报告

读取 references/report-design.md,先写 30 秒决策卡、关键争议与折叠底稿。再读取 references/report-model.md,建立包含 facts、data_health、sections、sources 和 quiz_cards 的结构化 JSON 真源,并由同一份对象生成:

  • HTML:主阅读与交互体验;
  • Markdown:本地存档、搜索与二次编辑;
  • JSON:事实、判断、来源和卡片的内部真源。

验证 JSON 后,调用 scripts/render_report.py 同时生成 HTML 与 Markdown。禁止分别即兴撰写两份报告;数字、结论、来源、测试答案与研究日期必须一致。JSON 必须保留逐条事实与证据血缘,不得退化为只有章节文字的容器。

在 JSON 中按用户选择设置 presentation.primary_audience 为 investment、career 或 balanced。投资为主时不默认生成求职章节;求职为主时不展开估值底稿;只有用户选择双主线时两者都进入主阅读路径。presentation.reason 记录用户选择,不得伪装成自动判断。

7. 生成选择题卡片

读取 references/quiz-cards.md。卡片必须是单选或多选题,包含正确答案、选项解析、证据引用和可复制追问;不生成填空或简答题。测试位于报告末尾,不阻塞用户获取报告。

报告最小结构

  1. 研究对象、基准日和信息质量;
  2. 一页结论:一句话理解公司、三个核心判断、最大机会、最大风险;
  3. 商业模式、财务与增长、生态位与护城河、管理层与治理;
  4. 投资判断(适用时);
  5. 求职判断与面试核实清单(求职主视角或用户明确要求时完整展开;投资主视角时折叠为公司级入口);
  6. 反证、信息局限、可能推翻结论的条件;
  7. 理解测试选择题;
  8. 来源与方法;
  9. 可继续追问方向。

质量门禁

输出前确认:

  • 同名公司、品牌、母子公司与上市标的没有混淆。
  • 法律注册地与实际经营总部已分开标注,没有让用户误解公司在哪里经营。
  • 核心数字有期间、币种、口径和原始链接。
  • 外文一手资料已准确中文转述;英文来源同时显示中文译名与原文标题,且没有用中文二手资料替代更强的一手证据。
  • 事实、计算、推断和建议已分开。
  • 非上市公司没有被补全未披露的精确财务数据。
  • 投资判断包含价格基准日,或明确降级为公司质量判断。
  • 价格门已给出三情景内在价值、目标回报率、所需安全边际和买入上限;未完成时标记 INSUFFICIENT。
  • 没有岗位与个人信息时,没有输出 Offer 级最终建议。
  • 求职主视角或用户明确要求求职判断时,完整输出面试反问 10 问;投资主视角的默认报告只保留折叠的求职入口,用户展开求职研究后再生成10问。
  • 首屏已标明主视角,次视角没有抢占主要阅读路径,也没有被彻底删除。
  • 每个核心结论有支持证据、反证、置信度和推翻条件。
  • HTML 与 Markdown 来自同一份结构化真源。
  • 理解卡片全部为单选/多选,且正确答案可追溯到报告证据。

反馈 & 帮助迭代

欢迎在 Issues 页面提交反馈,或直接联系作者。

关于我

大厂转型人强哥(全网同名)

河北邯郸人,曾武汉求学,现居北京。曾就职腾讯、字节跳动。目前负责 AI + 内容增长、产品运营。关注以下三方面的机会,欢迎交流 / 围观朋友圈:

  • AI 内容运营:从战略、策略到执行的内容增长
  • AI 培训 / 布道:帮团队真正用好 AI,不只是上个课
  • AI 内部提效:搭建工具流,把 AI 落地到业务流程里

联系方式与链接:

© zhangxiaoqiang1991, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 24 other files (scripts, references) in modes/company of zhangxiaoqiang1991/luopan.

  • SKILL.md
  • agents/openai.yaml
  • examples/example_report.json
  • references/audience-routing.md
  • references/automation-roadmap.md
  • references/career-framework.md
  • references/data-routing.md
  • references/evidence-standard.md
  • references/interview-questions.md
  • references/investment-framework.md
  • references/language-and-sources.md
  • references/price-safety-margin.md
  • references/quiz-cards.md
  • references/report-design.md
  • references/report-model.md
  • scripts/render_report.py
  • scripts/sec_fetch.py
  • … and 8 more

Open the folder on GitHubat commit 499eb43

Compare with similar skills

Luopan Company Research 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.

Luopan Company Research compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Luopan Company Research this skillzhangxiaoqiang1991/luopan389—~998Automated safety check: PassMIT
Company Researchstophobia/deerflow2.0-enhanced822—~845Automated safety check: PassMIT
Meeting Prep BriefBrianRWagner/ai-marketing-claude-code-skills441—~922Automated safety check: PassNone
SdtStopDisTrain/sdt-skills309—~535Automated safety check: PassMIT
Account Researchextruct-ai/gtm-skills109—~1.6kAutomated safety check: PassNone
Call Prepbreakstageaxe61/genspark-claw169—~986Automated safety check: PassMIT

Similar skills

  • Company Research

    stophobia/deerflow2.0-enhanced

    综合企业背景调研技能,用于尽职调查、合作伙伴评估、投资分析、市场研究等场景。支持公司工商信息、财务数据、法律风险、舆情分析、竞品对比等多维度调研,自动生成Markdown和HTML格式的专业调研报告。触发条件:用户提及"企业调研"、"公司背景"、"尽职调查"、"合作伙伴评估"、"投资分析"、"市场研究"等关键词。

    822 GitHub stars~845 tokensUpdated 6 mo ago
    Sales & SupportAuto-check passed
  • Meeting Prep Brief

    BrianRWagner/ai-marketing-claude-code-skills

    Builds a pre-meeting brief from your Obsidian vault: participant research, past notes, open commitments, a prioritized agenda and sharp questions.

    441 GitHub stars~922 tokensUpdated 6 mo ago
    Sales & SupportAuto-check passed
  • Sdt

    StopDisTrain/sdt-skills

    SDT 内容生产工具箱的总入口:根据当前任务选择最合适的 sdt- 模块,既能完成标题、开头等单一步骤,也能组织从账号研究到发布的完整流程。用户不知道该用哪个 SDT Skill,或希望一站式完成内容生产时使用。

    309 GitHub stars~535 tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed
  • Account Research

    extruct-ai/gtm-skills

    Deep-research a single target account into a decision-ready dossier: the entity tree, the buying units and decision-makers, live signals (open/closed roles, leadership moves, news, tech stack), and…

    109 GitHub stars~1.6k tokensUpdated 12 days ago
    Sales & SupportAuto-check passed
  • Call Prep

    breakstageaxe61/genspark-claw

    Prepare an AI phone call end-to-end — research the callee, set a concrete objective and fallback, draft a natural call script with branching, and produce a post-call summary template.

    169 GitHub stars~986 tokensUpdated 15 days ago
    Sales & SupportAuto-check passed
  • Company Research

    thesun4sky/jobstack

    기업 분석 스킬. An agent skill from thesun4sky/jobstack.

    156 GitHub stars~2.9k tokensUpdated 1 mo ago
    Sales & SupportAuto-check: notes

More from zhangxiaoqiang1991/luopan

  • Luopan Industry

    zhangxiaoqiang1991/luopan

    罗盘行业研究模式。用于研究行业结构、产业链、市场规模、竞争格局、商业模式、行业趋势、风险,以及行业是否值得进入. An agent skill from zhangxiaoqiang1991/luopan.

    389 GitHub stars~905 tokensUpdated 2 mo ago
    Auto-check passed
  • Luopan

    zhangxiaoqiang1991/luopan

    商业研究路由器:根据研究对象进入行业研究或公司研究. An agent skill from zhangxiaoqiang1991/luopan.

    389 GitHub stars~604 tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Luopan Company Research

What does Luopan Company Research do?

罗盘的公司研究子模式。研究具体上市或非上市公司的财务增长、商业模式、 竞争生态位、治理与组织信号,并分别生成投资初筛和求职初筛。. Luopan Company Research is an agent skill from zhangxiaoqiang1991/luopan.

When should I use Luopan Company Research?

Luopan Company Research fits situations like: tasks that involve Sales call preparation.

How do I install Luopan Company Research in Claude Code?

Run `npx skills add zhangxiaoqiang1991/luopan --skill luopan-company-research -a claude-code`. Or copy the skill folder (modes/company in zhangxiaoqiang1991/luopan) into .claude/skills/luopan-company-research in your project. Claude Code loads it when a task matches its description.

How do I install Luopan Company Research in Codex?

Run `npx skills add zhangxiaoqiang1991/luopan --skill luopan-company-research -a codex`. Or copy the skill folder (modes/company in zhangxiaoqiang1991/luopan) into .agents/skills/luopan-company-research in your project. Codex loads it when a task matches its description.

Can I use Luopan Company Research 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 zhangxiaoqiang1991/luopan --skill luopan-company-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/luopan-company-research, .gemini/skills/luopan-company-research, .github/skills/luopan-company-research and .opencode/skills/luopan-company-research in your project.

What does Luopan Company Research need to run?

Going by SKILL.md and its folder, Luopan Company Research needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Luopan Company Research access the network?

SKILL.md names 2 domains. As links in the text: xiaohongshu.com and x.com. This is read from the text; nothing was executed.

Is Luopan Company Research 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Luopan Company Research use?

Luopan Company Research is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Luopan Company Research use?

About 998 tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 12k tokens, read only when the agent opens those files.

What are the alternatives to Luopan Company Research?

Skills that share tags, products or a category with Luopan Company Research: Company Research (stophobia/deerflow2.0-enhanced, 822 stars), Meeting Prep Brief (BrianRWagner/ai-marketing-claude-code-skills, 441 stars), Sdt (StopDisTrain/sdt-skills, 309 stars) and Account Research (extruct-ai/gtm-skills, 109 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Luopan Company Research?

zhangxiaoqiang1991 (a GitHub user) maintains it in zhangxiaoqiang1991/luopan, which has 389 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on July 18, 2026.

Source: zhangxiaoqiang1991/luopan on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.