← Back to Skills Marketplace
153
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install caibaojiedu
Description
精准解读真实财报数据，分析重资产周期拐点，排查财务造假，提供严谨投资决断建议。
README (SKILL.md)
角色定位\r
你是“Antigravity”量化系统的首席财报参谋长。你在重工业城市历练多年，深谙实体经济运转规律。你的交易纪律是：无逻辑不进攻，底盘不净绝对不买，死守止损，严控底线。\r \r
核心纪律（物理锁死）\r
你的桌子上有不同中枢（Worker 01-04）提交的底层物理战报。\r
- 绝对服从： 你必须、且只能基于 Python 底层引擎抽取的真实数据和触发的警报进行解读，绝不允许擅自捏造财务数据或发散外部教科书理论！\r
- 拒绝废话： 不要复述干巴巴的数字，要把数据翻译成“工厂里的机床、仓库里的存货、银行里的真金白银”。\r \r
汇报阵型（标准作业流程）\r
当总指挥让你分析一只股票时，你必须按以下逻辑依次汇报：\r \r
- 【进攻雷达解读】（基于 1号/2号/3号 战报）： 指出该公司的产能扩张是否到了拐点？固定资产占比是否符合重资产周期反转逻辑？业务有没有爆发的势头？\r
- 【终极排雷解剖】（基于 4号 战报）：\r 极其冷酷地宣判它是否触发了财务造假熔断。针对触发的反向逻辑，用老辣的口吻还原它在物理世界里可能在捣什么鬼（如：假发货、真掏空、骗贷款）。\r
- 【参谋长最终决断】：\r 进攻逻辑是否能覆盖防守风险？给总指挥一句痛快话：是加入核心股票池，还是直接拉黑？
Usage Guidance
This skill is instruction-only and does not itself install software or ask for credentials, so it appears coherent with its purpose. Before installing, confirm: (1) how the agent will supply the required 'Worker 01-04' reports (files, API, or prior tool outputs), because the SKILL.md assumes those data are available; (2) who controls those reports and whether they contain sensitive information you don't want the agent to see; and (3) whether you trust the skill owner (note the _meta.json ownerId differs from the registry ownerId). Also remember: even a coherent skill can give incorrect investment advice — treat outputs as informational and verify with your own data and controls. If you want to limit risk, run it with autonomous invocation disabled or in a sandbox where it cannot access network or private files until you confirm data sources.
Capability Analysis
Type: OpenClaw Skill
Name: caibaojiedu
Version: 1.0.2
The skill bundle consists of metadata and instructions (SKILL.md) for an AI agent to act as a financial analyst within the 'Antigravity' quantitative system. The instructions define a specific persona and workflow for interpreting financial reports and detecting fraud based on data from internal workers. There are no indicators of malicious intent, data exfiltration, or unauthorized execution.
Capability Assessment
Purpose & Capability
The name/description claim a financial-report analysis tool; the SKILL.md contains instructions for that role and does not request unrelated binaries, secrets, or installs. Note: the skill insists on using Python-extracted data but provides no code or explicit data-source wiring — this is plausible for an instruction-only skill that expects the agent environment to supply those reports.
Instruction Scope
Instructions are narrowly scoped to analyze 'Worker 01-04' reports and produce specific outputs (radar, fraud check, final verdict). They do not instruct reading arbitrary system files, network exfiltration, or accessing unrelated env vars. However, the SKILL.md is vague about how Worker reports are provided to the agent (file paths, API, stdin, or prior tool output), which leaves implementation ambiguity that should be clarified before use.
Install Mechanism
No install spec, no code files to write, and no downloadable artifacts — lowest-risk installation surface for the platform.
Credentials
The skill declares no required environment variables, credentials, or config paths. The instructions reference 'Python 底层引擎' conceptually but do not request access tokens or unrelated secrets.
Persistence & Privilege
always is false and the skill is user-invocable with normal autonomous invocation allowed. That is typical; the skill does not request persistent system-wide privileges or attempt to modify other skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install caibaojiedu - After installation, invoke the skill by name or use
/caibaojiedu - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Removed 9 files, including key script modules and metadata.
- Core functionality and internal worker scripts (such as stock analysis and data layers) have been deleted.
- No changes made to role description or workflow logic documentation (SKILL.md remains unchanged).
- This update significantly reduces the skill's technical implementation files.
v1.0.1
Initial public version with base documentation.
- Added SKILL.md describing skill positioning, discipline, and standard reporting procedures.
- Added _meta.json file for metadata configuration.
v1.0.0
- Initial release of the "cai" skill (version 1.0.0).
- Defines the user as the chief financial analysis officer for the "Antigravity" quant system, emphasizing real-industry experience and strict trading discipline.
- Requires strict adherence to real data from four central workers, prohibiting fabricated data or generic textbook theory.
- Introduces a standard reporting workflow: offensive signal analysis, financial fraud detection, and a clear final decision for stock pool inclusion or exclusion.
- All outputs must translate financial signals into tangible physical world terms, avoiding generic financial jargon.
Metadata
Frequently Asked Questions
What is caibao?
精准解读真实财报数据，分析重资产周期拐点，排查财务造假，提供严谨投资决断建议。 It is an AI Agent Skill for Claude Code / OpenClaw, with 153 downloads so far.
How do I install caibao?
Run "/install caibaojiedu" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is caibao free?
Yes, caibao is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does caibao support?
caibao is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created caibao?
It is built and maintained by houyucheg (@houyucheg); the current version is v1.0.2.
More Skills