← Back to Skills Marketplace
银行流水解析,流水报告生成等
by
ufcfengbin
· GitHub ↗
· v1.0.7
· MIT-0
316
Downloads
1
Stars
0
Active Installs
8
Versions
Install in OpenClaw
/install bankstatement
Description
流水报告生成,基于用户输入的Excel/PDF流水文件路径和问题,自动上传文件并生成分析报告。
README (SKILL.md)
Requirements
ZY_TOKEN
Setup
获取api-key地址 https://mp.weixin.qq.com/s/5AE3mQhsW_g-3R6C26i-9Q
流水报告生成技能
此技能用于生成银行流水分析报告。 仅当用户明确提出要对流水文件进行分析、处理、生成报告时,才应调用此技能。
包含两个步骤:
- 上传文件:将本地流水文件(PDF/Excel)上传到服务器
- 生成报告:使用上传后的文件路径和用户问题生成报告。
1. 上传文件 (Upload File)
- 文件有完整路径,请直接上传。文件名称请优先从workspace中查找,如果workspace中不存在,则提示用户输入完整路径。
- 如果有多个文件,文件地址使用逗号(,)隔开。例如:/xxxx/a.pdf,/xxx/b.pdf
- 调用脚本将本地文件上传至服务器,获取服务器上的文件路径。
使用方法
python3 /models/openclaw/skills/flow/scripts/upload_file.py \x3Ctoken> \x3Clocal_file_path>
参数
\x3Ctoken>: API Token, 从$ZY_TOKEN获取。\x3Clocal_file_path>: 本地流水文件的绝对路径。
输出示例 (JSON)
{
"file_path": "/models/app/dify_api/uploads/20260311/..."
}
2. 生成报告 (Generate Report)
使用第一步返回的文件路径server_file_path和用户问题生成报告。
使用方法
python3 /models/openclaw/skills/flow/scripts/generate_report.py \x3Ctoken> \x3Cserver_file_path> \x3Cquery>
参数
\x3Ctoken>: API Token, 从$ZY_TOKEN获取。\x3Cserver_file_path>: 第一步输出的file_path。\x3Cquery>: 用户的问题(如“生成报告”)。
输出示例
# **流水分析报告**
完整流程
# 1. 上传文件
upload_result=$(python3 /models/openclaw/skills/flow/scripts/upload_file.py token local_file_path )
server_path=$(echo $upload_result | jq -r .file_path)
# 2. 生成报告
python3 /models/openclaw/skills/flow/scripts/generate_report.py token "$server_path" query
错误处理
- 上传文件或生成报告输出内容包含"api_key无效",提示您的api_kay无效请前往小程序生成token,本次流程结束,并退出。
- 返回的code包含500,提示服务器内部错误,请稍后重试,本次流程结束,并退出。
- 其他错误,提示用户联系管理员,本次流程结束,并退出。
注意
- 每个步骤都只调用一次,如果失败,本次流程结束,不要在重复调用。
- 最终输出不需要完整的报告内容,只需要附带完整的报告链接,用户可以通过链接查看报告。
- 链接格式如下:
https://xxxx.dfwytech.com/files/tools/2d22f7e3-2e26-4f6c-8976-bd04f7424965.pdf?timestamp=1773645717&nonce=996e9064791853205cef1d30c2837633&sign=X4TNDsvRM62c4JPYQqFL3PmDg-3TOS1NXJwbPd4iKdI=
- 链接以及链接中的参数timestamp、nonce、sign请根据实际情况替换。
Usage Guidance
This skill appears coherent (it uploads files to a remote API and generates a report using ZY_TOKEN). The primary risk is privacy: bank statements are highly sensitive and will be transmitted to https://ziya.dfwytech.com. Before installing/use, do the following: 1) Confirm you trust the service operator and understand their privacy/storage/retention policy (no homepage or publisher info is provided). 2) Verify the token's scope and rotate it if possible; do not reuse a high-privilege credential. 3) Test with non-sensitive sample files first. 4) Run the skill in an isolated environment or sandbox and monitor outbound network requests to ensure endpoints match expectations. 5) Fix the script path references in SKILL.md if needed so the agent runs the correct files. If you cannot verify the service operator or privacy practices, treat this as high-risk for real bank data and avoid uploading sensitive documents.
Capability Analysis
Type: OpenClaw Skill
Name: bankstatement
Version: 1.0.7
The 'bankstatement' skill is designed to analyze financial documents by uploading them to a remote service (ziya.dfwytech.com) and retrieving a report. The implementation consists of two Python scripts, 'upload_file.py' and 'generate_report.py', which use the 'requests' library to interact with the backend API using a required 'ZY_TOKEN'. The instructions in 'SKILL.md' clearly define the workflow and restrict execution to explicit user requests. No evidence of malicious intent, such as unauthorized data exfiltration, obfuscation, or persistence, was found.
Capability Assessment
Purpose & Capability
The name/description (bank statement upload and report generation) matches the included scripts and SKILL.md. The scripts post files and report requests to ziya.dfwytech.com and use a Bearer token (ZY_TOKEN) as expected for an API-backed service.
Instruction Scope
SKILL.md confines activity to: locate a local file, call upload_file.py to upload it, then call generate_report.py. This is within the stated purpose. Minor inconsistency: SKILL.md references script paths under /models/openclaw/skills/flow/scripts/... while the packaged files live in scripts/ — this may require adjusting paths at runtime. The instructions explicitly upload user files to an external server (necessary for the feature) — this is expected but is a privacy consideration rather than incoherence.
Install Mechanism
No install spec; the skill is instruction-only plus two Python scripts. No network downloads or archive extraction occur at install time. Execution requires a Python runtime and network access, which is proportional to the task.
Credentials
Only the primary credential ZY_TOKEN is used and is required for API Authorization. The scripts accept the token as an argument or via ZY_TOKEN environment variable — consistent and proportionate to the described API usage.
Persistence & Privilege
The skill is not marked always:true and does not request system-wide or other-skills configuration changes. It runs on demand and does not request elevated persistence privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install bankstatement - After installation, invoke the skill by name or use
/bankstatement - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.7
- No code or documentation changes detected in this version.
- Functionality, requirements, setup, and instructions remain the same as the previous release.
v1.0.6
- No changes detected in this version; SKILL.md and all files remain unchanged.
- Functionality and usage for bank statement analysis are consistent with the previous release.
v1.0.5
- Updated API key retrieval link in the setup instructions.
- Added support for uploading multiple files at once by separating file paths with commas.
v1.0.4
- No changes detected in this version.
- The skill remains functionally identical to the previous release.
v1.0.3
bankstatement 1.0.3
- 增加了 `Requirements` 和 `Setup` 部分,明确所需环境变量和API key获取方式。
- 优化错误处理:新增通用错误提示,失败时不再重复调用流程。
- 明确流程规范:每个步骤仅允许调用一次,失败即流程终止。
- 文档结构调整,部分内容表述更简洁清晰。
v1.0.2
- Removed the README.md file.
- Updated usage notes to specify that only a report link (not the full report content) should be returned, and provided required link format details.
- Clarified that users can view the report via the generated link with specific URL parameters.
- No changes to code or API; only documentation changes.
v1.0.1
- Skill renamed from "flow" to "bankstatement"
- No changes to code, only documentation updated to reflect the new name
- All instructions, usage steps, and API information remain unchanged
v1.0.0
- Major change: Transitioned the skill from a general NLP workflow orchestrator to a focused bank statement report generator.
- Removed legacy orchestration and NLP components.
- Added two new scripts: file upload and report generation.
- Updated documentation to describe the new usage and shell interface.
- Provided detailed instructions and sample flows for generating reports from user-supplied PDF/Excel files.
Metadata
Frequently Asked Questions
What is 银行流水解析,流水报告生成等?
流水报告生成,基于用户输入的Excel/PDF流水文件路径和问题,自动上传文件并生成分析报告。 It is an AI Agent Skill for Claude Code / OpenClaw, with 316 downloads so far.
How do I install 银行流水解析,流水报告生成等?
Run "/install bankstatement" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 银行流水解析,流水报告生成等 free?
Yes, 银行流水解析,流水报告生成等 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 银行流水解析,流水报告生成等 support?
银行流水解析,流水报告生成等 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 银行流水解析,流水报告生成等?
It is built and maintained by ufcfengbin (@ufcfengbin); the current version is v1.0.7.
More Skills