Token导航 LogoToken导航TokenDH.com
研究检索敏感数据clawhub未标认证来源可访问clear审计通过

openfinanceopenfinance 搜索

Agent Skill

openfinance 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

6,048

周安装

252

GitHub Stars

1

下载量

2,016
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:openfinance(openfinance 搜索)
来源仓库:https://github.com/winxton/openfinance
安装命令:
openclaw skills install openfinance
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install openfinance

简介

通过 openfinance.sh 桥接银行账户与 AI 模型进行金融交互。

  • 支持交易查询、余额同步与支付指令生成。
  • 适用于个人理财助手或自动化财务流程场景。
  • 必须配置银行 API 凭证并启用双重认证。
  • 存在安全风险,仅限可信环境使用。openfinance 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
openfinance
slug
openfinance
version
0.0.3
description
Connect bank accounts to AI models using openfinance.sh
tags
requires
env
description
API key from openfinance.sh (Connect tab)
required
true
description
Custom API base URL (defaults to https://api.openfinance.sh)
required
false

OpenFinance Skill

Query your financial accounts and transactions via the OpenFinance API.

Setup

  1. Go to openfinance.sh and create an account
  2. Link a bank account through the dashboard
  3. Copy your API key from the Connect tab
  4. Set the environment variable:
   export OPENFINANCE_API_KEY="your_api_key_here"

All commands below use these variables:

BASE_URL="${OPENFINANCE_URL:-https://api.openfinance.sh}"
AUTH_HEADER="Authorization: Bearer $OPENFINANCE_API_KEY"

1. Get Accounts

Fetch all connected financial accounts with balances and institution info.

curl -s "$BASE_URL/api/accounts" -H "$AUTH_HEADER" | cat

Response shape per account:

  • id (number) — account ID (use for filtering transactions)
  • name, officialName — account names
  • type (e.g. "depository", "credit"), subtype (e.g. "checking", "credit card")
  • mask — last 4 digits
  • currentBalance, availableBalance, isoCurrencyCode
  • institutionName, institutionUrl
  • status — "active" or "hidden"
  • isSyncing (boolean), syncError (object or null)

2. Get Transactions

Search and filter transactions. Returns newest first by default.

curl -s -G "$BASE_URL/api/transactions" \
  -H "$AUTH_HEADER" \
  --data-urlencode "startDate=YYYY-MM-DD" \
  --data-urlencode "endDate=YYYY-MM-DD" \
  --data-urlencode "search=coffee" \
  --data-urlencode "merchants=Starbucks,Walmart" \
  --data-urlencode "accountId=123" \
  --data-urlencode "limit=100" \
  --data-urlencode "cursor=CURSOR_VALUE" \
  --data-urlencode "pending=false" \
  --data-urlencode "status=active,hidden" \
  --data-urlencode "fields=name,amount,date,merchantName" \
  --data-urlencode 'amountFilters=[{"operator":">","amount":100}]' \
  | cat

All query parameters are optional. Only include the ones you need.

Parameters

ParameterTypeDescription
startDateYYYY-MM-DDStart date filter
endDateYYYY-MM-DDEnd date filter
searchstringSearch by transaction name or merchant
merchantscomma-separatedFilter by exact merchant names
accountIdnumberFilter by account ID
limitnumberMax results (default 100, max 500)
cursorstringCursor for pagination (from previous response)
pendingbooleanFilter pending transactions
statuscomma-separatedFilter by status: active, hidden, deleted
fieldscomma-separatedReturn only these fields per transaction (reduces payload)
amountFiltersJSON arrayFilter by amount, e.g. [{"operator":">","amount":50}]

Transaction fields

id, name, amount, date, authorizedDate, pending, merchantName, isoCurrencyCode, accountId, status, createdAt, updatedAt


3. Query Transactions (SQL)

Run a SQL SELECT against the txns CTE for aggregations, grouping, and analysis. The query runs read-only with a 5-second timeout and 1000-row limit.

curl -s -X POST "$BASE_URL/api/transactions/query" \
  -H "$AUTH_HEADER" \
  -H "Content-Type: application/json" \
  -d '{"sql": "SELECT SUM(amount), COUNT(*) FROM txns WHERE merchant_name ILIKE '\''%starbucks%'\''"}' \
  | cat

txns CTE columns

id, name, amount (numeric), date, authorized_date, merchant_name, pending, iso_currency_code, account_id, status, created_at, updated_at

Note: SQL column names use snake_case (e.g. merchant_name), while the REST API returns camelCase (e.g. merchantName).

Example queries

Monthly spend breakdown:

SELECT TO_CHAR(date, 'YYYY-MM') as month, SUM(amount) as total, COUNT(*) as count
FROM txns GROUP BY 1 ORDER BY 1

Top merchants by total spend:

SELECT COALESCE(merchant_name, name) as merchant, SUM(amount) as total
FROM txns GROUP BY 1 ORDER BY total DESC LIMIT 10

Spending in a date range:

SELECT SUM(amount) as total FROM txns
WHERE date >= '2026-01-01' AND date < '2026-02-01'

Large transactions:

SELECT name, merchant_name, amount, date FROM txns
WHERE amount > 500 ORDER BY amount DESC

Response shape

Success: { "rows": [...], "rowCount": N } Error: { "error": "error message" } — fix the SQL and retry.


Tips

  • Use SQL for aggregations — monthly totals, top merchants, category breakdowns. It's faster and returns less data than fetching all transactions.
  • Use fields parameter on GET /api/transactions to reduce payload size when you only need a few columns.
  • Pagination: if there are more results, the response includes a cursor. Pass it as cursor in the next request.
  • Amount values are positive for debits (money spent) and negative for credits (money received).
  • When constructing SQL, always reference the txns CTE directly — do not define your own CTE or use transaction control statements.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

79.77%
按下载量换算1,608

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills