← 返回 Skills 市场
gptplusplus

Cfoclaw

作者 gptplusplus · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
38
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install cfoclaw
功能描述
CFO财务总监AI技能包——预算执行看板、战略归因、PDCA复盘、预算调拨、报表生成、费用管控。当用户查询执行率、预警、象限分析、调拨、PDCA复盘、报表、费用管控时使用。
使用说明 (SKILL.md)

CFO Claw — 财务总监AI技能包

Use this skill when

  • CFO/财务总监查询预算执行率、预警汇总、闭环率、象限健康度
  • 用户提及"执行率"、"红灯数"、"闭环率"、"一把手视图"
  • 用户询问预算战略归因、象限组合分析、调拨建议
  • 用户提及"战略归因"、"象限"、"资源配置"、"调拨"
  • CFO主持月度/季度经营分析会、PDCA复盘
  • 用户提及"PDCA"、"复盘"、"行动清单"、"改进行动"
  • 用户询问调拨可能性、审批路径、预算调整
  • 用户提及"调拨"、"预算调整"、"跨象限"、"审批"
  • 用户需要生成月度快报、季度汇报、年度复盘
  • 用户提及"生成报表"、"月度快报"、"季度汇报"
  • 用户查询报销状态、管控级别、审批路径、发票查重
  • 用户提及"报销"、"发票查重"、"强管控"、"双线审批"

首次使用

运行以下命令初始化演示数据库：

python3 {baseDir}/query_db.py --skill init-db

技能路由

当用户问题涉及多个子技能时，按以下优先级选择：

  1. 全局概览 → 使用 executive-dashboard
  2. 具体异常下钻 → 对应专项技能
  3. 跨技能综合分析 → 组合使用多个技能

子技能一览

子技能 触发词 核心能力 工作流文档
executive-dashboard "执行率"、"红灯数"、"闭环率" 一把手视图：执行率+灯色+预警+闭环率 {baseDir}/executive-dashboard/WORKFLOW.md
strategic-budget "战略归因"、"象限"、"调拨" 战略预算归因+象限组合分析+调拨建议 {baseDir}/strategic-budget/WORKFLOW.md
pdca-executive-review "PDCA"、"复盘"、"闭环率" PDCA-A/B/C三级复盘，行动清单生成 {baseDir}/pdca-executive-review/WORKFLOW.md
budget-allocation "调拨"、"预算调整"、"审批" 调拨申请/审批/执行，含审批路径判断 {baseDir}/budget-allocation/WORKFLOW.md
report-generation "生成报表"、"月度快报"、"季度汇报" 月度快报/季度汇报/年度复盘/经营分析会材料 {baseDir}/report-generation/WORKFLOW.md
expense-management "报销"、"发票查重"、"核销" 费用报销6步校验+管控路由+双线审批 {baseDir}/expense-management/WORKFLOW.md

数据获取

演示模式（SQLite，默认）

python3 {baseDir}/query_db.py --skill \x3Cskill-name> --period \x3CYYYY-MM>

API模式（连接真实后端）

设置环境变量 FINANCE_API_BASE 后：

python3 {baseDir}/data_adapter.py --skill \x3Cskill-name> --period \x3CYYYY-MM> --mode api

无后端时使用 mock 模式：

python3 {baseDir}/data_adapter.py --skill \x3Cskill-name> --period \x3CYYYY-MM> --mode mock

各技能数据查询命令

技能 命令 返回数据
executive-dashboard python3 {baseDir}/query_db.py --skill executive-dashboard --period 2026-05 budget_overview, budget_by_quadrant, budget_by_l1, alert_dashboard, b2a_summary, execution_trend
strategic-budget python3 {baseDir}/query_db.py --skill strategic-budget --period 2026-05 strategic_summary, transfers
pdca-executive-review python3 {baseDir}/query_db.py --skill pdca-executive-review --period 2026-05 alert_summary, b2a_summary, budget_by_l1, transfers, pdca_cycles, improvement_actions
budget-allocation python3 {baseDir}/query_db.py --skill budget-allocation --period 2026-05 transfers, budget_by_quadrant, budget_items
report-generation python3 {baseDir}/query_db.py --skill report-generation --period 2026-05 budget_overview, budget_by_l1, alert_dashboard, execution_trend
expense-management python3 {baseDir}/query_db.py --skill expense-management expense_reports

核心领域知识

对象本体

详见 {baseDir}/references/ONTOLOGY.md：

  • BudgetItem / BudgetSubjectL1/L2/L3
  • AlertRecord / AlertClosure
  • ExpenseReport / BudgetWriteOff
  • StrategicInitiative / BudgetQuadrant

规则体系

详见 {baseDir}/references/RULES.md：

  • HR-001~HR-015（硬规则，违反即拒绝）
  • SR-001~SR-008（软规则，触发预警但不拒绝）

数据模型

详见 {baseDir}/references/MODELS.md：

  • L1科目体系（9个科目 B1-B9）
  • L2/L3管控级别（强管控/中心弱管控/组合管控/不管控）
  • 战略意图维度（L1/L2 + 产品线 + 区域）
  • 灯色评分规则、闭环率标准、3GAP/3List

专项参考

文档 说明
{baseDir}/references/EXPENSE_CONTROL.md 四级管控模式详解、报销五原则、审批架构
{baseDir}/references/BUDGET_LIFECYCLE.md A/B类预算差异、战略意图维度、象限组合规则
{baseDir}/references/PDCA_ALERT.md PDCA三循环、3GAP/3List、一报一会机制

方法论

文档 说明
{baseDir}/references/methodology/CFO分析问题定义标准.md 战略层/经营层/操作层问题分级框架
{baseDir}/references/methodology/CFO指标定义与数据口径标准.md 执行率/闭环率/灯色评分/3GAP/3List标准定义
{baseDir}/references/methodology/CFO交互标准与沟通范式.md 战略评估/经营监控/复盘诊断场景的回答范式
{baseDir}/references/methodology/CFO报告撰写与呈现标准.md 月度快报/季度汇报结构与亮灯规则
{baseDir}/references/methodology/CFO预警响应标准.md 预警分级/双签闭环/升级规则

输出格式规范

所有子技能输出遵循统一格式：

▌[技能名称]   [期间]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
【核心指标】  指标1[值]  指标2[值]  指标3[值]
【明细/分布】  ...
【操作建议】  1. [建议]  2. [建议]

各技能的具体输出格式见对应的 WORKFLOW.md 和 EXAMPLES.md。

边界情况

  • 数据库未初始化 → 提示运行 python3 {baseDir}/query_db.py --skill init-db
  • 无预警数据 → "本月预警情况正常，无红色/橙色预警"
  • 预算项为空 → "当前无进行中的预算项目"
  • 闭环率 \x3C80% → 操作建议中提醒"建议加强预警响应机制"
  • 执行率 >100% → 标注"超额完成"，触发超支原因说明
  • 无当月数据 → 提示"当前期间无可用数据，是否查看上月？"
安全使用建议
Review before installing, especially in real finance environments. Only connect FINANCE_API_BASE to an approved internal HTTPS service, restrict access to authorized finance/compliance users, treat outputs as advisory, and remove or override the examples that recommend splitting claims or changing categories to reduce approval scrutiny.
能力标签
financial-authoritycan-sign-transactionsrequires-sensitive-credentials
能力评估
⚠ Purpose & Capability
The stated CFO purpose matches dashboards, reporting, budget allocation, and expense control, but the artifacts go beyond analysis into approval, execution, automatic approval/release, and reimbursement decision support for financial controls.
⚠ Instruction Scope
Several workflows are broad keyword-triggered and high-impact. Expense examples suggest claim splitting and weaker-control account substitution, which conflicts with the expense-governance purpose.
ℹ Install Mechanism
Installation requires python3 and optionally FINANCE_API_BASE for a real backend. The API mode is disclosed, but security requirements such as approved endpoints, HTTPS/authentication, and data minimization are not documented.
⚠ Credentials
For a finance skill, querying financial records and optional backend APIs is purpose-aligned, but returning applicant IDs and invoice numbers by default and using a caller-controlled API base without validation is overbroad for many users.
⚠ Persistence & Privilege
The demo database initializer deletes and recreates the local SQLite database without confirmation. Other runtime queries are mostly read-only, but the written workflows describe budget updates and automatic financial state changes without clear guardrails.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install cfoclaw
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /cfoclaw 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of cfoclaw (v1.0.0): - Introduces a comprehensive CFO/财务总监 AI skill package for budget performance dashboards, strategic attribution, PDCA review, budget allocation, report generation, and expense control. - Supports both demo mode (SQLite) and API mode for connecting to real backend financial data. - Includes six modular sub-skills for executive dashboard, strategy analysis, PDCA review, budget allocation, report generation, and expense management. - Provides detailed object ontology, rule system, data models, and CFO methodology references for financial operations. - Standardizes output formats and specifies handling for common and edge-case scenarios.
元数据
Slug cfoclaw
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Cfoclaw 是什么？

CFO财务总监AI技能包——预算执行看板、战略归因、PDCA复盘、预算调拨、报表生成、费用管控。当用户查询执行率、预警、象限分析、调拨、PDCA复盘、报表、费用管控时使用。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 38 次。

如何安装 Cfoclaw？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install cfoclaw」即可一键安装，无需额外配置。

Cfoclaw 是免费的吗？

是的，Cfoclaw 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Cfoclaw 支持哪些平台？

Cfoclaw 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Cfoclaw？

由 gptplusplus（@gptplusplus）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191113 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论