← 返回 Skills 市场
Self-Improving Finance
作者
José I. O.
· GitHub ↗
· v1.1.0
· MIT-0
106
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install self-improving-finance
功能描述
Captures reconciliation errors, forecast variances, control weaknesses, regulatory gaps, valuation errors, and cash flow anomalies to enable continuous finan...
安全使用建议
This skill appears internally consistent: it only injects local reminders, creates/initializes .learnings/ log files, and scans tool output for finance keywords. Before installing: (1) prefer project-level hook activation (not global) so reminders run only for finance projects, (2) review the referenced GitHub repo code if you plan to git-clone it, (3) be cautious enabling the PostToolUse/error-detector hook because it reads CLAUDE_TOOL_OUTPUT (which can include sensitive financial text) — the skill asks you to anonymize before logging but the detector will see raw output, (4) inspect and set script file permissions (chmod +x) only when you trust the environment, and (5) confirm you are comfortable with the skill writing files under your workspace (./skills/ or ~/.openclaw/workspace/.learnings). If any of these are unacceptable, skip enabling the hooks or use the activator-only setup described in SKILL.md.
功能分析
Type: OpenClaw Skill
Name: self-improving-finance
Version: 1.1.0
The 'self-improving-finance' skill bundle is a framework designed to help AI agents track and improve finance-related operations by logging reconciliation errors, control weaknesses, and forecast variances. It includes utility scripts (activator.sh, error-detector.sh, extract-skill.sh) for context injection and skill scaffolding, all of which contain appropriate input validation and lack malicious behavior. The documentation (SKILL.md) and hooks (handler.js) explicitly instruct the agent to anonymize all financial data and avoid logging sensitive information like account numbers or PII, aligning with the stated purpose of operational improvement.
能力标签
能力评估
Purpose & Capability
Name/description claim to capture finance learnings and promote recurring patterns; the repository contains only local logging helpers, hook handlers that inject reminders, and helper scripts to scaffold anonymized learning/skill files. There are no unrelated cloud credentials, network uploads, or unrelated binaries required.
Instruction Scope
Runtime instructions and hooks focus on creating/using a .learnings/ folder, emitting short reminder text, and scanning tool output for finance-related keywords. The error detector reads the CLAUDE_TOOL_OUTPUT environment variable (used to detect finance-related tool output) and the scripts create files under local workspace paths. This is in-scope for the stated purpose, but note: CLAUDE_TOOL_OUTPUT (tool output) may contain sensitive financial text; the skill emphasizes anonymization but will read that data when PostToolUse hooks are enabled.
Install Mechanism
No automated install spec is provided (instruction-only install recommended via ClawdHub or a git clone). The manual install suggestion references a GitHub repo (personal account). There are no downloads from untrusted URLs or archive extraction steps. Before cloning, you may want to inspect the repo upstream (if you trust it) — installing hooks into your OpenClaw workspace will cause the included handler scripts to run as hooks.
Credentials
The skill declares no required environment variables or credentials, and it doesn't attempt to access secret tokens. However, the error-detector script reads CLAUDE_TOOL_OUTPUT (an environment variable provided by host tooling) which is not listed in requires.env — this is expected in the hook context but worth noting because that variable can contain sensitive financial content. No credentials, API keys, or unrelated env vars are requested.
Persistence & Privilege
The skill is not always-enabled; hooks are opt-in and recommended to be enabled by the user. Hook handlers add virtual bootstrap files and the shell scripts create files under the local workspace; they do not attempt to modify other skills or system-wide config. Scripts run with the agent's permissions (documented), so enable them only where you trust the agent runtime.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install self-improving-finance - 安装完成后，直接呼叫该 Skill 的名称或使用
/self-improving-finance触发 - 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
v1.1.0
No user-facing changes in this release.
- Version bump to 1.1.0 with no modifications to skill files or documentation.
- All workflows, usage instructions, and setup procedures remain unchanged.
v1.0.0
Initial release of self-improving-finance skill:
- Captures and logs reconciliation errors, forecast variances, control weaknesses, regulatory gaps, valuation errors, and cash flow anomalies for finance process improvement.
- Provides detailed initialization steps to set up secure, anonymized learning and issues log files in a `.learnings/` directory.
- Quick reference guide for when and where to log different types of finance issues and learnings.
- Supports OpenClaw integration, including file structure, hooks for reminders, and promotion of important findings to checklists and procedures.
- Offers generic setup instructions for other agent platforms (e.g., Copilot) to ensure portability.
- Strong emphasis on sensitive data handling and compliance with regulatory frameworks.
元数据
常见问题
Self-Improving Finance 是什么？
Captures reconciliation errors, forecast variances, control weaknesses, regulatory gaps, valuation errors, and cash flow anomalies to enable continuous finan... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 106 次。
如何安装 Self-Improving Finance？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install self-improving-finance」即可一键安装，无需额外配置。
Self-Improving Finance 是免费的吗？
是的，Self-Improving Finance 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Self-Improving Finance 支持哪些平台？
Self-Improving Finance 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 Self-Improving Finance？
由 José I. O.（@jose-compu）开发并维护，当前版本 v1.1.0。
推荐 Skills