← Back to Skills Marketplace
Inbox Action Board
by
vx：17605205782
· GitHub ↗
· v1.0.0
· MIT-0
155
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install inbox-action-board
Description
把邮件或消息整理成回复、等待、跟进、归档四类行动视图。；use for inbox, triage, productivity workflows；do not use for 直接发送邮件, 删除原消息.
README (SKILL.md)
收件箱行动看板
你是什么
你是“收件箱行动看板”这个独立 Skill，负责：把邮件或消息整理成回复、等待、跟进、归档四类行动视图。
Routing
适合使用的情况
- 帮我把收件箱整理成行动看板
- 区分回复和等待
- 输入通常包含：邮件摘要、聊天片段、待回复项
- 优先产出：需要回复、等待他人、今天要做什么
不适合使用的情况
- 不要直接发送邮件
- 不要删除原消息
- 如果用户想直接执行外部系统写入、发送、删除、发布、变更配置，先明确边界，再只给审阅版内容或 dry-run 方案。
工作规则
- 先把用户提供的信息重组成任务书，再输出结构化结果。
- 缺信息时，优先显式列出“待确认项”，而不是直接编造。
- 默认先给“可审阅草案”，再给“可执行清单”。
- 遇到高风险、隐私、权限或合规问题，必须加上边界说明。
- 如运行环境允许 shell / exec，可使用：
python3 "{baseDir}/scripts/run.py" --input \x3C输入文件> --output \x3C输出文件>
- 如当前环境不能执行脚本，仍要基于
{baseDir}/resources/template.md与{baseDir}/resources/spec.json的结构直接产出文本。
标准输出结构
请尽量按以下结构组织结果：
- 需要回复
- 等待他人
- 需要跟进
- 可归档
- 高风险遗漏
- 今天要做什么
本地资源
- 规范文件：
{baseDir}/resources/spec.json - 输出模板：
{baseDir}/resources/template.md - 示例输入输出：
{baseDir}/examples/ - 冒烟测试：
{baseDir}/tests/smoke-test.md
安全边界
- 只生成看板和建议。
- 默认只读、可审计、可回滚。
- 不执行高风险命令，不隐藏依赖，不伪造事实或结果。
Usage Guidance
This skill appears to do what it says: generate a local, structured inbox/triage report. Before running it: (1) review scripts/run.py locally to confirm behavior (it's included and readable), (2) run with --dry-run and test on a small, non-sensitive sample, (3) avoid pointing --input at broad system or home directories to prevent accidental inclusion of secrets, (4) inspect any generated report before sharing, and (5) if you need stronger guarantees, run the script in a sandboxed environment or container. If you need the skill to directly act on external systems (send messages, change configs), do not enable those actions — the skill explicitly disallows them by design.
Capability Analysis
Type: OpenClaw Skill
Name: inbox-action-board
Version: 1.0.0
The skill bundle is a productivity tool designed to triage messages and emails into a structured Markdown report. The core logic in `scripts/run.py` is a read-only text processor that summarizes inputs, audits directory structures, and includes a utility to scan for (but not execute) high-risk patterns like hardcoded secrets or dangerous shell commands. The bundle lacks network access, avoids dangerous execution functions (e.g., eval, subprocess), and the `SKILL.md` instructions explicitly define safety boundaries that prohibit the agent from performing destructive actions like deleting messages or sending emails.
Capability Assessment
Purpose & Capability
Name, description, SKILL.md, and resources/spec.json all describe an inbox triage tool; the included Python script implements that structured_brief mode but also contains reusable audit helpers (directory/csv/pattern/skill audits). Those extra utilities are reasonable for local auditing but broaden the script's capabilities beyond only 'inbox items'.
Instruction Scope
SKILL.md instructs the agent to run the bundled script or to produce output from templates. The script reads arbitrary files and directories (many text extensions) when given a path, and will write an output file unless run with --dry-run. This is coherent with an audit/triage tool, but it means running the script against an overly-broad path (e.g., / or a home dir) could expose sensitive local contents in the generated report.
Install Mechanism
No install spec; only dependency is python3 (standard). There are no external downloads or package installs.
Credentials
The skill requests no environment variables or credentials and only needs python3. That is proportionate to its stated functionality.
Persistence & Privilege
always is false and the skill does not request persistent system privileges. The script may write an output file (normal) but does not modify other skills or system configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install inbox-action-board - After installation, invoke the skill by name or use
/inbox-action-board - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of inbox-action-board
- Organizes emails or messages into four actionable categories: reply, waiting, follow-up, archive.
- Offers structured outputs to help with triage and productivity workflows.
- Keeps actions read-only and auditable; does not directly send, delete, or modify original messages.
- Provides clear boundaries and risk notes for sensitive or high-risk information.
- Supports both shell execution and text generation based on templates, depending on runtime environment.
Metadata
Frequently Asked Questions
What is Inbox Action Board?
把邮件或消息整理成回复、等待、跟进、归档四类行动视图。；use for inbox, triage, productivity workflows；do not use for 直接发送邮件, 删除原消息. It is an AI Agent Skill for Claude Code / OpenClaw, with 155 downloads so far.
How do I install Inbox Action Board?
Run "/install inbox-action-board" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Inbox Action Board free?
Yes, Inbox Action Board is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Inbox Action Board support?
Inbox Action Board is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).
Who created Inbox Action Board?
It is built and maintained by vx：17605205782 (@52yuanchangxing); the current version is v1.0.0.
More Skills