← Back to Skills Marketplace
Insight Brief Generator
by
vx：17605205782
· GitHub ↗
· v1.0.0
· MIT-0
207
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install insight-brief-generator
Description
把报表和图表转成管理层可读的洞察摘要，区分发现、解释和建议动作。；use for insights, analytics, briefing workflows；do not use for 夸大结论, 把相关性当因果.
README (SKILL.md)
洞察简报生成器
你是什么
你是“洞察简报生成器”这个独立 Skill，负责：把报表和图表转成管理层可读的洞察摘要，区分发现、解释和建议动作。
Routing
适合使用的情况
- 把这些图表写成管理层看得懂的摘要
- 区分发现和建议
- 输入通常包含：图表结论、数据摘要、背景问题
- 优先产出：核心发现、数据解释、风险提醒
不适合使用的情况
- 不要夸大结论
- 不要把相关性当因果
- 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：
- 核心发现
- 数据解释
- 可能原因
- 建议动作
- 需补数据
- 风险提醒
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
- 会显式标注推断与事实的边界。
- 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 coherent and offline-first, but consider these practical precautions before running: (1) Review scripts/run.py yourself if you want to confirm there are no unexpected behaviors. (2) When invoking the script, avoid pointing --input at broad system directories (e.g., /, /home, or your entire repo) if those contain secrets; use a narrow path or run with --dry-run first. (3) The script can read and include file contents in outputs—treat outputs as potentially containing sensitive data. (4) The skill does not perform network calls or request credentials, so network exfiltration is not apparent in this bundle. If you need stronger guarantees, run the script in a sandbox or inspect the code locally before use.
Capability Analysis
Type: OpenClaw Skill
Name: insight-brief-generator
Version: 1.0.0
The skill bundle contains significant undocumented capabilities that exceed its stated purpose as an 'Insight Brief Generator.' While the documentation focuses on report summarization, the core logic in `scripts/run.py` includes specialized modes (`pattern_audit`, `directory_audit`, `skill_audit`) and regex patterns designed to scan the local filesystem for sensitive information, such as API keys, tokens, and dangerous shell commands (e.g., `curl|bash`). Although the script attempts to mask discovered secrets and lacks direct exfiltration logic, providing an AI agent with built-in tools to perform broad filesystem discovery and credential hunting is a high-risk behavior that could be easily exploited.
Capability Assessment
Purpose & Capability
Name/description (convert reports/charts into management-ready insights) align with the included files and script behavior. The only declared runtime requirement is python3 and the bundled script/resources/templates drive output generation—no unrelated binaries or cloud credentials are requested.
Instruction Scope
SKILL.md confines behavior to generating structured drafts and suggests using the local script if available. The script supports multiple modes (structured_brief, directory audit, CSV audit, pattern scan, skill audit) and will read files from whichever path you pass as --input. That means if a user invokes it on a large or sensitive directory it will enumerate and read many text files (which is consistent with its audit modes but worth noting). The skill explicitly warns not to fabricate facts and not to perform external system changes.
Install Mechanism
No install spec; instruction-only plus a local Python script. This is low-risk: nothing is downloaded or extracted, and the script uses only the Python standard library per README and SELF_CHECK.
Credentials
The skill requires no environment variables or credentials. The script includes built-in patterns to detect risky content (e.g., secret-like strings) and masks them in output, which is sensible for audit functionality. Users should avoid running it on directories containing secrets unless they intend to scan for them.
Persistence & Privilege
always is false, the skill does not request permanent presence, does not modify other skills, and only writes output when asked (or when --output provided). It does not attempt to change agent/system configuration.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install insight-brief-generator - After installation, invoke the skill by name or use
/insight-brief-generator - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of insight-brief-generator.
- Generates management-level insight briefs from reports and charts, clearly separating findings, explanations, and recommended actions.
- Emphasizes distinction between correlation and causation; avoids exaggerating conclusions.
- Provides structured outputs: core findings, data interpretation, possible causes, recommended actions, data gaps, and risk alerts.
- Includes built-in guidance for missing information, security boundaries, and review workflows.
- Supports both script-driven and direct text generation based on environment capabilities.
Metadata
Frequently Asked Questions
What is Insight Brief Generator?
把报表和图表转成管理层可读的洞察摘要，区分发现、解释和建议动作。；use for insights, analytics, briefing workflows；do not use for 夸大结论, 把相关性当因果. It is an AI Agent Skill for Claude Code / OpenClaw, with 207 downloads so far.
How do I install Insight Brief Generator?
Run "/install insight-brief-generator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Insight Brief Generator free?
Yes, Insight Brief Generator is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Insight Brief Generator support?
Insight Brief Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).
Who created Insight Brief Generator?
It is built and maintained by vx：17605205782 (@52yuanchangxing); the current version is v1.0.0.
More Skills