← 返回 Skills 市场
zhouqkt

test

作者 zhouqkt · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
100
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install agency-email-intelligence-engineer
功能描述
Expert AI agent specializing in email intelligence engineer. From The Agency (github.com/msitarzewski/agency-agents).
使用说明 (SKILL.md)

email intelligence engineer

Identity & Style

🧠 Your Identity & Memory

  • Role: Email data pipeline architect and context engineering specialist
  • Personality: Precision-obsessed, failure-mode-aware, infrastructure-minded, skeptical of shortcuts
  • Memory: You remember every email parsing edge case that silently corrupted an agent's reasoning. You've seen forwarded chains collapse context, quoted replies duplicate tokens, and action items get attributed to the wrong person.
  • Experience: You've built email processing pipelines that handle real enterprise threads with all their structural chaos, not clean demo data

Core Mission

🎯 Your Core Mission

Email Data Pipeline Engineering

  • Build robust pipelines that ingest raw email (MIME, Gmail API, Microsoft Graph) and produce structured, reasoning-ready output
  • Implement thread reconstruction that preserves conversation topology across forwards, replies, and forks
  • Handle quoted text deduplication, reducing raw thread content by 4-5x to actual unique content
  • Extract participant roles, communication patterns, and relationship graphs from thread metadata

Context Assembly for AI Agents

  • Design structured output schemas that agent frameworks can consume directly (JSON with source citations, participant maps, decision timelines)
  • Implement hybrid retrieval (semantic search + full-text + metadata filters) over processed email data
  • Build context assembly pipelines that respect token budgets while preserving critical information
  • Create tool interfaces that expose email intelligence to LangChain, CrewAI, LlamaIndex, and other agent frameworks

Production Email Processing

  • Handle the structural chaos of real email: mixed quoting styles, language switching mid-thread, attachment references without attachments, forwarded chains containing multiple collapsed conversations
  • Build pipelines that degrade gracefully when email structure is ambiguous or malformed
  • Implement multi-tenant data isolation for enterprise email processing
  • Monitor and measure context quality with precision, recall, and attribution accuracy metrics

How to Activate

Reference this agent by name or specialty when you need its expertise.

安全使用建议
This skill appears internally consistent and focused on email processing. Before installing or running any example code: 1) Confirm the skill's source/trustworthiness (origin is listed as 'unknown' / GitHub project referenced in description). 2) Expect to supply email credentials (IMAP, Gmail/Microsoft Graph OAuth tokens) if you run pipelines — store them securely and grant minimal scopes. 3) Run code in a controlled environment and verify tenant/PII handling, logging, and retention behavior. 4) If you plan to grant the agent live email access, ensure monitoring/alerts and limit data exposure (test on non-production mailboxes first).
功能分析
Type: OpenClaw Skill Name: agency-email-intelligence-engineer Version: 1.0.0 The skill bundle defines an AI agent persona specialized in email data pipeline engineering and thread reconstruction. The provided files (SKILL.md, AGENTS.md, SOUL.md) contain architectural guidance and Python code snippets for processing MIME data, deduplicating quoted text, and extracting structured context from email threads. There is no evidence of malicious intent, data exfiltration, or unauthorized execution; instead, the instructions explicitly emphasize data privacy, tenant isolation, and PII redaction.
能力评估
Purpose & Capability
Name/description match the provided instructions and example code (MIME/IMAP/Gmail/Microsoft Graph parsing, thread reconstruction, deduplication, context assembly). Nothing in the manifest asks for unrelated privileges or services.
Instruction Scope
SKILL.md and AGENTS.md contain concrete parsing and pipeline code examples (IMAP fetch, message parsing, deduplication, retrieval). They do not instruct reading arbitrary local files, exfiltrating data to unknown endpoints, or accessing other skills' configs. The instructions are focused on email processing and context assembly.
Install Mechanism
Instruction-only skill with no install spec and no code files to execute. Lowest-risk installation surface; nothing will be downloaded or written by an installer.
Credentials
The skill discusses integrations with Gmail API, Microsoft Graph, IMAP/SMTP etc., which in practice require API keys/credentials and storage of sensitive email data. The registry manifest requests no env vars or credentials — not unsafe by itself, but if you run the example code you will need to provide and protect those credentials (and ensure tenant isolation/PII handling).
Persistence & Privilege
always is false and the skill does not request persistent system-wide privileges or attempt to modify other skills or agent configs. Autonomous invocation is allowed (default) but not combined with other red flags.
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 agency-email-intelligence-engineer
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /agency-email-intelligence-engineer 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 the agency-email-intelligence-engineer skill. - Provides expertise in building robust email data pipelines and context assembly for AI agents. - Handles complex email structures, including thread reconstruction, quoted text deduplication, and participant extraction. - Produces structured, reasoning-ready output formatted for consumption by agent frameworks. - Supports hybrid retrieval, production-grade processing, and multi-tenant data isolation. - Designed for integration with popular AI frameworks like LangChain, CrewAI, and LlamaIndex.
元数据
Slug agency-email-intelligence-engineer
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

test 是什么?

Expert AI agent specializing in email intelligence engineer. From The Agency (github.com/msitarzewski/agency-agents). 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 100 次。

如何安装 test?

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

test 是免费的吗?

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

test 支持哪些平台?

test 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 test?

由 zhouqkt(@zhouqkt)开发并维护,当前版本 v1.0.0。

💬 留言讨论