test

Expert AI agent specializing in email intelligence engineer. From The Agency (github.com/msitarzewski/agency-agents).

Security Scan

The skill's files and runtime instructions are consistent with an 'email intelligence engineer' — examples show email parsing, threading, and context assembly and do not request unrelated credentials, installs, or hidden endpoints.

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.

Assessment

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).

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.