The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation, templates, and strategic playbooks. No executable scripts, automated tasks, or platform-specific command triggers were identified.
[NO_CODE]: The skill contains no executable code or scripts, serving only as an instructional framework for an AI agent.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and summarizing untrusted external data from LinkedIn profiles, job boards, and press releases. This creates an indirect prompt injection surface where external content could attempt to influence the agent's behavior. Evidence: 1. Ingestion points: Phase 2.1 (web research), Phase 3.1 (intel brief generation). 2. Boundary markers: The skill provides specific outreach templates (assets/email-sequences.md) and messaging rules (Phase 4.1) which limit output variability. 3. Capability inventory: No internal code; depends on host agent tools. 4. Sanitization: Structural constraints enforced through templates.

calendar-pipeline