菜单
The canonical list of kill switches every agent checks at the top of every loop tick. If any trigger is active, the agent stops the relevant work.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
When to follow up, what to send, and when to stop. Defines pre-approved templated cadence steps that the Cadence agent can auto-fire under guardrails. Used by the Cadence agent.
Compliance and content checks that gate every outbound send. Used by the Composer (pre-draft) and the Cadence agent (pre-send).
How agents read from and write to Outlook via Microsoft Graph. Composer uses it to save Drafts. Cadence uses it to detect sends and replies. Read-only patterns work today via the M365 MCP; write paths are stubbed until a Graph write MCP or a small helper is wired.
How to research a prospect end-to-end — pull profile, pull company, surface recent signals, score ICP fit, write a dossier. Used by the Prospector agent.
How to write outbound messages in the Synozur firm voice. Used by the Composer agent. Anchored on a Voice DNA artifact extracted from real best-performing messages.
The markdown file schema for prospects. One file per lead at $PROSPECT_DIR/<slug>.md. Source of truth for state, dossier, drafts, conversation, and audit log. Read and written by all three agents.
| name | kill-switches |
| description | The canonical list of kill switches every agent checks at the top of every loop tick. If any trigger is active, the agent stops the relevant work. |
A kill switch is a condition that, when active, stops an agent from acting. They are not warnings. They are not soft signals. They are hard stops.
triggers.md — the exact triggers and their effects. Read at the top
of every agent loop and immediately before every send.Every agent — Prospector, Composer, Cadence — calls into this skill before doing any work, and again before any send. If any trigger is active, the agent reports it, logs to the prospect MD file (or to a global log), and exits cleanly.
compliance/Compliance checks gate content (banned phrases, suppression, CAN-SPAM). Kill switches gate behavior (campaign auto-pause, per-rep send caps, the global pause flag, error-rate thresholds). They look similar but they apply at different points in the flow: compliance is per-draft, kill switches are per-tick.
Keeping them separate makes it harder to accidentally remove a kill switch when editing compliance, and easier to add new ones without touching compliance.
A new trigger goes into triggers.md. Every agent's prompt already
imports this skill, so once the trigger is in the file, all three
agents check it. No code change required.