菜单
Structured AI-guided interrogation skill for breaking into greenfield accounts. Use when the user wants to research a target account, identify urgency signals and warm paths, map stakeholders, build an Account Brief, and draft persona-specific outreach before outbound.
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。
Quick urgency scan for a target account. Identifies triggers, scores urgency (1-10), and tells you whether to move now, build slowly, or park. Use when you need a fast read on whether an account is worth pursuing right now. Runs Stage 0.5 only.
Map every warm path into a target account — LinkedIn connections, internal intel, customer networks, investor overlap, partner relationships, alumni, and pre-warm engagement. Use when the AE wants to find the easiest doors before going cold. Combines LinkedIn Co-Pilot, Pre-Stage company branching, Stage 1, and Stage 6.
Score and audit an existing Account Brief. Finds gaps, unverified claims, missing warm paths, weak messaging, and the overall quality of the intelligence. Use after a full Greenfield run to validate quality, or as a manager reviewing an AE's account plan.
Deep executive research and outreach strategy for a target account. Maps leadership, builds executive narratives, enforces the Earned Right Test, and generates persona-specific message drafts. Use when the AE is preparing to contact a specific executive. Runs Stage 5, Stage 5.5, and Stage 9.
Lightweight 5-minute account snapshot. Company overview, top 3 triggers, top 3 personas, and a go/no-go recommendation. Use when the AE wants a fast read on an account before deciding whether to invest time in a full Greenfield run. No Account Brief, no message drafts.
| name | greenfield |
| description | Structured AI-guided interrogation skill for breaking into greenfield accounts. Use when the user wants to research a target account, identify urgency signals and warm paths, map stakeholders, build an Account Brief, and draft persona-specific outreach before outbound. |
Use GREENFIELD.md as the canonical workflow for a full run.
UNVERIFIED instead of implying access you do not have.When the user's request matches a focused skill, route to it instead of running the full workflow:
| Request Pattern | Skill | Path |
|---|---|---|
| "Quick scan," "is this worth pursuing," "triage this account" | Quick Scan | skills/quick-scan/SKILL.md |
| "Check urgency," "any triggers," "why now," "is this urgent" | Trigger Radar | skills/trigger-radar/SKILL.md |
| "Find warm paths," "who do I know," "LinkedIn connections," "warm intro" | Warm Path | skills/warm-path/SKILL.md |
| "Executive research," "leadership deep dive," "exec outreach," "earned right" | Leadership Intel | skills/leadership-intel/SKILL.md |
| "Review this account brief," "score my account plan," "audit my research" | Account Review | skills/account-review/SKILL.md |
| "Run Greenfield," "full run," "hack this account" | Full Run | GREENFIELD.md |
If no specific pattern matches, default to the full run.
When the user asks to run Greenfield, start with the exact opener defined in GREENFIELD.md and continue from there.
Every skill run must end with:
STATUS: DONE | DONE_WITH_CONCERNS | INCOMPLETE | BLOCKED
For full Greenfield runs, append the JSON sidecar defined in GREENFIELD.md immediately after the human status block. See QUALITY_GATES.md for the full Completion Status Protocol.