菜单
Build a confirm-or-kill diligence plan where every workstream tests a named thesis assumption and every finding is mapped to thesis or price impact — not a data-room checklist. Reach for this once a thesis exists and a deal is live.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/mcorbett51090/RavenClaude --skill run-a-diligence-plan命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Route everyday, well-defined work (single-file edits, test-writing, summarization, mechanical refactors, boilerplate) to a cheaper coding agent (Grok or Copilot CLI) instead of doing it in the main Claude session, escalating multi-file/architecture/debugging/security work to Claude. Opt-in via the `cheap_lane:` comfort-posture knob.
Authors, validates and packages a claude.ai Organization Skill — the intake questions, the trigger and scope exercises, then lint, pack and verify against measured platform constraints. Reach for this when someone wants to publish a Skill to their organization, or when an upload was rejected and the reason is unclear.
Drafts a reply to an inbound customer email, grounded in the account record and the published help-centre articles rather than in recall. Use when a customer emails about billing, a renewal or an outage, when a reply must cite current policy, or when a teammate asks for a first draft to edit.
基于 SOC 职业分类
正在显示 SKILL.md
| name | run-a-diligence-plan |
| description | Build a confirm-or-kill diligence plan where every workstream tests a named thesis assumption and every finding is mapped to thesis or price impact — not a data-room checklist. Reach for this once a thesis exists and a deal is live. |
Diligence exists to change the decision, not to fill a data room (§3 #5).
From the deal thesis, extract each assumption the deal depends on (the value-creation drivers and the deal-breakers). These, not a generic checklist, define the plan.
For each assumption, assign the workstream that tests it (financial / commercial / technology / legal / people & culture) and write the confirm-or-kill question. A workstream that tests no assumption is dropped.
Scrutinize adjusted/normalized EBITDA add-backs, separate recurring from one-time revenue, and flag working-capital and revenue-recognition issues. Route audited-number confirmation to accountants; you flag, they attest.
Identify key-person concentration and retention risk and cultural-fit red flags (§3 #7) — these are diligence items, priced before signing.
Rank findings by thesis impact and price impact, each with the evidence needed to confirm and an escalation owner. Feed re-pricing findings back to the valuation.
A diligence plan (workstreams mapped to thesis assumptions with confirm-or-kill questions), a QoE read, a people/culture underwrite, and a ranked red-flag register with thesis/price impact and owners. See ../../knowledge/ma-decision-trees.md.