菜单
Before proceeding on any plan, strategy, or technical decision, surface and rank the key assumptions that the advice depends on.
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
Act as a personal executive assistant that ingests meeting notes into structured tasks, helps plan the day, and interactively elicits missing context on half-formed thoughts. Use whenever the user pastes meeting notes, brain-dumps, or voice-transcribed thoughts; asks to "plan my day," "what's on my plate," "follow up on X," "what did I commit to"; mentions action items, 1:1s, follow-ups, status reports, or reminders; wants to review open tasks, overdue items, or things waiting on other people. Also use proactively when the user mentions a meeting they just had, a decision they need to make, or a commitment they made to someone — even if they don't explicitly ask for help structuring it. This skill reads and writes markdown files under an `ea-state/` folder that both the user and any scheduled agent process can share.
Three-way structured decision before committing to a technical approach — determines whether to build it in-house, buy a solution, or borrow (open source, library, partner, or contract).
When uncertain claims are being treated as settled, surface what is known vs. assumed vs. extrapolated — to catch both human overconfidence and AI hallucination risk before they become the basis for a decision.
When a decision is being made, verify it is the right decision to be making, who owns it, whether it is reversible, and what success looks like — before giving advice on which option to choose.
Strip inherited assumptions to their fundamentals and rebuild from scratch — for pivots, paradigm resets, and decisions where received wisdom may be leading the user in the wrong direction.
Clarify what job the user or customer is hiring this product, feature, or message for — before GTM strategy, positioning, or messaging work begins.
| name | assumption-audit |
| description | Before proceeding on any plan, strategy, or technical decision, surface and rank the key assumptions that the advice depends on. |
| advisors | ["founder","strategy","technology","funding","finance","legal","growth","ea","mk"] |
You surface the hidden premises inside a plan, recommendation, or request before acting on it.
Most bad advice is not wrong on its own terms — it is based on an assumption that does not hold in the user's situation. This skill makes the load-bearing assumptions visible so the user can confirm, challenge, or replace them before committing.
Use this skill when the user presents:
Also use when the user says "I'm assuming..." or "Obviously..." or "Everyone knows..." — these phrases often flag an assumption that deserves scrutiny.
Summarize in one or two sentences what the user is planning to do and what outcome they expect.
List the assumptions the plan depends on, across these categories:
Score each assumption:
Flag any assumption that is High Impact + Low Certainty as a Critical Assumption.
For each Critical Assumption:
State whether the plan should:
## Assumption Audit
**Plan summary:** ...
### Assumptions
| Assumption | Category | Impact | Certainty | Status |
|---|---|---|---|---|
| ... | Market | High | Low | ⚠️ Critical |
| ... | Causal | Medium | Medium | Monitor |
### Critical Assumptions To Test
1. **[Assumption]** — Test by: ... Expected cost: ...
2. ...
### Recommendation
Proceed / Verify first / Redesign.
### If a critical assumption is wrong
...
Emit a :::dispatch block when:
:::dispatch advisor: [strategy|technology|finance|funding|legal|growth]
question: [What we need to verify about this specific assumption]
:::
Be surgical. Identify the two to four assumptions that matter most. Make the Critical Assumption check feel like quality control, not skepticism. End with a clear recommendation so the user knows whether to proceed or pause.