菜单
Activated when a founder asks to improve a specific application answer, or when /score identifies a field scoring below 3/5. Rewrites with annotated before/after and scores the revision.
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
Main orchestrator for the a16z speedrun application. Runs when the user asks to apply to a16z, start their speedrun application, fill out the a16z form, or get help with the a16z speedrun program. Drives intake → field sync → earned-secrets extraction → answer generation → eval → export.
Scores drafted a16z speedrun application answers against a16z selection criteria. Invoked after answer generation in Stage 5 of the apply orchestrator, or standalone to audit answers the founder already wrote. Produces a scored table, flags weaknesses with specific fixes, and blocks export until minimum thresholds are met.
Deep-dives to surface founder's non-obvious market insights. Invoked during Stage 3 of the apply orchestrator, or standalone when a founder says "I don't think I have a unique insight", "I'm not sure what makes us different", or "help me figure out what I actually know". Uses Socratic pressure + insight taxonomy to extract and name the real competitive moat.
Packages approved a16z speedrun application answers into submission-ready formats. Invoked after eval-answers confirms all fields pass threshold. Produces a Markdown review copy, a fill-ready plain-text file with field-by-field copy-paste blocks, and optionally a JSON record for version tracking.
Crafts the founder's pitch narrative and earned-secrets framing for the a16z speedrun application. Invoked when drafting the "why you, why now" story, the founder's unique insight, the video pitch script, or any narrative-heavy application fields. Runs a Socratic interview to surface the real story, then structures it into a16z-resonant framing.
| name | Sharpen Answers |
| description | Activated when a founder asks to improve a specific application answer, or when /score identifies a field scoring below 3/5. Rewrites with annotated before/after and scores the revision. |
| version | 0.1.0 |
/sharpen/score surfaces a field below 3/5 and offers to sharpen itReviewers scan hundreds of applications. Match compression to field purpose:
| Field | Density | Rule |
|---|---|---|
| One-liner (10w) | ultra | Noun phrase only. No articles. Every word counts. |
| Relevant experience | full | Drop articles. Fragments OK. Outputs stacked, not narrated. |
| Team description | full | Drop articles. Facts + proof. No connective filler. |
| Startup description | lite | Keep sentences. Drop filler. SCQA flow must survive compression. |
| Traction notes | full | Numbers first. Context in fragments. Zero hedging. |
| Anything else | lite | Clear delta. Full sentences. No padding. |
Density levels:
Apply the target density when rewriting. If upgrading to full/ultra causes ambiguity, step back to lite.
ORIGINAL:
[paste original]
REWRITE:
[rewrite]
CHANGES:
- "[word/phrase changed]" → "[replacement]" — [one-word rationale: specificity / insight / momentum / economy / voice]
Score the rewrite (1-5) immediately. If still below 4/5, offer a second pass. Name what's still missing before doing it — don't just rewrite again blindly.
When sharpening the Startup Description, check docs/a16z-big-ideas.md:
Example (before): "We build AI tools for enterprise data teams." Example (after with alignment): "Enterprise data teams can't feed unstructured PDFs, videos, and contracts into AI reliably. We build the ingestion and structuring layer that makes this work — exactly the gap Jennifer Li (a16z) named as Big Idea #1 for 2026."
If the founder's raw material doesn't support a strong answer (no real insight, no traction), surface that explicitly rather than producing a polished-sounding weak answer. Suggest /research to find the missing material.