Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By thisisfatih
Help founders write killer applications to the a16z speedrun program (up to $1M in funding). Guides through every field, scores drafts against a16z criteria, and sharpens answers until they convert.
npx claudepluginhub thisisfatih/apply-a16z --plugin apply-a16zStart or resume your a16z speedrun application. Runs the full pipeline — founder intake, field sync, earned-secrets extraction, answer drafting, eval scoring, and export.
Auto-fill the a16z speedrun application form in your browser using approved answers. Requires Playwright MCP and a completed /apply session. Never submits — founder clicks Submit after reviewing.
Deep-dive into a founder's background and market to surface earned secrets and unfair advantages before running /apply. Use this when a founder isn't sure what makes them unique or wants to do prep work before the full application pipeline.
Score a draft or completed application against a16z speedrun criteria. Use this on answers the founder already wrote, imported drafts, or to re-score after edits. Returns a weighted score table and prioritized fix list.
Rewrite a specific application field to score higher on a16z criteria. Use on any answer that scored below 7.5 in /score, or on any draft the founder wants to strengthen before running the full eval.
Retrieves and maintains the current a16z speedrun application field list. Combines community-researched known fields with any new fields the founder pastes from the live form. Called by the apply orchestrator in Stage 2 to ensure answer generation targets the real form — not a stale field list. Also updates the local fields cache when the founder confirms new or changed fields.
Application coach for a16z speedrun. Guides founders through the full application process — intake, drafting, scoring, and sharpening — with the warmth of a founder-friendly advisor and the precision of someone who has read thousands of VC applications.
Browser automation agent for filling the a16z speedrun application form. Uses Playwright MCP to navigate the form, map generated answers to fields, and fill them — pausing for founder review before any submission. Never submits without explicit founder action.
Simulates an a16z speedrun reviewer reading the application cold. Reads all finalized answers as a skeptical, pattern-matching VC reviewer would — looking for red flags, generic claims, and missing signals. Called after eval-answers passes threshold but before export, providing a final adversarial read from the reviewer's perspective.
Adversarial VC critic. Reads the application as a skeptical a16z partner would — looking for red flags, weak signals, and easy rejections. Invoked by /score to provide the "kill shot" perspective before submission.
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.
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.
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.
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.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Memory compression system for Claude Code - persist context across sessions
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Help founders write, draft, critique, and auto-fill their Y Combinator application.
A Claude Code plugin that helps founders write strong a16z speedrun applications — up to $1M in funding.
The a16z speedrun program funds early-stage AI startups fast. The application is short-form. The bar is high. Most applications fail not because the company is weak, but because the answers are generic — vague problem descriptions, traction numbers without context, team sections that list credentials instead of outputs.
apply-a16z guides you through the application field-by-field. It asks the right questions to surface what makes your company specific and non-obvious, drafts answers from your raw material, scores every field against the criteria a16z reviewers actually use, and sharpens the weak ones before you submit.
The workflow: research your earned secrets → draft all fields → score the draft → sharpen the weak fields → auto-fill the live form → you click Submit.
claude plugin marketplace add thisisfatih/apply-a16z
claude plugin install apply-a16z@apply-a16z
Requires Claude Code. No API keys, no external services, no data leaves your machine.
Optional — browser auto-fill (fills the live form for you):
claude plugin install playwright@anthropic
| Command | What it does |
|---|---|
/apply | Full pipeline — CV intake, questions, earned secrets, drafting, scoring |
/fill | Auto-fill the live form in your browser (requires Playwright MCP) |
/score | Score a draft or existing application against a16z criteria |
/sharpen | Rewrite a specific field to score higher — shows before/after with annotations |
/research | Surface your earned secrets and founder-market fit before drafting |
Every field is scored 1-5 on the rubric in docs/scoring-rubric.md. Fields are weighted by their a16z priority:
Overall score maps to a verdict: Submit now (85+), Sharpen first (70-84), Major revision (55-69), or Rethink framing (<55).
Strong a16z applications share a pattern: every answer contains something specific that could only come from a founder with earned access to the problem — a number, a named customer, a contrarian insight, a thing they built. Generic applications fail because they describe the market without revealing what the founder knows that others don't.
apply-a16z is built around extracting that specificity. The intake questions are designed to surface earned secrets, not just product descriptions. The rubric penalizes vague language and rewards concrete evidence. The sharpening loop doesn't accept polished-sounding weak answers — it asks for the real data.
See examples/sample-application/ for a full annotated application (fictional company, score: 92/100) and a sample coach session showing the intake and sharpening loop.
See CONTRIBUTING.md. The highest-leverage contributions: better field templates, new sample applications with honest scoring, and rubric calibration based on real application outcomes.
MIT — build on it, fork it, use it to fund your company.
README maintained automatically by 🐘 elephant — keep your docs in sync without the manual work.