Accelerator Application logo

Accelerator Application

Community
shawnpang
accelerator-application

When the user wants to apply to startup accelerators, incubators, or fellowship programs. Also use when the user mentions "YC application", "Techstars", "accelerator", or "apply to programs".

Overview

Publishershawnpang
Repositorystartup-founder-skills
Skill nameaccelerator-application
Stars
368
Forks
43
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by shawnpang on GitHub. Read the source before you install it.

Installation

Install the Accelerator Application AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/shawnpang/startup-founder-skills/tree/main/skills/accelerator-application
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/shawnpang/startup-founder-skills.git /tmp/startup-founder-skills
mkdir -p .claude/skills
cp -r /tmp/startup-founder-skills/skills/accelerator-application .claude/skills/accelerator-application
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Accelerator Application in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Accelerator Application on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Accelerator Application is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Accelerator Application

When to Use

  • Founder wants to apply to Y Combinator, Techstars, or other accelerator programs
  • Founder wants to identify which accelerators are the best fit for their stage and sector
  • Founder wants help drafting application essays and preparing for interviews
  • Founder wants to batch-apply to multiple programs efficiently

Context Required

  • Company stage, product, and traction metrics
  • Founder backgrounds and why this team is uniquely positioned
  • What the founder wants from an accelerator (funding, network, credibility, customers, mentorship)
  • Industry/vertical (some accelerators are sector-specific)
  • Geography and willingness to relocate
  • Previous applications or rejections (to improve this round)

Workflow

  1. Match accelerators to the startup — filter the directory below by stage fit, sector focus, geography, and program terms. Recommend a shortlist of 5-10 programs ranked by fit.
  2. Research each program's preferences — review recent cohort companies, partner bios, and published advice from each accelerator on what they look for. Note any patterns (YC values technical founders and fast growth; Techstars values coachability and market size).
  3. Draft the core narrative — write the foundational answers that most applications share:
    • What does your company do? (one sentence, no jargon)
    • What problem are you solving and for whom?
    • Why now? What's changed that makes this possible?
    • Why is this team the right team?
    • What traction do you have?
    • What's your unfair advantage or unique insight?
  4. Customize per application — adapt the core narrative to each program's specific questions, word limits, and culture. YC applications are famously terse. Techstars wants to see coachability. Others want market size.
  5. Prepare the video (if required) — draft a script for the 1-2 minute application video. Structure: problem → solution → traction → team → ask. Keep it authentic, not polished.
  6. Prepare for interviews — draft answers to common accelerator interview questions (see below). Practice the 30-second pitch.

Top US Accelerators Directory (40+)

Tier 1 — Generalist, Top-Tier

ProgramWebsiteInvestmentEquityDurationLocationBest For
Y Combinatorycombinator.com$500K ($125K for 7% + $375K uncapped MFN SAFE)7% (on $125K portion)3 monthsSan FranciscoTechnical founders, fast-growing startups at any stage
Techstarstechstars.com$120K6%3 monthsMultiple citiesCoachable founders, strong mentor network needs
500 Global500.co$150K5%4 monthsSan FranciscoInternational founders, diverse backgrounds
Antlerantler.co$250K8-10%6 monthsNYC, AustinPre-team / pre-idea founders looking for co-founders
Launch Acceleratorlaunchaccelerator.co$100K6%3 monthsSan FranciscoConsumer and SaaS, media exposure via TWIST network
Entrepreneur Firstjoinef.com$80-125K~10%6 monthsNYC, London, globalPre-team, build with a co-founder from the cohort
South Park Commonssouthparkcommons.comFellowshipNo equityOngoingSan FranciscoExperienced operators exploring what to build next
Pioneerpioneer.app$20K1%RemoteRolling (weekly)Very early stage, global, remote-first
HF0hf0.comFellowship + communityNo equityOngoingSan FranciscoDeeply technical founders, hacker community, ex-FAANG builders

Tier 2 — Sector-Specific

ProgramWebsiteFocusInvestmentLocation
a16z Speedruna16z.com/speedrunConsumer tech$750KSan Francisco
Neoneo.comEnterprise / deep techVariesSan Francisco
Alchemist Acceleratoralchemistaccelerator.comEnterprise sales$36KSan Francisco
Dreamit Venturesdreamit.comHealthTech, UrbanTech$50-100KPhiladelphia / NYC
Plug and Playplugandplaytechcenter.comIndustry verticalsVaries (no equity)Sunnyvale
ERA (Entrepreneur Roundtable)era.coNYC ecosystem$100KNew York
Gener8torgener8tor.comMidwest / emerging markets$100KMilwaukee, multiple
Founders Factoryfoundersfactory.comCorporate-backed verticalsVariesNYC, London
Boomtown Acceleratorboomtownaccelerators.comMedia, tech, sustainability$50KBoulder, CO
Mucker Capitalmuckercapital.comB2B SaaS, consumer$150KLos Angeles
Indie Bioindiebio.coBiotech / life sciences$250KSan Francisco
HAXhax.coHardware / deep tech$250KNewark, NJ
Techstars AItechstars.comAI-native startups$120KMultiple
Google for Startups Acceleratorstartup.google.comAI, Cloud, various$0 (no equity)Multiple
Microsoft for Startupsmicrosoft.com/startupsCloud / AICredits (no equity)Remote
AWS Activateaws.amazon.com/activateCloud infrastructureCredits (no equity)Remote

Tier 3 — Non-Profit, University & Government

ProgramWebsiteFocusLocation
MassChallengemasschallenge.orgSocial impact, any sector ($0, no equity)Boston, multiple
StartX (Stanford)startx.comStanford-affiliatedPalo Alto
Creative Destruction Labcreativedestructionlab.comScience-based venturesMultiple
NSF I-Corpsicorps.nsf.govDeep tech commercializationNational
SBIR/STTRsbir.govGovernment R&D grantsNational
Lassonde Entrepreneur Institutelassonde.utah.eduStudent foundersSalt Lake City
Berkeley SkyDeckskydeck.berkeley.eduUC Berkeley-affiliatedBerkeley
MIT delta ventrepreneurship.mit.eduMIT-affiliatedCambridge
Columbia Startup Labstartup.columbia.eduColumbia-affiliatedNew York
Carnegie Mellon Swartz Centercmu.edu/swartz-centerCMU-affiliatedPittsburgh

Note: Terms, investment amounts, and equity percentages change frequently. Verify current terms on each program's website before applying.

Output Format

markdown
## Accelerator Application Plan

### Recommended Programs (ranked by fit)
1. **[Program]** — [why it's a fit] | Deadline: [date] | Apply: [link]
2. ...

### Core Narrative
- **One-liner:** [what you do in one sentence]
- **Problem:** [2-3 sentences]
- **Solution:** [2-3 sentences]
- **Why now:** [1-2 sentences]
- **Traction:** [key metrics]
- **Team:** [why you're the right people]
- **Unique insight:** [what you know that others don't]

### [Program Name] Application Draft
**Q: [Question from application]**
A: [Draft answer within word limit]
...

### Interview Prep
**30-second pitch:** [draft]
**Common questions and answers:**
- "What do you understand that others don't?" — [answer]
- "How do you acquire users/customers?" — [answer]
- "What's the biggest risk?" — [answer]
- "Why hasn't this been done before?" — [answer]
- "What will you do if this doesn't work?" — [answer]

Frameworks & Best Practices

What top accelerators look for:

  • YC: Founders who build fast. Technical co-founders. Clear thinking, not polish. "Make something people want." They read applications in under 2 minutes — be concise.
  • Techstars: Coachability and self-awareness. Market size. The "why you" answer. They call references on founders.
  • 500 Global: Diverse founders, international-friendly. Traction and hustle over pedigree.

Application writing principles:

  • Lead with what you've built and what's working, not the market opportunity
  • Use specific numbers ("1,200 users, 40% WoW growth") not vague claims ("rapidly growing")
  • Show velocity — what you've accomplished in the last 4 weeks matters more than a 5-year vision
  • Be honest about what's not working — self-awareness is a signal of founder quality
  • Write at a 6th-grade reading level. No jargon, no buzzwords, no "leveraging AI to disrupt"

Common mistakes:

  • Applying to every accelerator instead of targeting the best 5-7 fits
  • Writing what you think they want to hear instead of what's true
  • Burying the traction (put numbers in the first sentence)
  • Over-explaining the market instead of showing what you've done
  • Sending a polished video instead of an authentic one (YC explicitly says don't do this)
  • Not researching which partners/mentors at the program are relevant to your space

Related Skills

  • pitch-deck — accelerator interviews often involve a short pitch
  • fundraising-email — for follow-up communication with program partners
  • investor-research — accelerator partners are also investors

Examples

Prompt: "Help me apply to YC for the next batch. We're a developer tools startup with 500 users."

Good output includes: Tailored YC application draft with concise answers to each question, emphasis on technical depth and growth rate, a 60-second video script, and interview prep focused on YC's known question patterns.

Prompt: "What accelerators should I apply to for my healthtech startup? We're pre-revenue but have LOIs from 3 hospitals."

Good output includes: Filtered list prioritizing Dreamit (HealthTech focus), YC (strong health portfolio), and relevant sector programs. Application strategy emphasizing LOIs as traction signal.

Frequently asked questions

What does the Accelerator Application AI skill do?

When the user wants to apply to startup accelerators, incubators, or fellowship programs. Also use when the user mentions "YC application", "Techstars", "accelerator", or "apply to programs".

Why use Accelerator Application on TypingMind?

Because you install it once and use it with any model. Accelerator Application is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Accelerator Application in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/shawnpang/startup-founder-skills/tree/main/skills/accelerator-application. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Accelerator Application?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Accelerator Application?

As many as you like. As long as a model supports skills, you can use Accelerator Application with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Accelerator Application AI skill free?

Yes. It is published on GitHub by shawnpang under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇