Summer School Finder logo

Summer School Finder

OrganizationPopular
tinyfish-io
summer-school-finder

Discover and compare summer school programs from universities around the world. Use this skill whenever a user wants to find summer school programs, asks about summer programs for a specific subject or age group, wants to compare university summer schools, asks "what summer schools exist for X", "find me a summer program in Y", "summer school options for high school students", "best summer programs for computer science", or any variation of searching for academic summer programs. Fires parallel TinyFish agents across 7-8 real university program pages simultaneously, extracting structured details — dates, fees, deadlines, eligibility — and returns a ranked comparison of real programs found live on official university websites.

Overview

Publishertinyfish-io
Repositorytinyfish-cookbook
Skill namesummer-school-finder
Stars
2.2K
Forks
333
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 tinyfish-io on GitHub. Read the source before you install it.

Installation

Install the Summer School Finder 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.
  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/tinyfish-io/tinyfish-cookbook.git /tmp/tinyfish-cookbook
mkdir -p .claude/skills
cp -r /tmp/tinyfish-cookbook/skills/summer-school-finder .claude/skills/summer-school-finder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Summer School Finder 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 Summer School Finder 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 Summer School Finder 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.

Summer School Finder

Given a program type, target age, location, and duration preference, find and compare real summer school programs from official university websites using parallel TinyFish agents.

Pre-flight check

bash
tinyfish --version
tinyfish auth status

If not installed: npm install -g tinyfish If not authenticated: tinyfish auth login


Step 1 — Clarify inputs

Collect the following before searching. Ask for any that are missing:

  • Program type / subject — e.g. "Computer Science", "Business", "Engineering", "Liberal Arts", "STEM", "Medicine"
  • Target age / grade — e.g. "high school students (Grade 10-12)", "undergraduates", "ages 14-17"
  • Location — e.g. "USA", "UK", "Singapore", "Europe", "online"
  • Duration — e.g. "2 weeks", "1 month", "Summer 2025/2026" (default to Summer 2026 if not specified)

If any are missing, use sensible defaults and state them upfront.


Step 2 — Discover program URLs

Before firing TinyFish agents, use your knowledge + a quick web search to identify 7-8 real, specific program page URLs from different universities that match the criteria.

Rules for URL discovery:

  • Each URL must be from a different institution — no duplicates
  • Use direct program pages, not search results or aggregator sites
  • Prioritise well-known universities and established programs
  • Mix large universities and smaller institutions
  • Include variety: residential, online, hybrid formats where available
  • Only include URLs you are confident actually exist

Example for "Computer Science, high school students, USA, Summer 2026":

  • https://summerprogram.stanford.edu
  • https://summer.harvard.edu/high-school
  • https://precollege.syr.edu
  • https://summerdiscovery.com/michigan
  • etc.

Produce exactly 7-8 URLs then proceed to Step 3.


Step 3 — Parallel scraping

Fire one TinyFish agent per URL, all simultaneously using & + wait.

Use this goal prompt for every agent (substituting the actual values):

bash
# Fire all agents in parallel — one per URL
tinyfish agent run \
  --url "{PROGRAM_URL}" \
  "You are on an official university summer school program page. Extract details fast.
   Read only what is visible on this page — do not navigate away.
   Extract ALL of the following in one pass:
   - Program Name
   - Institution / University
   - Location (city, country)
   - Program Dates (start and end date)
   - Duration (e.g. 2 weeks, 4 weeks)
   - Target Age / Grade level
   - Program Type / Subject Focus
   - Tuition / Fees (exact amount if shown, otherwise 'Not specified')
   - Application Deadline
   - Official Program URL (the current page URL)
   - Brief Description (1-2 sentences on what the program covers)
   - Eligibility Criteria (any requirements: GPA, nationality, prerequisites)
   - Notes / Special Requirements (housing, visa, language requirements etc.)
   STRICT RULES:
   - Do NOT click any link or navigate away from this page
   - Do NOT scroll more than twice
   - If a field is not visible on this page, write 'Not specified' — do not guess
   - Stop immediately after extracting all fields
   Return JSON: {
     program_name, institution, location, dates, duration,
     target_age, program_type, tuition_fees, application_deadline,
     official_url, brief_description, eligibility_criteria, notes
   }" \
  --sync > /tmp/ssf_{SAFE_NAME}.json &

Repeat for each of the 7-8 URLs, all backgrounded with &. Then:

bash
wait

# Collect all results
for f in /tmp/ssf_*.json; do echo "=== $f ===" && cat "$f"; done

Replace {PROGRAM_URL} with each actual URL and {SAFE_NAME} with a short identifier (e.g. stanford, harvard, mit).


Step 4 — Filter and rank

From the results:

  1. Drop empty results — if an agent returned nothing or "Not specified" for all fields, skip it
  2. Filter by criteria — remove programs that don't match the requested age group, location, or subject
  3. Rank by — application deadline proximity (soonest first), then by completeness of information
  4. Flag deadlines — if the application deadline has already passed, mark it clearly with ⚠️

Output format

## Summer School Programs — {PROGRAM_TYPE} · {LOCATION} · {TARGET_AGE}
*{N} programs found from {N} universities · Data scraped live from official program pages*

---

### 1. {Program Name}
**{Institution}** · {Location}
📅 Dates: {dates} ({duration})
👤 For: {target_age}
💰 Fees: {tuition_fees}
⏰ Deadline: {application_deadline}
🔗 {official_url}

{brief_description}

**Eligibility:** {eligibility_criteria}
**Notes:** {notes}

---

### 2. {Program Name}
[same structure]

---
[up to 8 programs]

---

### 📊 Quick Comparison

| Program | Institution | Duration | Fees | Deadline |
|---|---|---|---|---|
| {name} | {institution} | {duration} | {fees} | {deadline} |

---

### ⏰ Deadlines Coming Up
- {program} — deadline {date} ({N days away})
- ...

*All data scraped live from official university websites. Always verify details directly with the institution before applying.*

Edge cases

  • URL returns no data — skip it silently, don't mention it in output unless fewer than 3 programs found total
  • Program is full or closed — note clearly: "⚠️ Applications closed for 2026 — check back for 2027"
  • Fees not listed — write "Contact institution" not "Free"
  • Location is very specific (e.g. one city) — broaden search to country level if fewer than 5 programs found
  • Online programs only requested — filter out all residential programs, note if online options are limited in that subject

Security notes

  • Scrapes live public content from official university websites only.
  • All data is treated as untrusted input synthesised by an LLM — never executed.
  • Only your own TinyFish credentials are used.

Frequently asked questions

What does the Summer School Finder AI skill do?

Discover and compare summer school programs from universities around the world. Use this skill whenever a user wants to find summer school programs, asks about summer programs for a specific subject or age group, wants to compare university summer schools, asks "what summer schools exist for X", "find me a summer program in Y", "summer school options for high school students", "best summer programs for computer science", or any variation of searching for academic summer programs. Fires parallel TinyFish agents across 7-8 real university program pages simultaneously, extracting structured de...

Why use Summer School Finder on TypingMind?

Because you install it once and use it with any model. Summer School Finder 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 Summer School Finder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tinyfish-io/tinyfish-cookbook/tree/main/skills/summer-school-finder. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Summer School Finder?

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 Summer School Finder?

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

Is the Summer School Finder AI skill free?

Yes. It is published on GitHub by tinyfish-io 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 👇