New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Stack Picker

by MAGA2010 in MAGA2010/hackathon-run

Recommends a tech stack when the team has no preference, the prize category biases a stack, or time pressure forces the simplest viable choice.

MITAuto-check passedMobile

Install Stack Picker

skills CLI
$ npx skills add MAGA2010/hackathon-run --skill stack-picker -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install MAGA2010/hackathon-run stack-picker --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/MAGA2010/hackathon-run.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/stack-picker .claude/skills/stack-picker && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
stack-picker
GitHub stars
349
Token cost
~1.1k tokens
SKILL.md length
417 words
Files
2 (incl. scripts)
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Recommends a tech stack when the team has no preference, the prize category biases a stack, or time pressure forces the simplest viable choice.

  • Works in 4 steps: Filter viable stacks → Score each viable stack → Recommend top 1 + runners-up → …
  • Mobile work in your project
  • SKILL.md covers Input contract, Execution, Helper and Output contract, plus 3 more sections
  • Runs Python scripts from its folder

What it does

Stack Picker is an agent skill from MAGA2010/hackathon-run. Recommends a tech stack when the team has no preference, the prize category biases a stack, or time pressure forces the simplest viable choice. Use at the start of a hackathon before any code is written.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/pick.py`).

It sits in Mobile. The licence is MIT.

When your agent uses it

  • Mobile work in your project

Example prompts

  • “Use the stack-picker skill to recommend a tech stack when the team has no preference, the prize category biases a stack, or time pressure forces the…”
  • “/stack-picker”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Filter viable stacks
  2. Score each viable stack
  3. Recommend top 1 + runners-up
  4. Emit the 30-minute setup

What it can do on your machine

Read from SKILL.md and the folder at commit de3bcfb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Stack Picker loads about 1.1k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 417 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from MAGA2010/hackathon-run at commit de3bcfb, republished under its MIT licence (© MAGA2010). 417 words, ~1,133 tokens.

Download SKILL.mdSave it as .claude/skills/stack-picker/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
stack-picker
description
Recommends a tech stack when the team has no preference, the prize category biases a stack, or time pressure forces the simplest viable choice. Use at the start of a hackathon before any code is written.
when_to_use
Trigger when the user says "what should we build with", "we don't know the stack", "what language for a hackathon", or after idea-clarify surfaces a domain…
version
1.0
category
scoping
tags
["tech-stack", "bootstrap", "30-min"]
dependencies
["idea-clarify", "scope-knife"]
side_effects
["stack"]
triggers
["what stack should we use", "tech stack", "how do we bootstrap", "pick the framework", "recommended stack"]

stack-picker

Choosing a stack under pressure is the single highest-leverage decision in the first hour. Wrong stack = 4 hours of yak-shaving instead of building. Right stack = an MVP by midnight.

Input contract

Required:

  • team_skills: list of strings ("python" | "javascript" | "typescript" | "react" | "react-native" | "swift" | "kotlin" | "rust" | "go" | "java" | "ruby" | "elixir" | ...)
  • time_remaining_minutes: integer >= 0
  • demo_format: one of web | mobile | desktop | cli | api | data | ml | hardware

Optional:

  • prize_category: free text ("best ai use" | "best sustainability" | "best new developer tool" | ...)
  • must_integrate: list of external APIs or services the project must touch
  • team_size: integer >= 1 (default 1)

Execution

1. Filter viable stacks

For each entry in the candidate table, the stack is viable iff:

  • All required team skills are present in team_skills, OR
  • The team has at least one generalist (javascript + python both count)
2. Score each viable stack

score = skill_match * 3 + speed * 2 + prize_fit * 2 - setup_cost

ComponentRangeDefinition
skill_match0 – 1fraction of required skills the team has
speed0 – 1how fast a competent team can hit MVP (<= 1h = 1.0)
prize_fit0 – 1match between stack and prize_category
setup_cost0 – 3minutes to a hello-world (0 for browser, 3 for native)
3. Recommend top 1 + runners-up

Output:

  • recommendation: the top-scored stack, with a one-line rationale
  • runners_up: next 2 stacks, with the tradeoff each one buys
  • anti_recommendation: the worst-scored viable stack, with the failure mode
4. Emit the 30-minute setup

For the recommended stack, emit a step-by-step 30-minute bootstrap:

  1. Install / clone / scaffold command
  2. One minimal "hello world" file path + content
  3. The single command that proves it works (browser URL, CLI exit, curl)
Show full SKILL.md (155 more words)Show less

Helper

The skill ships scripts/pick.py which implements the scoring algorithm above end-to-end and writes both .hackathon/state/stack.json and .hackathon/artifacts/stack-bootstrap.md. Run it with:

python3 skills/stack-picker/scripts/pick.py \ --team-skills python,javascript \ --time-remaining 240 \ --demo-format web \ --out-dir .hackathon

Output contract

Files written:

  • .hackathon/state/stack.json (NEW schema)
  • .hackathon/artifacts/stack-bootstrap.md (30-min setup walkthrough)

Acceptance criteria

  • Outputs exactly one recommendation from the viable set.
  • Each recommendation has a one-line rationale.
  • Recommendation stack is reachable inside setup_cost minutes.
  • anti_recommendation is named and the failure mode is concrete.
  • Bootstrap walkthrough is runnable end-to-end in <= 30 minutes.

Failure modes

ModeBehavior
No viable stacksRefuse; suggest adding a generalist to the team
team_skills emptyRefuse; ask the user for at least one skill
must_integrate has unknown APIWarn; suggest a 30-min spike first
Two stacks tiePrefer the one with lower setup_cost

Trigger phrases (for agent intent matching)

  • "what should we build with"
  • "what language for a hackathon"
  • "we need to pick a stack"
  • "best stack for X"
  • "what framework"

© MAGA2010, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in skills/stack-picker of MAGA2010/hackathon-run.

  • SKILL.md
  • scripts/pick.py

Open the folder on GitHubat commit de3bcfb

Compare with similar skills

Stack Picker next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Stack Picker compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Stack Picker this skillMAGA2010/hackathon-run349—~1.1kAutomated safety check: PassMIT
React Native Best Practicesvercel-labs/openreview1.7k17 repos~1.1kAutomated safety check: PassMIT
Swiftui Protwostraws/SwiftUI-Agent-Skill5k2 repos~1kAutomated safety check: PassMIT
Ip As LogoKartikLabhshetwar/better-shot2.4k1 repos~4.3kAutomated safety check: PassMIT
Compose Multiplatform Patternsmonta-app/ocpp-emulator1795 repos~2kAutomated safety check: PassApache-2.0
Aso Appstore Screenshotsadamlyttleapps/claude-skill-aso-appstore-screenshots1.8k1 repos~9.6kAutomated safety check: PassMIT

Similar skills

  • React Native Best Practices

    vercel-labs/openreview

    Official

    A prioritized rule set for React Native and Expo apps covering list performance, animation, navigation, UI patterns, state, rendering, monorepos and configuration.

    1.7k GitHub starsUsed in 17 repos~1.1k tokens
    MobileAuto-check passed

  • Swiftui Pro

    twostraws/SwiftUI-Agent-Skill

    Comprehensively reviews SwiftUI code for best practices on modern APIs, maintainability, and performance.

    5k GitHub starsUsed in 2 repos~1k tokens
    MobileAuto-check passed

  • Ip As Logo

    KartikLabhshetwar/better-shot

    Generate extremely simple, cute, personified square character images with rounded heavy forms, two purposeful character colors, one solid background color, and a dominant lower-corner composition.

    2.4k GitHub starsUsed in 1 repo~4.3k tokens
    MobileAuto-check passed

  • Compose Multiplatform Patterns

    monta-app/ocpp-emulator

    Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI.

    179 GitHub starsUsed in 5 repos~2k tokens
    MobileAuto-check passed

  • Aso Appstore Screenshots

    adamlyttleapps/claude-skill-aso-appstore-screenshots

    Generate high-converting App Store screenshots by analyzing your app's codebase, discovering core benefits, and creating ASO-optimized screenshot images using Nano Banana Pro.

    1.8k GitHub starsUsed in 1 repo~9.6k tokens
    MobileAuto-check passed

  • Swiftui UI Patterns

    AFK-surf/OpenBridge

    Best practices and example-driven guidance for building SwiftUI views and components.

    430 GitHub starsUsed in 4 repos~887 tokens
    MobileAuto-check passed

More from MAGA2010/hackathon-run

All 15 skills in this repo

  • Decision Log

    MAGA2010/hackathon-run

    Writes every KEEP/CUT/DEFER/PIVOT scope decision into an append-only team log with rationale, author, and timestamp.

    349 GitHub stars~847 tokensUpdated 3 days ago
    Auto-check passed

  • Demo Coach

    MAGA2010/hackathon-run

    Drafts a 30, 60, or 90-second pitch script for the demo, structured as opening, pain, product, action, result, close.

    349 GitHub stars~895 tokensUpdated 3 days ago
    Auto-check passed

  • Judge Sim

    MAGA2010/hackathon-run

    Scores a hackathon project 0 to 5 across seven judging dimensions and produces a prioritized fix list for the last hour.

    349 GitHub stars~970 tokensUpdated 3 days ago
    Auto-check passed

  • Scope Knife

    MAGA2010/hackathon-run

    Forces a KEEP, CUT, or DEFER decision on every feature when scope is too large, no MVP consensus exists, or time is running out.

    349 GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed

  • Time Box

    MAGA2010/hackathon-run

    Allocates time across the hackathon lifecycle (idea - scope - build - verify - demo - ship) and warns before each deadline slips.

    349 GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed

  • Fast Verify

    MAGA2010/hackathon-run

    Verifies the demo path runs end-to-end by executing each step in order, recording the actual outcome, and stopping at the first failure with a diagnostic.

    349 GitHub stars~893 tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Stack Picker

What does Stack Picker do?

Recommends a tech stack when the team has no preference, the prize category biases a stack, or time pressure forces the simplest viable choice. Stack Picker is an agent skill from MAGA2010/hackathon-run. Recommends a tech stack when the team has no preference, the prize category biases a stack, or time pressure forces the simplest viable choice.

When should I use Stack Picker?

Stack Picker fits situations like: mobile work in your project.

How do I install Stack Picker in Claude Code?

Run `npx skills add MAGA2010/hackathon-run --skill stack-picker -a claude-code`. Or copy the skill folder (skills/stack-picker in MAGA2010/hackathon-run) into .claude/skills/stack-picker in your project. Claude Code loads it when a task matches its description.

How do I install Stack Picker in Codex?

Run `npx skills add MAGA2010/hackathon-run --skill stack-picker -a codex`. Or copy the skill folder (skills/stack-picker in MAGA2010/hackathon-run) into .agents/skills/stack-picker in your project. Codex loads it when a task matches its description.

Can I use Stack Picker in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MAGA2010/hackathon-run --skill stack-picker -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/stack-picker, .gemini/skills/stack-picker, .github/skills/stack-picker and .opencode/skills/stack-picker in your project.

What does Stack Picker need to run?

Going by SKILL.md and its folder, Stack Picker needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Stack Picker access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Stack Picker safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Stack Picker use?

Stack Picker is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Stack Picker use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Stack Picker?

Skills that share tags, products or a category with Stack Picker: React Native Best Practices (vercel-labs/openreview, 1.7k stars), Swiftui Pro (twostraws/SwiftUI-Agent-Skill, 5k stars), Ip As Logo (KartikLabhshetwar/better-shot, 2.4k stars) and Compose Multiplatform Patterns (monta-app/ocpp-emulator, 179 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Stack Picker?

MAGA2010 (a GitHub user) maintains it in MAGA2010/hackathon-run, which has 349 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 4, 2026.

Source: MAGA2010/hackathon-run on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.