Flutter Cherry Pick
flutter/flutter
How to land a formal cherry-pick of a merged PR for the flutter/flutter repo stable or beta channel.
Picks which prize category a hackathon project should chase and how to position the demo around that prizes judging criteria.
MITAuto-check passed
Install Prize Strategy
$ npx skills add MAGA2010/hackathon-run --skill prize-strategy -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MAGA2010/hackathon-run prize-strategy --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/MAGA2010/hackathon-run.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prize-strategy .claude/skills/prize-strategy && rm -rf skills-srcUse ~/.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/
Install the "prize-strategy" agent skill from https://github.com/MAGA2010/hackathon-run/tree/main/skills/prize-strategy into .claude/skills/prize-strategy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prize-strategy", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/MAGA2010/hackathon-run/tree/main/skills/prize-strategyType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add MAGA2010/hackathon-run --skill prize-strategy -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MAGA2010/hackathon-run prize-strategy --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MAGA2010/hackathon-run.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/prize-strategy .agents/skills/prize-strategy && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prize-strategy" agent skill from https://github.com/MAGA2010/hackathon-run/tree/main/skills/prize-strategy into .agents/skills/prize-strategy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prize-strategy", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MAGA2010/hackathon-run --skill prize-strategy -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MAGA2010/hackathon-run prize-strategy --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MAGA2010/hackathon-run.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/prize-strategy .cursor/skills/prize-strategy && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "prize-strategy" agent skill from https://github.com/MAGA2010/hackathon-run/tree/main/skills/prize-strategy into .cursor/skills/prize-strategy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prize-strategy", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/MAGA2010/hackathon-run.git --path skills/prize-strategy--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add MAGA2010/hackathon-run --skill prize-strategy -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MAGA2010/hackathon-run prize-strategy --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MAGA2010/hackathon-run.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/prize-strategy .gemini/skills/prize-strategy && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "prize-strategy" agent skill from https://github.com/MAGA2010/hackathon-run/tree/main/skills/prize-strategy into .gemini/skills/prize-strategy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prize-strategy", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install MAGA2010/hackathon-run prize-strategyInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add MAGA2010/hackathon-run --skill prize-strategy -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/MAGA2010/hackathon-run.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/prize-strategy .github/skills/prize-strategy && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "prize-strategy" agent skill from https://github.com/MAGA2010/hackathon-run/tree/main/skills/prize-strategy into .github/skills/prize-strategy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prize-strategy", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MAGA2010/hackathon-run --skill prize-strategy -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install MAGA2010/hackathon-run prize-strategy --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MAGA2010/hackathon-run.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/prize-strategy .opencode/skills/prize-strategy && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "prize-strategy" agent skill from https://github.com/MAGA2010/hackathon-run/tree/main/skills/prize-strategy into .opencode/skills/prize-strategy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prize-strategy", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
prize-strategy- GitHub stars
- 411
- Token cost
- ~1.1k tokens
- SKILL.md length
- 440 words
- Files
- 2 (incl. scripts)
- Skills in repo
- 15
- Repo updated
- First seen
- Licence
- MIT
At a glance
Picks which prize category a hackathon project should chase and how to position the demo around that prizes judging criteria.
- Works in 4 steps: Score every prize → Rank and emit target → Emit positioning notes → …
- SKILL.md covers Input contract, Execution, Output contract and Acceptance criteria, plus 3 more sections
- Runs Python scripts from its folder
What it does
Prize Strategy is an agent skill from MAGA2010/hackathon-run. Picks which prize category a hackathon project should chase and how to position the demo around that prizes judging criteria. Use at the start of the build phase once the demogoal is stable and at least 4 hours remain.
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/target.py`).
The licence is MIT.
Example prompts
- “Use the prize-strategy skill to pick which prize category a hackathon project should chase and how to position the demo around that prizes judging…”
- “/prize-strategy”
Requirements
- Python 3
Workflow steps
4 steps, taken from the step headings in SKILL.md.
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
Prize Strategy loads about 1.1k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 440 words of instructions outside code blocks.
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). 440 words, ~1,135 tokens.
Download SKILL.mdSave it as
.claude/skills/prize-strategy/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- prize-strategy
- description
- Picks which prize category a hackathon project should chase and how to position the demo around that prizes judging criteria. Use at the start of the build phase once the demo_goal is stable and at least 4 hours remain.
- when_to_use
- Trigger when the user says what prize should we target, which track should we go for, judges care about X, or right after scope-knife produces a KEEP list. Do…
- version
- 1
- category
- scoping
- tags
- prize, strategy, positioning, judges
- dependencies
- scope-knife
- side_effects
- prize
- triggers
- what prize should we target, which track should we go for, how do we position for X prize, what do judges want, which prize category
- capabilities
- fs_read, fs_write
prize-strategy
Most hackathon submissions that lose do not lose because of code; they lose because the team did not consciously pick a prize and did not frame their demo for the judges that award it. This skill forces that decision.
Input contract
Required:
prizes: list of{name, criteria: list[str], weight: int}from the hackathon page (e.g. overall, ai-use, sustainability, newcomer).project:{demo_goal: str, features: list[str], stack: list[str]}from.hackathon/state/plan.json.team_skills: list of strings (e.g. python, react, llm).
Optional:
time_remaining_minutes: integer >= 0 (default 240).target_demo_minutes: integer (default 3).previous_prizes: list of prize names the team has won before (default empty).
Execution
1. Score every prize
For each prize, compute:
fit_score = 0.45 * criteria_overlap + 0.30 * demo_goal_match + 0.15 * stack_match + 0.10 * team_fit
Where:
criteria_overlap= fraction of prize.criteria words that appear in demo_goal or features (case-insensitive).demo_goal_match= fraction of demo_goal words that appear in prize.criteria.stack_match= 1 if any stack element matches any criteria word, 0 otherwise.team_fit= bonus if team_skills contains common winning tools for the prize (LLMs/transformers for ai-use, etc.).
2. Rank and emit target
The highest fit_score wins. Emit a one-line rationale citing the top 3 scoring features and the time needed to reposition.
3. Emit positioning notes
For the target prize, list 3-5 things to do in the next 30 minutes that maximize the judges perception:
- What to say in the first 10 seconds (opening hook).
- Which feature to demo first.
- Which technical detail to mention for this prizes judges.
- Which line of the README to highlight.
Show full SKILL.md (185 more words)Show less
4. Emit anti-targets
For the bottom 1-2 prizes, name them and explain why they are a bad fit (so the team is not tempted by their prize pool).
Output contract
Files written:
.hackathon/state/prize.json(NEW schema, seesrc/state/schemas/prize.schema.json).hackathon/artifacts/prize-strategy.md(human-readable positioning doc)
Acceptance criteria
- Exactly one
target_prizeis named. -
target_prize.fit_scoreis the highest among all prizes. - Positioning notes include at least 3 concrete actions.
- Anti-targets are named with one reason each.
- Score per prize is reproducible (deterministic, no RNG).
Failure modes
| Mode | Behavior |
|---|---|
prizes empty | Refuse; ask the user for the hackathon page URL or copy the prize list. |
demo_goal empty | Refuse; run idea-clarify or scope-knife first. |
| All prizes tie at fit_score 0 | Default to the prize with the largest weight. |
Trigger phrases (for agent intent matching)
- "what prize should we target"
- "which track should we go for"
- "how do we position for X prize"
- "what do judges want"
- "which prize category"
Helper
The skill ships scripts/target.py (Python stdlib only) which implements the fit_score algorithm above end-to-end and writes both prize.json and prize-strategy.md. Run it with:
python3 skills/prize-strategy/scripts/target.py --prizes prizes.json --project plan.json --team-skills python,react --out-dir .hackathonwhere prizes.json is the list of {name, criteria, weight} entries.
© 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/prize-strategy of MAGA2010/hackathon-run.
- SKILL.md
- scripts/target.py
Open the folder on GitHubat commit de3bcfb
Compare with similar skills
Prize Strategy 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Prize Strategy this skillMAGA2010/hackathon-run | 411 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Flutter Cherry Pickflutter/flutter | 179k | — | ~1.8k | Automated safety check: Pass | BSD-3-Clause | |
| Categories Functorsparcadei/Continuous-Claude-v3 | 3.9k | 1 repos | ~468 | Automated safety check: Notes | MIT | |
| Chatbox Pro Cherry-Pick Syncchatboxai/chatbox | 42k | — | ~1.2k | Automated safety check: Pass | GPL-3.0 | |
| Etsy Category Listingbrowser-act/skills | 6.1k | — | ~2k | Automated safety check: Pass | MIT | |
| Category Positioningappeeky/aso-skills | 2.2k | — | ~2.2k | Automated safety check: Pass | MIT |
Similar skills
Categories Functors
parcadei/Continuous-Claude-v3
Problem-solving strategies for categories functors in category theory
Chatbox Pro Cherry-Pick Sync
chatboxai/chatbox
Cherry-picks commits from the chatbox-pro repo into the open chatbox repo, skipping mobile-only files and keeping the open package name.
Etsy Category Listing
browser-act/skills
Etsy category page scraper: given an Etsy category URL (e.g.
Category Positioning
appeeky/aso-skills
When the user wants to choose, change, or evaluate their App Store / Google Play category and subcategory — including primary vs secondary category trade-offs, chart-rank competitive analysis…
Category Narrative Mapper
aaron-he-zhu/aaron-marketing-skills
A skill your agent uses when the user asks to "map the category narrative", "tear down how competitors tell their story", or "find the language conventions in our market"; produces a category…
More from MAGA2010/hackathon-run
All 15 skills in this repoDecision Log
MAGA2010/hackathon-run
Writes every KEEP/CUT/DEFER/PIVOT scope decision into an append-only team log with rationale, author, and timestamp.
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.
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.
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.
Time Box
MAGA2010/hackathon-run
Allocates time across the hackathon lifecycle (idea - scope - build - verify - demo - ship) and warns before each deadline slips.
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.
Questions about Prize Strategy
What does Prize Strategy do?
Picks which prize category a hackathon project should chase and how to position the demo around that prizes judging criteria. Prize Strategy is an agent skill from MAGA2010/hackathon-run. Picks which prize category a hackathon project should chase and how to position the demo around that prizes judging criteria.
How do I install Prize Strategy in Claude Code?
Run `npx skills add MAGA2010/hackathon-run --skill prize-strategy -a claude-code`. Or copy the skill folder (skills/prize-strategy in MAGA2010/hackathon-run) into .claude/skills/prize-strategy in your project. Claude Code loads it when a task matches its description.
How do I install Prize Strategy in Codex?
Run `npx skills add MAGA2010/hackathon-run --skill prize-strategy -a codex`. Or copy the skill folder (skills/prize-strategy in MAGA2010/hackathon-run) into .agents/skills/prize-strategy in your project. Codex loads it when a task matches its description.
Can I use Prize Strategy 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 prize-strategy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prize-strategy, .gemini/skills/prize-strategy, .github/skills/prize-strategy and .opencode/skills/prize-strategy in your project.
What does Prize Strategy need to run?
Going by SKILL.md and its folder, Prize Strategy needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Prize Strategy 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 Prize Strategy 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 Prize Strategy use?
Prize Strategy 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 Prize Strategy 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 Prize Strategy?
Skills that share tags, products or a category with Prize Strategy: Flutter Cherry Pick (flutter/flutter, 179k stars), Categories Functors (parcadei/Continuous-Claude-v3, 3.9k stars), Chatbox Pro Cherry-Pick Sync (chatboxai/chatbox, 42k stars) and Etsy Category Listing (browser-act/skills, 6.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Prize Strategy?
MAGA2010 (a GitHub user) maintains it in MAGA2010/hackathon-run, which has 411 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 7, 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.