Token导航 LogoToken导航TokenDH.com
开发需要联网github未标认证来源可访问许可证需确认审计通过

hackathon-scope-cutter黑客马拉松范围切割机

Agent Skill

hackathon-scope-cutter 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

371

周安装

15

GitHub Stars

1

下载量

116
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:hackathon-scope-cutter(黑客马拉松范围切割机)
来源仓库:https://github.com/bernieweb3/hackathon-ai-devkit
仓库路径:skills/hackathon-scope-cutter
安装命令:
npx skills add https://github.com/bernieweb3/hackathon-ai-devkit --skill hackathon-scope-cutter
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/bernieweb3/hackathon-ai-devkit --skill hackathon-scope-cutter

简介

用于处理 GitHub 仓库、Issue 和 Pull Request 信息,协助代码协作与变更管理。

  • 适合在需要围绕仓库状态或代码变更进行整理时使用,支持多宿主环境。
  • 通过 npx skills add 命令从指定仓库安装,具体用法请参考原始 README。
  • 安装前应确认权限范围、维护状态,并评估是否会触发联网或文件操作。
  • 注意:避免直接执行未经验证的命令,防止误改生产环境代码。

SKILL.md

hackathon-scope-cutter

Goal

Reduce a project's feature set to the minimum viable product (MVP) that can be shipped within the hackathon time limit while preserving demo impact.


Trigger Conditions

Use this skill when:

  • A top idea has been selected and confirmed by hackathon-idea-scoring
  • A feature wishlist exists and must be reduced to a shippable set
  • The hackathon duration and team size are known
  • The team is at risk of building too much and shipping nothing
  • Invoked once per project, immediately after idea selection; output is an upstream dependency for planning, implementation, and presentation skills

Inputs

InputTypeRequiredDescription
project_titlestringYesName of the selected project
feature_wishliststring[]YesFull desired feature list
core_mechanismstringYesThe single mechanism the project must demonstrate
hackathon_duration_hoursintegerYesTotal hours available
team_sizeintegerYesNumber of team members
team_skillsstring[]YesTechnologies the team can use effectively
wow_factorstringYesWhat must land for judges to be impressed

Outputs

OutputDescription
mvp_featuresFeatures included in the MVP
deferred_featuresFeatures cut from MVP (post-hackathon backlog)
cut_rationaleWhy each deferred feature was cut
mvp_demo_flowMinimal user journey that demonstrates core value
time_budgetRough hour estimate per MVP feature
scope_riskRemaining risks even after scoping
recommended_skillsSuggested next skills to invoke

Rules

  1. Include a feature in MVP only if it is required to demonstrate core_mechanism or wow_factor.
  2. Default to cutting any feature that cannot be implemented in less than 20% of total time.
  3. Preserve at least one visually compelling UI moment in mvp_demo_flow.
  4. Total time_budget must not exceed 70% of hackathon_duration_hours (reserve 30% for polish and presentation).
  5. Mark features as [FAKE-OK] if they can be simulated or hardcoded for demo purposes.
  6. Do not cut the feature that delivers wow_factor.

Output Format

mvp_features:
  - feature: "<name>"
    purpose: "<why it's essential>"
    fake_ok: <true|false>

deferred_features:
  - feature: "<name>"
    cut_rationale: "<reason>"

mvp_demo_flow:
  - step: <number>
    action: "<user action>"
    outcome: "<visible result>"

time_budget:
  - feature: "<name>"
    estimated_hours: <number>

scope_risk:
  - "<risk>"

recommended_skills:
  - "<skill-name>"

Example

Input:

project_title: "AnchorAI"
feature_wishlist:
  - "User authentication and profiles"
  - "GPT-4 emotional check-in conversation"
  - "Session memory (recall past conversations)"
  - "Mood trend dashboard"
  - "Push notifications for daily check-ins"
  - "Crisis escalation to hotline resources"
  - "Onboarding quiz to personalize tone"
core_mechanism: "GPT-4 conversation with persistent emotional context memory"
hackathon_duration_hours: 24
team_size: 3
team_skills: ["Python", "React", "OpenAI API"]
wow_factor: "AI recalls emotional context from past sessions and adapts tone in real time"

Output:

mvp_features:
  - feature: "GPT-4 emotional check-in conversation"
    purpose: "Core mechanism — must ship"
    fake_ok: false
  - feature: "Session memory (recall past conversations)"
    purpose: "Delivers the wow factor"
    fake_ok: false
  - feature: "Crisis escalation to hotline resources"
    purpose: "Safety requirement visible to judges"
    fake_ok: true

deferred_features:
  - feature: "User authentication and profiles"
    cut_rationale: "3–4h cost; demo uses single hardcoded session"
  - feature: "Mood trend dashboard"
    cut_rationale: "Not in demo flow; 4h cost"
  - feature: "Push notifications"
    cut_rationale: "Backend complexity; irrelevant to live demo"
  - feature: "Onboarding quiz"
    cut_rationale: "Can be mocked with pre-set tone for demo"

mvp_demo_flow:
  - step: 1
    action: "User opens app and types: 'I'm feeling really overwhelmed today'"
    outcome: "AI responds empathetically with personalized opening"
  - step: 2
    action: "User describes a recurring work stress"
    outcome: "AI references last week's similar conversation from memory"
  - step: 3
    action: "User expresses hopelessness"
    outcome: "AI surfaces crisis resource card gracefully"

time_budget:
  - feature: "GPT-4 check-in conversation"
    estimated_hours: 4
  - feature: "Session memory"
    estimated_hours: 5
  - feature: "Crisis escalation (mocked)"
    estimated_hours: 1

scope_risk:
  - "Memory retrieval latency may degrade demo experience on slow networks"

recommended_skills:
  - "hackathon-task-planner"
  - "hackathon-wow-detector"

Context Files

Knowledge Base

  • knowledge/hackathon-mvp-strategy.md
  • knowledge/hackathon-common-failures.md
  • knowledge/hackathon-winning-patterns.md
  • knowledge/hackathon-demo-patterns.md

Playbooks

  • playbooks/hackathon-workflow.md
  • playbooks/24h-hackathon-playbook.md
  • playbooks/36h-hackathon-playbook.md
  • playbooks/48h-hackathon-playbook.md

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.31%
按下载量换算41

Claude

31.99%
按下载量换算37

Cursor

18.84%
按下载量换算22

Gemini CLI

10.3%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills