New: 98,000+ 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

Scope Knife

by MAGA2010 in 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.

MITAuto-check passedAgent Workflows

Install Scope Knife

skills CLI
$ npx skills add MAGA2010/hackathon-run --skill scope-knife -a claude-code

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

GitHub CLI
$ gh skill install MAGA2010/hackathon-run scope-knife --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/scope-knife .claude/skills/scope-knife && 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
scope-knife
GitHub stars
367
Token cost
~1.3k tokens
SKILL.md length
507 words
Files
3 (incl. scripts)
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 5 steps: Scan repo → Compute pressure → Force classification → …
  • Producing the minimum demo path and a next-steps task list
  • SKILL.md covers Input contract, Execution, Helper and Output contract, plus 3 more sections
  • Runs Python scripts from its folder

What it does

Scope Knife is an agent skill from 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. Use for producing the minimum demo path and a next-steps task list.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/classify.py` and `scripts/scan_repo.py`).

It sits in Agent Workflows, covering Task breakdown. The licence is MIT.

When your agent uses it

  • Producing the minimum demo path and a next-steps task list
  • Tasks that involve Task breakdown

Example prompts

  • “Use the scope-knife skill to force a KEEP, CUT, or DEFER decision on every feature when scope is too large, no MVP consensus exists, or time is…”
  • “/scope-knife”

Requirements

  • Python 3

Workflow steps

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

  1. Scan repo
  2. Compute pressure
  3. Force classification
  4. Demo path
  5. Task list

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 2 files 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

Scope Knife loads about 1.3k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 507 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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). 507 words, ~1,330 tokens.

Download SKILL.mdSave it as .claude/skills/scope-knife/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
scope-knife
description
Forces a KEEP, CUT, or DEFER decision on every feature when scope is too large, no MVP consensus exists, or time is running out. Use for producing the minimum demo path and a next-steps task list.
when_to_use
Trigger when the user has too many ideas, the feature list is long, the team has no MVP consensus, time is running out, or any skill invocation fails because…
version
1
category
scoping
tags
keep-cut-defer, mvp, demo-path
side_effects
plan
triggers
scope is too big, too many features, no MVP consensus, time is running out, trim the scope, force a keep cut or defer decision, classify the features

scope-knife

Input contract

Required:

  • repo_root: path to current project root
  • time_remaining_minutes: integer (>= 0)
  • demo_goal: one-sentence string ("what should judges see at the end?")

Optional:

  • .hackathon/state/plan.json (load if exists)
  • features: array (else inferred from repo scan)

Execution

1. Scan repo

Run scripts/scan_repo.py <repo_root> to produce a feature inventory:

StatusMeaning
implementedCode present, tests pass
half-implementedCode exists but incomplete or tests failing
unimplementedIn README/plan only
brokenWas working, now failing
2. Compute pressure

Based on time_remaining_minutes:

Time leftMinimum CUT rate
> 6hwarn if < 30%
3–6henforce >= 50%
1–3henforce >= 70%
< 1henforce >= 90% (demo path only)
3. Force classification

For every feature: KEEP / CUT / DEFER.

Hard rules:

  • Cannot mark all features as KEEP.
  • Features off the demo path default to CUT or DEFER.
  • If user insists all-KEEP, refuse, output pressure calc, ask again.
4. Demo path

Linear sequence: open URL → trigger core action → see result → understand value.

Every feature is written to plan.json with passes: false, acceptance_criteria, and an empty evidence array. This is the default-FAIL contract: no feature is considered done until an evaluator flips passes to true with machine-checkable evidence. Scope-knife itself never marks a feature passing.

Acceptance criteria must describe user-visible end-to-end behavior, not an implementation detail. Example: "A user can open the app, sign up, save a note, and see it in the list." If a criterion can be checked only by reading source code, rewrite it as a behavior a judge could reproduce.

5. Task list

Priorities:

  1. P0: critical path (cannot demo without)
  2. P1: demo polish
  3. P2: nice-to-haves (skip if time runs out)
Show full SKILL.md (235 more words)Show less

Helper

The skill ships scripts/classify.py (Python stdlib only). It reads a features inventory, applies the pressure table, and emits .hackathon/state/plan.json. The CLI now supports WSJF tie-breaking:

python3 skills/scope-knife/scripts/classify.py --inventory features.json --demo-goal user_signup --time-remaining 180 --enable-wsjf

When --enable-wsjf is set, every feature should carry WSJF inputs:

  • user_business_value (1-10, what it earns you in the demo)
  • time_criticality (1-10, will it hurt to ship without it?)
  • risk_reduction (1-10, does it de-risk the demo?)
  • job_size (1-10, person-hours to build)

wsjf_score = (user_business_value + time_criticality + risk_reduction) / job_size

Off-demo-path features are sorted by WSJF before KEEP vs CUT vs DEFER is decided, so high-WSJF non-path features can be DEFERred rather than CUT when time pressure lets you.

Output contract

Files written:

  • .hackathon/state/plan.json (matches src/state/schemas/plan.schema.json)
  • .hackathon/artifacts/scope-knife-output.md (human-readable)

Acceptance criteria

  • Outputs KEEP/CUT/DEFER classification for every input feature.
  • Outputs a demo path with at most 5 steps.
  • Outputs a next-steps task list with priorities.
  • Refuses to mark all features as KEEP.
  • CUT rate at least meets the pressure threshold for time_remaining_minutes.
  • plan.json validates against plan.schema.json.
  • Every KEEP feature starts passes: false with at least one acceptance criterion.

Failure modes

ModeBehavior
Empty repoSuggest running idea-clarify first
Missing demo_goalAsk once, refuse to guess
User rejects all cutsOutput pressure calc, ask once more
Schema mismatchFail loud with diff, do not silently coerce

Trigger phrases (for agent intent matching)

  • "I have too many ideas"
  • "the feature list is huge"
  • "no MVP consensus"
  • "what should we cut"
  • "running out of time"
  • "what should judges see"

© 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 2 other files (scripts) in skills/scope-knife of MAGA2010/hackathon-run.

  • SKILL.md
  • scripts/classify.py
  • scripts/scan_repo.py

Open the folder on GitHubat commit de3bcfb

Compare with similar skills

Scope Knife 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.

Scope Knife compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scope Knife this skillMAGA2010/hackathon-run367—~1.3kAutomated safety check: PassMIT
Multi-Role Spec and Task Breakdownmylukin/agent-foreman250—~5.1kAutomated safety check: NotesNone
Wayfinder Planning Mapsrengwu/wayfinder-maps134—~3.5kAutomated safety check: PassMIT
Roadmap Generatoralirezarezvani/claude-cto-team117—~1.9kAutomated safety check: PassMIT
Autospec Tasksariel-frischer/autospec144—~2.5kAutomated safety check: PassMIT
Oma Pmfirst-fluke/oh-my-agent1.3k—~1.7kAutomated safety check: PassMIT

Similar skills

  • Multi-Role Spec and Task Breakdown

    mylukin/agent-foreman

    Runs a requirement through four research-backed specialist agents, a PM, a UX designer, a tech architect and QA, to produce implementable tasks.

    250 GitHub stars~5.1k tokensUpdated 8 mo ago
    Agent WorkflowsAuto-check: notes

  • Wayfinder Planning Maps

    rengwu/wayfinder-maps

    Plans work too big for one agent session as a shared map of investigation tickets, resolved one at a time until the route to the destination is clear.

    134 GitHub stars~3.5k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

  • Roadmap Generator

    alirezarezvani/claude-cto-team

    Generate phased implementation roadmaps with Epic/Story/Task breakdown, effort estimates, and validation checkpoints.

    117 GitHub stars~1.9k tokensUpdated 9 mo ago
    Agent WorkflowsAuto-check passed

  • Autospec Tasks

    ariel-frischer/autospec

    Generate YAML task breakdown from implementation plan. An agent skill from ariel-frischer/autospec.

    144 GitHub stars~2.5k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed

  • Oma Pm

    first-fluke/oh-my-agent

    Product manager that decomposes requirements into actionable tasks with priorities and dependencies.

    1.3k GitHub stars~1.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Plan

    softspark/ai-toolkit

    Breaks features/goals into phased plans with task lists, agent assignments, dependencies.

    179 GitHub stars~1.3k tokensUpdated yesterday
    Agent WorkflowsAuto-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.

    367 GitHub stars~847 tokensUpdated today
    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.

    367 GitHub stars~895 tokensUpdated today
    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.

    367 GitHub stars~970 tokensUpdated today
    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.

    367 GitHub stars~1.3k tokensUpdated today
    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.

    367 GitHub stars~893 tokensUpdated today
    Auto-check passed

  • Pivot

    MAGA2010/hackathon-run

    Detects a mid-build scope change and re-runs scope-knife against the new direction without losing prior progress.

    367 GitHub stars~981 tokensUpdated today
    Auto-check passed

Categories

Questions about Scope Knife

What does Scope Knife do?

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

When should I use Scope Knife?

Scope Knife fits situations like: producing the minimum demo path and a next-steps task list; tasks that involve Task breakdown.

How do I install Scope Knife in Claude Code?

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

How do I install Scope Knife in Codex?

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

Can I use Scope Knife 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 scope-knife -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scope-knife, .gemini/skills/scope-knife, .github/skills/scope-knife and .opencode/skills/scope-knife in your project.

What does Scope Knife need to run?

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

Does Scope Knife 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 Scope Knife 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 Scope Knife use?

Scope Knife 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 Scope Knife use?

About 1.3k tokens (SKILL.md is roughly 5.3k 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 Scope Knife?

Skills that share tags, products or a category with Scope Knife: Multi-Role Spec and Task Breakdown (mylukin/agent-foreman, 250 stars), Wayfinder Planning Maps (rengwu/wayfinder-maps, 134 stars), Roadmap Generator (alirezarezvani/claude-cto-team, 117 stars) and Autospec Tasks (ariel-frischer/autospec, 144 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scope Knife?

MAGA2010 (a GitHub user) maintains it in MAGA2010/hackathon-run, which has 367 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.