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

Idea Clarify

by MAGA2010 in MAGA2010/hackathon-run

Surfaces what the user actually wants when the repo is empty or the request is one paragraph of vibes.

MITAuto-check passed

Install Idea Clarify

skills CLI
$ npx skills add MAGA2010/hackathon-run --skill idea-clarify -a claude-code

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

GitHub CLI
$ gh skill install MAGA2010/hackathon-run idea-clarify --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/idea-clarify .claude/skills/idea-clarify && 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
idea-clarify
GitHub stars
390
Token cost
~929 tokens
SKILL.md length
360 words
Files
2 (incl. references)
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Surfaces what the user actually wants when the repo is empty or the request is one paragraph of vibes.

  • Works in 3 steps: Surface the problem → Detect contradictions → Emit a one-page brief
  • SKILL.md covers Input contract, Execution, Output contract and Acceptance criteria, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Idea Clarify is an agent skill from MAGA2010/hackathon-run. Surfaces what the user actually wants when the repo is empty or the request is one paragraph of vibes. Use before scope-knife on empty repos or vague briefs; do not invoke after a plan exists.

Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/idea-clarify-examples.md`).

The licence is MIT.

Example prompts

  • “Use the idea-clarify skill to surface what the user actually wants when the repo is empty or the request is one paragraph of vibes”
  • “/idea-clarify”

Workflow steps

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

  1. Surface the problem
  2. Detect contradictions
  3. Emit a one-page brief

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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Idea Clarify loads about 929 tokens when it runs, and up to ~1.2k if it reads all its reference files. Until then it costs about 51 tokens; SKILL.md has 360 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~929
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.2k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from MAGA2010/hackathon-run at commit de3bcfb, republished under its MIT licence (© MAGA2010). 360 words, ~929 tokens.

Download SKILL.mdSave it as .claude/skills/idea-clarify/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
idea-clarify
description
Surfaces what the user actually wants when the repo is empty or the request is one paragraph of vibes. Use before scope-knife on empty repos or vague briefs; do not invoke after a plan exists.
when_to_use
Trigger when scope-knife refuses to run because the repo is empty, the idea is too vague, or the user gave a one-paragraph brief. Run as a pre-step to…
version
1
category
scoping
tags
empty-repo, vague-brief, pre-scope
triggers
we have no idea, what are we building, empty repo, vague brief, scope is unclear

idea-clarify

When a team shows up with an empty repo and a sentence, the problem is not "we have no features". It's "we have no shared picture of what we're building." This skill forces that picture into the open.

Input contract

Required:

  • user_brief: the raw one-paragraph description from the user
  • audience: who the demo is for (judges, customers, internal team)

Optional:

  • time_remaining_minutes: integer >= 0 (default 36 * 60)
  • prior_artifacts: list of any pre-existing notes, sketches, links

Execution

1. Surface the problem

Ask the user the four canonical questions:

#QuestionWhy it matters
1Who is the user and what are they trying to do?defines the value prop
2What does success look like at the demo?locks the demo_path later
3What's the smallest thing we can show that proves the idea works?prevents over-building
4What's the one thing we cannot ship without?forces a hard priority

Refuse to proceed until each answer is at least one concrete sentence.

2. Detect contradictions

If two answers contradict (e.g. "we want ML" + "no ML allowed"), surface the contradiction. Do not silently pick one. The agent must resolve it before scope-knife runs.

3. Emit a one-page brief

Write .hackathon/artifacts/idea-brief.md with:

  • the four answers verbatim
  • any contradictions + how the agent resolved them
  • a one-line demo_goal candidate
  • a one-line mvp_axis (the smallest axis along which the MVP can grow)
Show full SKILL.md (135 more words)Show less

Output contract

Files written:

  • .hackathon/artifacts/idea-brief.md (human-readable, one page)

This skill does NOT write to .hackathon/state/*.json directly. It is a pre-scope-knife step; scope-knife reads the brief and writes plan.json from it.

Acceptance criteria

  • The four canonical questions are asked exactly once.
  • Contradictions are surfaced, not silently resolved.
  • demo_goal is a single sentence (max 20 words).
  • mvp_axis is a single noun phrase.
  • .hackathon/artifacts/idea-brief.md exists and is <= 1 page.

Failure modes

ModeBehavior
User gives one-word answerAsk again, refuse to guess
User refuses to answerSurface as contradiction; refuse to proceed
Contradiction detectedBlock until resolved
Time < 1hSkip step 1 questions; ask 3 + 4 only

Trigger phrases (for agent intent matching)

  • "we have an empty repo"
  • "what should we build"
  • "the brief is one paragraph"
  • "we have an idea but no plan"
  • "idea is too vague"

© 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 (references) in skills/idea-clarify of MAGA2010/hackathon-run.

  • SKILL.md
  • references/idea-clarify-examples.md

Open the folder on GitHubat commit de3bcfb

Compare with similar skills

Idea Clarify 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.

Idea Clarify compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Idea Clarify this skillMAGA2010/hackathon-run390—~929Automated safety check: PassMIT
Idea Darwinsickn33/agentic-awesome-skills47k2 repos~1.1kAutomated safety check: PassMIT
Idea Ossickn33/agentic-awesome-skills47k1 repos~1.5kAutomated safety check: PassMIT
Idea Refinementaddyosmani/agent-skills103k6 repos~2kAutomated safety check: PassMIT
Workspace Surface Auditaffaan-m/ECC276k3 repos~1.3kAutomated safety check: NotesMIT
Same Idea Both Platformssickn33/agentic-awesome-skills47k1 repos~1.4kAutomated safety check: PassMIT

Similar skills

  • Idea Darwin

    sickn33/agentic-awesome-skills

    Darwinian idea evolution engine — toss rough ideas onto an evolution island, let them compete, crossbreed, and mutate through structured rounds to surface your strongest concepts.

    47k GitHub starsUsed in 2 repos~1.1k tokens
    Auto-check passed

  • Idea Os

    sickn33/agentic-awesome-skills

    Five-phase pipeline (triage → clarify → research → PRD → plan) that turns a raw idea into four linked files: clarifying questions, deep research, a PRD with non-goals and metrics, and a phased…

    47k GitHub starsUsed in 1 repo~1.5k tokens
    Product & Project ManagementAuto-check passed

  • Idea Refinement

    addyosmani/agent-skills

    Guides a conversation that takes a vague idea through divergent and convergent thinking and ends in a markdown one-pager covering scope and assumptions.

    103k GitHub starsUsed in 6 repos~2k tokens
    Agent WorkflowsAuto-check passed

  • Workspace Surface Audit

    affaan-m/ECC

    Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows.

    276k GitHub starsUsed in 3 repos~1.3k tokens
    Agent WorkflowsAuto-check: notes

  • Same Idea Both Platforms

    sickn33/agentic-awesome-skills

    Write one idea as a Twitter/X post and a LinkedIn post that read as written separately, not pasted twice.

    47k GitHub starsUsed in 1 repo~1.4k tokens
    Writing & ContentAuto-check passed

  • Idea Evaluator

    sickn33/agentic-awesome-skills

    Evaluates an idea by hosting a multi-turn debate between a Pro and Con agent, delivering a final verdict on whether it's worth pursuing.

    47k GitHub starsUsed in 1 repo~930 tokens
    Auto-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.

    390 GitHub stars~847 tokensUpdated 2 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.

    390 GitHub stars~895 tokensUpdated 2 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.

    390 GitHub stars~970 tokensUpdated 2 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.

    390 GitHub stars~1.3k tokensUpdated 2 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.

    390 GitHub stars~1.3k tokensUpdated 2 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.

    390 GitHub stars~893 tokensUpdated 2 days ago
    Auto-check passed

Questions about Idea Clarify

What does Idea Clarify do?

Surfaces what the user actually wants when the repo is empty or the request is one paragraph of vibes. Idea Clarify is an agent skill from MAGA2010/hackathon-run. Surfaces what the user actually wants when the repo is empty or the request is one paragraph of vibes.

How do I install Idea Clarify in Claude Code?

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

How do I install Idea Clarify in Codex?

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

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

What does Idea Clarify need to run?

SKILL.md names no scripts, command-line tools or credentials: Idea Clarify is instructions for the agent only.

Does Idea Clarify 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 Idea Clarify 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. Review the folder before installing.

What licence does Idea Clarify use?

Idea Clarify 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 Idea Clarify use?

About 929 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 263 tokens, read only when the agent opens those files.

What are the alternatives to Idea Clarify?

Skills that share tags, products or a category with Idea Clarify: Idea Darwin (sickn33/agentic-awesome-skills, 47k stars), Idea Os (sickn33/agentic-awesome-skills, 47k stars), Idea Refinement (addyosmani/agent-skills, 103k stars) and Workspace Surface Audit (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Idea Clarify?

MAGA2010 (a GitHub user) maintains it in MAGA2010/hackathon-run, which has 390 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.