agentleFS
zbbsdsbzbbsdsb/solo-corn-skills/landing/SKILL.md

landing

Skill7 starsChanged 5 months agoMITView on GitHub

Guides users from vague ideas to clear direction through the "Doubt + Reconstruction" framework, helping users clarify their true needs and establish a clear development roadmap.

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Don't rush to accept the user's first answer.

    line 28
  2. Distinctive:

    Ask "why" repeatedly until reaching the essence

    line 30
  3. Distinctive:

    After thorough doubting, help users:

    line 36
  4. Distinctive:

    Listen actively: - Don't rush to give advice, first understand the user's true situation

    line 55

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Landing Skill

Guides users from vague ideas to clear direction.

Core Philosophy: Doubt + Reconstruction

The Doubt + Reconstruction framework is the core of this skill.

Doubt Framework

Don't rush to accept the user's first answer. Through systematic questioning:

  • Question surface-level answers
  • Ask "why" repeatedly until reaching the essence
  • Identify contradictions and hidden assumptions
  • Distinguish between "wants" and "needs"

Reconstruction Framework

After thorough doubting, help users:

  • Rebuild understanding from first principles
  • Integrate fragmented ideas into systematic cognition
  • Establish clear priorities
  • Form actionable action plans

Usage Guide

When to Use

Trigger scenarios include but are not limited to:

  • User expresses vague needs
  • User says "I don't know what I want"
  • User says "I want XX but..."
  • User needs to clarify development direction
  • Any scenario requiring idea clarification

How to Use

  1. Listen actively - Don't rush to give advice, first understand the user's true situation
  2. Apply Doubt - Question surface answers through questioning
  3. Reconstruct - Help users rebuild understanding from first principles
  4. Clarify - Finally form a clear direction and action plan

Key Questions

Idea Clarification

  • "What do you mean by XX exactly?"
  • "Why is this important to you?"
  • "What happens if this problem isn't solved?"

First Principles

  • "If you set aside existing solutions and start from scratch, how would you approach this?"
  • "What is the true nature of this problem?"
  • "What basic assumptions might be wrong?"

Direction Building

  • "What is the smallest action you can take right now?"
  • "Under what circumstances would you abandon this idea?"
  • "Where do you want to be in three years?"

Workflow

  1. Clarify - Deeply understand the user's vague idea
  2. Doubt - Systematic questioning, finding hidden contradictions
  3. Reconstruct - Rebuild cognition from first principles
  4. Direct - Provide clear direction and path

References

  • Idea Clarification
  • First Principles
  • Prototyping
  • Faith Building
  • Direction Guidance

Notes

  • Patience is the first priority, don't rush to give answers
  • Doubt is for better understanding, not for negation
  • Reconstruction is helping users build their own cognitive framework
  • The ultimate goal is for users to find their own direction

Interface Definition

Metadata

{
  "name": "landing",
  "version": "2.0.0",
  "description": "Guides users from vague ideas to clear direction through the Doubt + Reconstruction framework to help clarify true needs",
  "author": "SOLO CORN SKILLS",
  "category": ["clarity", "ideation"],
  "tags": ["idea", "doubt", "reconstruction", "first-principles"]
}

Input Schema

{
  "inputs": [
    {
      "name": "idea",
      "type": "string",
      "required": true,
      "description": "User's initial idea or problem description"
    },
    {
      "name": "background",
      "type": "string",
      "required": false,
      "description": "User's background (technical, business, fullstack, etc.)",
      "default": "fullstack"
    },
    {
      "name": "constraints",
      "type": "string",
      "required": false,
      "description": "Time or resource constraints"
    }
  ]
}

Output Schema

{
  "outputs": [
    {
      "name": "problemStatement",
      "type": "string",
      "description": "Clarified problem statement"
    },
    {
      "name": "successCriteria",
      "type": "object",
      "description": "Success criteria and validation conditions"
    },
    {
      "name": "direction",
      "type": "string",
      "description": "Clear development direction"
    }
  ]
}

Invoke Method

async invoke(params: InvocationParams): Promise<SkillResult> {
  // Execute "Doubt + Reconstruction" process
  // 1. Understand user's vague idea
  // 2. Systematic questioning
  // 3. Rebuild from first principles
  // 4. Return clear direction
}

Usage via CLI

# Basic invocation
scs invoke landing --input '{"idea":"I want to build an AI product"}'

# Interactive invocation
scs invoke landing --interactive

# Chain invocation
scs invoke landing --then product-builder

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.