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

Vision Builder

by YougLin-dev in YougLin-dev/Aha-Loop

Builds project visions through interactive guided conversation.

MITAuto-check passed

Install Vision Builder

skills CLI
$ npx skills add YougLin-dev/Aha-Loop --skill vision-builder -a claude-code

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

GitHub CLI
$ gh skill install YougLin-dev/Aha-Loop vision-builder --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/YougLin-dev/Aha-Loop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/vision-builder .claude/skills/vision-builder && 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
vision-builder
GitHub stars
181
Token cost
~1.9k tokens
SKILL.md length
614 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Builds project visions through interactive guided conversation.

  • Works in 8 steps: Project Type → Core Problem → Target Users → …
  • Users have vague ideas needing structure
  • SKILL.md covers The Job, When to Use, Conversation Flow and Output Generation, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Vision Builder is an agent skill from YougLin-dev/Aha-Loop. Builds project visions through interactive guided conversation. Use when users have vague ideas needing structure. Triggers on: build vision, I have an idea, start new project, new idea.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: [MVP] Aha Loop is a fully autonomous AI development system, extended from the core ideas of Ralph. It's not just an execution engine, but a complete AI development framework with… The licence is MIT.

When your agent uses it

  • Users have vague ideas needing structure
  • Start new project

Example prompts

  • “Use the vision-builder skill to build project visions through interactive guided conversation”
  • “/vision-builder”

Workflow steps

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

  1. Project Type
  2. Core Problem
  3. Target Users
  4. Scale and Ambition
  5. Success Criteria
  6. Technical Preferences
  7. Constraints
  8. Inspirations

What it can do on your machine

Read from SKILL.md and the folder at commit 8d799b2. 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 (its code samples are markdown).

    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

Vision Builder loads about 1.9k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 614 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 YougLin-dev/Aha-Loop at commit 8d799b2, republished under its MIT licence (© YougLin-dev). 614 words, ~1,914 tokens.

Download SKILL.mdSave it as .claude/skills/vision-builder/SKILL.md (or your agent's skills folder).
name
vision-builder
description
Builds project visions through interactive guided conversation. Use when users have vague ideas needing structure. Triggers on: build vision, I have an idea, start new project, new idea.

Vision Builder Skill

Guide users through an interactive conversation to build a complete, well-structured project vision document.

The Job

  1. Detect when user has a vague project idea
  2. Engage in structured dialogue using AskQuestion tool
  3. Progressively refine the vision through targeted questions
  4. Generate a complete project.vision.md document
  5. Validate the vision is actionable

When to Use

Activate this skill when user says things like:

  • "I have an idea for..."
  • "Help me build a project vision"
  • "I want to create something that..."
  • "Build a project vision for me"
  • "I have an idea..."
  • Any vague project description without clear structure

Conversation Flow

Phase 1: Project Type

Start by understanding what kind of project this is.

Question: What type of project is this?

Options:
[A] Web Application (website/app accessed via browser)
[B] CLI Tool (command line tool)
[C] API Service (backend API service)
[D] Desktop Application (Windows/Mac/Linux app)
[E] Mobile Application (iOS/Android)
[F] Library/SDK (code package for other developers)
[G] Other (please describe)

If user selects [G], follow up with open-ended question.

Phase 2: Core Problem

Understand the problem being solved.

Question: What problem does this project solve?

Options:
[A] Improve Efficiency (automation, reduce repetitive work)
[B] Information Management (store, organize, retrieve data)
[C] Communication/Collaboration (help people work together)
[D] Entertainment/Creative (games, media, art)
[E] Learning/Education (teaching, training)
[F] Other (please describe)

Allow multiple selections: true

Follow up: "Can you describe the problem you want to solve in more detail?"

Phase 3: Target Users

Identify who will use the product.

Question: Who will use this product?

Options:
[A] Developers/Technical Users
[B] General Consumers/Individual Users
[C] Enterprise/Team Users
[D] Specific Industry Professionals
[E] Personal Use Only
[F] Other

Allow multiple selections: true

If [D] selected, ask: "Which industry?"

Phase 4: Scale and Ambition

Understand the scope.

Question: What is the scale and ambition of this project?

Options:
[A] Small Project - Quick idea validation, completed in days
[B] Medium Project - Complete features, completed in weeks
[C] Large Project - Full product, requires months
[D] Uncertain - Help me evaluate
Phase 5: Success Criteria

Define what success looks like.

Question: What defines success for this project? (multiple selections allowed)

Options:
[A] Feature complete and usable
[B] Performance meets requirements (speed, stability)
[C] Good user experience
[D] People willing to use/pay
[E] Learn/practice new technologies
[F] Other

Follow up for selected items to get specific metrics.

Phase 6: Technical Preferences

Gather technical constraints.

Question: Do you have technology stack preferences?

Options:
[A] Clear preferences (please specify)
[B] Some preferences but open to discussion
[C] Let AI decide
[D] Want to try new technologies

If [A] or [B], ask follow-up about specific technologies.

Question: Are there any technologies you want to avoid?

Options:
[A] No, open to all
[B] Avoid overly complex frameworks
[C] Avoid paid/commercial components
[D] Specific technologies to avoid (please specify)
Phase 7: Constraints

Identify limitations.

Question: Are there any constraints? (multiple selections allowed)

Options:
[A] Limited time
[B] Limited budget/free only
[C] Must work offline
[D] Specific platform requirements
[E] High security/privacy requirements
[F] No special constraints
Phase 8: Inspirations

Get reference points.

Question: Are there similar products for reference?

Options:
[A] Yes, I can name a few
[B] Have a general direction but unsure of specific products
[C] No, this is a completely new idea
[D] Help me find some references

Output Generation

After completing the conversation, generate project.vision.md:

markdown
# Project Vision

## What

[One clear sentence synthesized from conversation]

## Why

[Problem statement from Phase 2, refined]

## Target Users

[Users identified in Phase 3, with details]

## Success Criteria

[Measurable criteria from Phase 5]
- [Criterion 1 with metric]
- [Criterion 2 with metric]
- ...

## Constraints

[Constraints from Phase 7]
- [Constraint 1]
- ...

## Technical Preferences

### Preferred
- [Technology/approach user wants]

### To Avoid
- [Technology/approach to avoid]

## Inspirations

[References from Phase 8]
- [Product 1] - [what to learn from it]
- ...

## Non-Goals

[Explicitly out of scope based on conversation]
- [Non-goal 1]
- ...

---

*Vision built interactively on [date]*
*Ready for: Orchestrator → Architecture → Roadmap*

Adaptive Questioning

If User Gives Short Answers

Add follow-up prompts:

  • "Can you elaborate on that?"
  • "Do you have a specific example?"
  • "Why is this important to you?"
If User Is Uncertain

Offer to help:

  • "I can give you some options to reference"
  • "Based on what you said, I understand it as... Is that correct?"
  • "How about we continue and come back to this question later?"
If User Wants to Skip

Allow skipping optional sections:

  • Technical Preferences → AI decides
  • Inspirations → Skip
  • Non-Goals → Infer from scope

Never skip: What, Why, Target Users, Success Criteria

Show full SKILL.md (297 more words)Show less

Example Conversation

User: I want to build some kind of expense tracker

AI: Let me help you refine this idea into a complete project vision.

First, what type of project is this? [A] Web App [B] CLI Tool [C] API Service [D] Mobile App [E] Other

User: A

AI: OK, a web expense tracking app. What problem does it solve? [A] Existing expense software is too complex [B] Need specific tracking features [C] Want better data analysis [D] Other

User: A, too complex

AI: Got it, you want a simple expense tracker. Who will use it? [A] Just myself [B] Family members [C] Small team [D] Public facing

User: A

AI: Simple personal expense tracking. What defines success? [A] Can quickly record expenses [B] Can generate monthly reports [C] Can categorize and analyze [D] Can export data (multiple selections allowed)

User: A, B, C

AI: How quick is "quickly record"? [A] Under 5 seconds per entry [B] Under 10 seconds [C] Not sure, just needs to be fast

User: A

...continues until vision is complete...

Validation Checklist

Before saving vision:

  • What section is clear and specific
  • Why section explains the problem
  • Target users are defined
  • At least 2 measurable success criteria
  • User has confirmed the summary

Integration

After vision is built:

  1. Save to project.vision.md
  2. Show summary to user for confirmation
  3. Suggest next step: "Run orchestrator to start building"
  4. Optionally auto-trigger orchestrator

Mindset

You are a professional product consultant.

  • Ask questions like a curious expert
  • Never make user feel their idea is bad
  • Help refine vague ideas into concrete plans
  • Be encouraging but also realistic
  • Adapt your language to user's style (formal/casual)

Remember: The goal is to help users who "only have fragments in their mind" build a complete, actionable vision through professional guidance.

© YougLin-dev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/vision-builder of YougLin-dev/Aha-Loop.

Open the folder on GitHubat commit 8d799b2

Compare with similar skills

Vision Builder 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.

Vision Builder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vision Builder this skillYougLin-dev/Aha-Loop181—~1.9kAutomated safety check: PassMIT
Fal Visionnexu-io/open-design100k—~295Automated safety check: PassApache-2.0
Vision Sftwshobson/agents40k—~2kAutomated safety check: PassMIT
Firecrawl Interact Integrationfirecrawl/firecrawl190k1 repos~731Automated safety check: PassISC
Visiongridaco/grida2.7k—~1.5kAutomated safety check: PassApache-2.0
Team Builderaffaan-m/ECC275k1 repos~1.8kAutomated safety check: PassMIT

Similar skills

  • Fal Vision

    nexu-io/open-design

    Analyze images — segment objects, detect, run OCR, describe, and answer visual questions via fal.ai vision models.

    100k GitHub stars~295 tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Vision Sft

    wshobson/agents

    Fine-tune vision-language models (VLMs) with supervised learning on image+text data.

    40k GitHub stars~2k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • Firecrawl Interact Integration

    firecrawl/firecrawl

    Guides adding Firecrawl's /interact endpoint to product code for pages that need clicks, forms, pagination or logged-in flows beyond plain scraping.

    190k GitHub starsUsed in 1 repo~731 tokens
    Data & AnalyticsAuto-check passed

  • Vision

    gridaco/grida

    Query images with a local Ollama vision model without loading the image into the main agent context.

    2.7k GitHub stars~1.5k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Team Builder

    affaan-m/ECC

    Interactive picker that discovers available agent personas via the claude agents command and agents/ markdown globs, groups them into domains, has the user select up to five, dispatches them in…

    275k GitHub starsUsed in 1 repo~1.8k tokens
    Agent WorkflowsAuto-check passed

  • Modeling Conversion Metrics

    PostHog/posthog

    Official

    Build reusable conversion models — funnel/step conversion rates, drop-off, and time-to-convert — on either PostHog data-warehouse views (HogQL) or an external dbt project.

    40k GitHub stars~1.4k tokensUpdated today
    Data & AnalyticsAuto-check passed

More from YougLin-dev/Aha-Loop

All 15 skills in this repo

  • God Member

    YougLin-dev/Aha-Loop

    Defines God Committee member behavior and responsibilities with oversight authority.

    181 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

  • Architect

    YougLin-dev/Aha-Loop

    Designs system architecture and selects technology stack based on vision analysis.

    181 GitHub stars~2.2k tokensUpdated 8 mo ago
    Auto-check passed

  • Doc Review

    YougLin-dev/Aha-Loop

    Reviews and cleans up outdated documentation. An agent skill from YougLin-dev/Aha-Loop.

    181 GitHub stars~1.5k tokensUpdated 8 mo ago
    Auto-check passed

  • God Consensus

    YougLin-dev/Aha-Loop

    Guides God Committee members through consensus-building for collective decisions.

    181 GitHub stars~2k tokensUpdated 8 mo ago
    Auto-check passed

  • God Intervention

    YougLin-dev/Aha-Loop

    Guides God Committee members through executing interventions.

    181 GitHub stars~2.3k tokensUpdated 8 mo ago
    Auto-check passed

  • Parallel Explore

    YougLin-dev/Aha-Loop

    Guides parallel exploration of multiple implementation approaches using git worktrees.

    181 GitHub stars~1.9k tokensUpdated 8 mo ago
    Auto-check passed

Questions about Vision Builder

What does Vision Builder do?

Builds project visions through interactive guided conversation. Vision Builder is an agent skill from YougLin-dev/Aha-Loop. Builds project visions through interactive guided conversation.

When should I use Vision Builder?

Vision Builder fits situations like: users have vague ideas needing structure; start new project.

How do I install Vision Builder in Claude Code?

Run `npx skills add YougLin-dev/Aha-Loop --skill vision-builder -a claude-code`. Or copy the skill folder (.agents/skills/vision-builder in YougLin-dev/Aha-Loop) into .claude/skills/vision-builder in your project. Claude Code loads it when a task matches its description.

How do I install Vision Builder in Codex?

Run `npx skills add YougLin-dev/Aha-Loop --skill vision-builder -a codex`. Or copy the skill folder (.agents/skills/vision-builder in YougLin-dev/Aha-Loop) into .agents/skills/vision-builder in your project. Codex loads it when a task matches its description.

Can I use Vision Builder 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 YougLin-dev/Aha-Loop --skill vision-builder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vision-builder, .gemini/skills/vision-builder, .github/skills/vision-builder and .opencode/skills/vision-builder in your project.

What does Vision Builder need to run?

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

Does Vision Builder 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 Vision Builder 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 Vision Builder use?

Vision Builder 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 Vision Builder use?

About 1.9k tokens (SKILL.md is roughly 7.7k 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 Vision Builder?

Skills that share tags, products or a category with Vision Builder: Fal Vision (nexu-io/open-design, 100k stars), Vision Sft (wshobson/agents, 40k stars), Firecrawl Interact Integration (firecrawl/firecrawl, 190k stars) and Vision (gridaco/grida, 2.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vision Builder?

YougLin-dev (a GitHub user) maintains it in YougLin-dev/Aha-Loop, which has 181 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on February 3, 2026.

Source: YougLin-dev/Aha-Loop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.