scope

Turn ideas into clear, buildable specs for AI tools or stakeholder review. Use when starting features, planning projects, or when AI keeps building the wrong thing. Creates Quick Feature Specs (10-15 min) for immediate AI builds or Full Project Scopes (1-2 hours) for budget planning and contractor estimates.

181 stars

Best use case

scope is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Turn ideas into clear, buildable specs for AI tools or stakeholder review. Use when starting features, planning projects, or when AI keeps building the wrong thing. Creates Quick Feature Specs (10-15 min) for immediate AI builds or Full Project Scopes (1-2 hours) for budget planning and contractor estimates.

Teams using scope should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/1-scope/SKILL.md --create-dirs "https://raw.githubusercontent.com/majiayu000/claude-skill-registry/main/skills/data/1-scope/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/1-scope/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How scope Compares

Feature / AgentscopeStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Turn ideas into clear, buildable specs for AI tools or stakeholder review. Use when starting features, planning projects, or when AI keeps building the wrong thing. Creates Quick Feature Specs (10-15 min) for immediate AI builds or Full Project Scopes (1-2 hours) for budget planning and contractor estimates.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Scope

Turn ideas into specs that AI tools can execute and stakeholders can evaluate.

## When to Use This Skill

- Starting any new feature or product
- Before hiring developers or estimating costs  
- When AI keeps building the wrong thing (unclear spec)
- When stakeholders need to review scope and budget

## Choose Your Approach

**Quick Feature Spec (10-15 minutes)**
- Use for: Single features, iterations, additions
- Give to: AI tools (Claude Code, Lovable, Replit) to build directly
- See: [QUICK-SPEC.md](QUICK-SPEC.md)

**Full Project Scope (1-2 hours)**
- Use for: New products, major releases, stakeholder review
- Give to: Contractors, team members, budget planning
- See: [PROJECT-SCOPE.md](PROJECT-SCOPE.md)

---

## Quick Feature Spec Workflow

Use this checklist and complete each section:

```
Feature Spec Progress:
- [ ] Write what users will do (2-3 sentences)
- [ ] Show what it looks like (reference, screenshot, or description)
- [ ] Define happy path (3-5 steps)
- [ ] List edge cases (2-4 scenarios)
- [ ] Specify out of scope items
- [ ] Save to docs/specs/YYYY-MM-DD-feature-name.md
```

### Section 1: What Users Will Do

Write 2-3 sentences describing user actions and outcomes.

**Template:**
```
Users can [ACTION] to [OUTCOME].
When they [DO THIS], they see [WHAT HAPPENS].
If [EDGE CASE], then [WHAT HAPPENS].
```

**Example:**
```
Users sign up with email/password, receive confirmation email, and log in to 
see their dashboard. They can reset forgotten passwords via email link.
```

### Section 2: What It Looks Like

Pick ONE:
- **Reference app:** "Login like Linear - minimal, centered, email/password/button"
- **Screenshot/sketch:** Quick mockup or phone photo
- **Description:** "Card 400px wide, 'Welcome' header Inter 24px, two inputs, blue button"

### Section 3: Happy Path

List 3-5 steps users take to complete the task.

### Section 4: Edge Cases  

List 2-4 scenarios where things don't go as planned and what happens.

**Format:**
```
- **[Scenario]:** [Response shown to user]
```

### Section 5: Out of Scope

Define what you're NOT building to prevent scope creep.

For complete template and examples, see [QUICK-SPEC.md](QUICK-SPEC.md)

---

## Full Project Scope Workflow

Use this checklist for comprehensive project planning:

```
Project Scope Progress:
- [ ] Write introduction (background, in/out of scope)
- [ ] Define user roles
- [ ] List all pages/screens
- [ ] Describe core features
- [ ] Identify integrations
- [ ] Create milestones with hour estimates
- [ ] Document assumptions and open questions
- [ ] Save to docs/specs/YYYY-MM-DD-project-name.md
```

### The 7 Required Sections

1. **Introduction** - Background, in scope, out of scope
2. **User Roles** - Each role's responsibilities
3. **Pages & Screens** - Every page with one-line purpose
4. **Core Features** - Outcome-focused capabilities
5. **Integrations** - External services with complexity/risk notes
6. **Milestones & Tasks** - Phases with hour estimates
7. **Open Questions** - Assumptions and unresolved decisions

For complete template and examples, see [PROJECT-SCOPE.md](PROJECT-SCOPE.md)

---

## Using Your Spec With AI Tools

**Claude Code / Cursor:**
```
Build this feature: [paste Quick Feature Spec]
```

**Lovable / Replit / Bolt:**
- Paste Quick Feature Spec as initial prompt
- Break complex features into smaller chunks
- Iterate: "Close, but error message should say X not Y"

**Hiring contractors:**
- Send Full Project Scope
- Ask: "What's unclear? What would you change?"
- Get hour estimate and compare to yours

---

## Common Mistakes

| Mistake | Fix |
|---------|-----|
| "Build a dashboard" | Describe what's ON dashboard and what each thing does |
| Describing HOW to code it | Describe WHAT it should do |
| Forgetting mobile | Add "Works on mobile" to every spec |
| Skipping edge cases | Define what happens when things break |
| No out-of-scope | Prevents scope creep |

---

## When You're Stuck

**"I don't know what I want yet"**
- Use competitor's product for 20 minutes
- Screenshot 3 things you like
- Write: "I want these 3 things, but simpler"

**"AI keeps building the wrong thing"**
- Your spec is vague
- Use templates in QUICK-SPEC.md or PROJECT-SCOPE.md
- Fill in EVERY section

---

## After Scoping

**Save as:** `docs/specs/YYYY-MM-DD-feature-name.md`

**Then:**
- Quick Feature Spec → Give directly to AI tool
- Full Project Scope → Review with stakeholders/contractors first

---

## Success Looks Like

✅ AI builds it right first time (or very close)
✅ Contractors give realistic estimates without surprises  
✅ Edge cases don't surprise you in production
✅ Stakeholders know exactly what they're getting

Related Skills

ontopo

159
from majiayu000/claude-skill-registry

An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.

General Utilities

modal-deployment

159
from majiayu000/claude-skill-registry

Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.

DevOps & Infrastructure

astro

159
from majiayu000/claude-skill-registry

This skill provides essential Astro framework patterns, focusing on server-side rendering (SSR), static site generation (SSG), middleware, and TypeScript best practices. It helps AI agents implement secure authentication, manage API routes, and debug rendering behaviors within Astro projects.

Coding & Development

tech-blog

159
from majiayu000/claude-skill-registry

Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.

Content & DocumentationClaude

grail-miner

159
from majiayu000/claude-skill-registry

This skill assists in setting up, managing, and optimizing Grail miners on Bittensor Subnet 81, handling tasks like environment configuration, R2 storage, model checkpoint management, and performance tuning.

DevOps & Infrastructure

thor-skills

159
from majiayu000/claude-skill-registry

An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.

SecurityClaude

vly-money

159
from majiayu000/claude-skill-registry

Generate crypto payment links for supported tokens and networks, manage access to X402 payment-protected content, and provide direct access to the vly.money wallet interface.

Fintech & CryptoClaude

ux

159
from majiayu000/claude-skill-registry

This AI agent skill provides comprehensive guidance for creating professional and insightful User Experience (UX) designs, covering user research, information architecture, interaction design, visual guidance, and usability evaluation. It aims to produce actionable, user-centered solutions that avoid generic AI aesthetics.

UX Design & StrategyClaude

lets-go-rss

159
from majiayu000/claude-skill-registry

A lightweight, full-platform RSS subscription manager that aggregates content from YouTube, Vimeo, Behance, Twitter/X, and Chinese platforms like Bilibili, Weibo, and Douyin, featuring deduplication and AI smart classification.

Content & Documentation

chrome-debug

159
from majiayu000/claude-skill-registry

This skill empowers AI agents to debug web applications and inspect browser behavior using the Chrome DevTools Protocol (CDP), offering both collaborative (headful) and automated (headless) modes.

Coding & DevelopmentClaude

whisper-transcribe

159
from majiayu000/claude-skill-registry

Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.

Media Processing

advanced-skill-creator

181
from majiayu000/claude-skill-registry

Meta-skill that generates domain-specific skills using advanced reasoning techniques. PROACTIVELY activate for: (1) Create/build/make skills, (2) Generate expert panels for any domain, (3) Design evaluation frameworks, (4) Create research workflows, (5) Structure complex multi-step processes, (6) Instantiate templates with parameters. Triggers: "create a skill for", "build evaluation for", "design workflow for", "generate expert panel for", "how should I approach [complex task]", "create skill", "new skill for", "skill template", "generate skill"