spec-kit-skill
GitHub Spec-Kit integration for constitution-based spec-driven development. 7-phase workflow. Triggers: "spec-kit", "speckit", "constitution", "specify", ".specify/", "规格驱动开发", "需求规格".
Install
mkdir -p .claude/skills/spec-kit-skill && curl -L -o skill.zip "https://mcp.directory/api/skills/download/1218" && unzip -o skill.zip -d .claude/skills/spec-kit-skill && rm skill.zipInstalls to .claude/skills/spec-kit-skill
About this skill
Spec-Kit: Constitution-Based Spec-Driven Development
Official GitHub Spec-Kit integration providing a 7-phase constitution-driven workflow for feature development.
Quick Start
This skill works with the GitHub Spec-Kit CLI to guide you through structured feature development:
- Constitution → Establish governing principles
- Specify → Define functional requirements
- Clarify → Resolve ambiguities
- Plan → Create technical strategy
- Tasks → Generate actionable breakdown
- Analyze → Validate consistency
- Implement → Execute implementation
Storage: Creates files in .specify/specs/NNN-feature-name/ directory with numbered features
When to Use
- Setting up spec-kit in a project
- Creating constitution-based feature specifications
- Working with .specify/ directory
- Following GitHub spec-kit workflow
- Constitution-driven development
Prerequisites & Setup
Check CLI Installation
First, verify if spec-kit CLI is installed:
command -v specify || echo "Not installed"
Installation
If not installed:
# Persistent installation (recommended)
uv tool install specify-cli --from git+https://github.com/github/spec-kit.git
# One-time usage
uvx --from git+https://github.com/github/spec-kit.git specify init <PROJECT_NAME>
Requirements:
- Python 3.11+
- Git
- uv package manager (install uv)
Project Initialization
If CLI is installed but project not initialized:
# Initialize in current directory
specify init . --ai claude
# Initialize new project
specify init <project-name> --ai claude
# Options:
# --force: Overwrite non-empty directories
# --script ps: Generate PowerShell scripts (Windows)
# --no-git: Skip Git initialization
<details> <summary>🔍 Phase Detection Logic</summary>
Detecting Project State
Before proceeding, always detect the current state:
1. CLI Installed?
if command -v specify &> /dev/null || [ -x "$HOME/.local/bin/specify" ]; then
echo "CLI installed"
else
echo "CLI not installed - guide user through installation"
fi
2. Project Initialized?
if [ -d ".specify" ] && [ -f ".specify/memory/constitution.md" ]; then
echo "Project initialized"
else
echo "Project not initialized - guide user through 'specify init'"
fi
3. Current Feature
# Get latest feature directory
LATEST=$(ls -d .specify/specs/[0-9]* 2>/dev/null | sort -V | tail -1)
echo "Latest feature: $LATEST"
4. Current Phase
Detect phase by checking file existence in latest feature:
FEATURE_DIR=".specify/specs/001-feature-name"
if [ ! -f ".specify/memory/constitution.md" ]; then
echo "Phase: constitution"
elif [ ! -d "$FEATURE_DIR" ]; then
echo "Phase: specify"
elif [ -f "$FEATURE_DIR/spec.md" ] && ! grep -q "## Clarifications" "$FEATURE_DIR/spec.md"; then
echo "Phase: clarify"
elif [ ! -f "$FEATURE_DIR/plan.md" ]; then
echo "Phase: plan"
elif [ ! -f "$FEATURE_DIR/tasks.md" ]; then
echo "Phase: tasks"
elif [ -f "$FEATURE_DIR/tasks.md" ] && grep -q "\\- \\[ \\]" "$FEATURE_DIR/tasks.md"; then
echo "Phase: implement"
else
echo "Phase: complete"
fi
</details>
<details>
<summary>📜 Phase 1: Constitution</summary>
Constitution Phase
Establish foundational principles that govern all development decisions.
Purpose
Create .specify/memory/constitution.md with:
- Project values and principles
- Technical standards
- Decision-making frameworks
- Code quality expectations
- Architecture guidelines
Process
-
Gather Context
- Understand project domain
- Identify key stakeholders
- Review existing standards (if any)
-
Draft Constitution
- Core values and principles
- Technical standards
- Quality expectations
- Decision criteria
-
Structure
# Project Constitution
## Core Values
1. **[Value Name]**: [Description and implications]
2. **[Value Name]**: [Description and implications]
## Technical Principles
### Architecture
- [Principle with rationale]
### Code Quality
- [Standards and expectations]
### Performance
- [Performance criteria]
## Decision Framework
When making technical decisions, consider:
1. [Criterion with priority]
2. [Criterion with priority]
- Versioning
- Constitution can evolve
- Track changes for governance
- Review periodically
Example Content
# Project Constitution
## Core Values
1. **Simplicity Over Cleverness**: Favor straightforward solutions that are easy to understand and maintain over clever optimizations.
2. **User Experience First**: Every technical decision should improve or maintain user experience.
## Technical Principles
### Architecture
- Prefer composition over inheritance
- Keep components loosely coupled
- Design for testability
### Code Quality
- Code reviews required for all changes
- Unit test coverage > 80%
- Documentation for public APIs
### Performance
- Page load < 3 seconds
- API response < 200ms
- Progressive enhancement for slower connections
## Decision Framework
When choosing between approaches:
1. Does it align with our core values?
2. Is it maintainable by the team?
3. Does it scale with our growth?
4. What's the long-term cost?
</details>
<details>
<summary>📝 Phase 2: Specify</summary>
Specify Phase
Define what needs building and why, avoiding technology specifics.
Script Usage
# Create new feature
.specify/scripts/bash/create-new-feature.sh --json "feature-name"
# Expected JSON output:
# {"BRANCH_NAME": "001-feature-name", "SPEC_FILE": "/path/to/.specify/specs/001-feature-name/spec.md"}
Parse JSON: Extract BRANCH_NAME and SPEC_FILE for subsequent operations.
Template Structure
Load .specify/templates/spec-template.md to understand required sections, then create specification at SPEC_FILE location.
Specification Content
Focus on functional requirements:
# Feature Specification: [Feature Name]
## Problem Statement
[What problem are we solving?]
## User Stories
### Story 1: [Title]
As a [role]
I want [capability]
So that [benefit]
**Acceptance Criteria:**
- [ ] [Specific, testable criterion]
- [ ] [Specific, testable criterion]
### Story 2: [Title]
[Continue...]
## Non-Functional Requirements
- Performance: [Specific metrics]
- Security: [Requirements]
- Accessibility: [Standards]
- Scalability: [Expectations]
## Success Metrics
- [Measurable outcome]
- [Measurable outcome]
## Out of Scope
[Explicitly state what's NOT included]
Key Principles
- Technology-agnostic: Don't specify "use React" or "MySQL"
- Outcome-focused: Describe what user achieves, not how
- Testable: Acceptance criteria must be verifiable
- Complete: Address edge cases and error scenarios
Git Integration
The script automatically:
- Creates new feature branch (e.g.,
001-feature-name) - Checks out the branch
- Initializes spec file
Clarify Phase
Resolve underspecified areas through targeted questioning.
Purpose
Before planning implementation, ensure specification is complete and unambiguous.
Process
-
Analyze Specification
- Read spec.md thoroughly
- Identify ambiguities, gaps, assumptions
- Note areas with multiple valid interpretations
-
Generate Questions (Maximum 5)
- Prioritize high-impact areas
- Focus on decisions that affect architecture
- Ask about edge cases and error handling
-
Question Format
## Clarifications
### Q1: [Clear, specific question]
**Context**: [Why this matters]
**Options**: [If multiple approaches exist]
### Q2: [Clear, specific question]
**Context**: [Why this matters]
**Impact**: [What decisions depend on this]
- Update Specification
- Add "## Clarifications" section to spec.md
- Document questions and answers
- Update relevant sections based on answers
- Iterate until all critical questions answered
Guidelines
- Maximum 5 questions per round
- Specific, not general: "How should we handle concurrent edits?" not "How should it work?"
- Decision-focused: Questions that inform technical choices
- Incremental: Can run multiple clarification rounds
Example Questions
## Clarifications
### Q1: How should the system handle conflicts when two users edit the same document simultaneously?
**Context**: This affects data model design and user experience.
**Options**:
- Last-write-wins (simple, may lose data)
- Operational transforms (complex, preserves all edits)
- Locked editing (simple, limits collaboration)
**Answer**: [User provides answer]
### Q2: What's the maximum number of concurrent users we need to support?
**Context**: Affects infrastructure planning and architecture decisions.
**Impact**: Determines caching strategy, database choices, and scaling approach.
**Answer**: [User provides answer]
</details>
<details>
<summary>🏗️ Phase 4: Plan</summary>
Plan Phase
Create technical implementation strategy based on clarified specification.
Script Usage
# Setup plan phase
.specify/scripts/bash/setup-plan.sh --json
# Expected JSON output:
# {"FEATURE_SPEC": "/path/spec.md", "IMPL_PLAN": "/path/plan.md", "SPECS_DIR": "/path/specs", "BRANCH": "001-feature"}
Documents to Create
1. Main Plan (plan.md)
# Implementation Plan: [Feature Name]
## Technology Stack
### Frontend
- Framework: [Choice with rationale]
- State Management: [Choice with rationale]
- Styling: [Choice with rationale]
### Backend
- Language/Framework: [Choice with rationale]
- Database: [Choice with rationale]
- API Style: [REST/GraphQL/etc with rationale]
## Architecture
### System Overview
```mermaid
graph TD
A[Client] --> B[API Gateway]
B --> C[Service Layer]
C --> D[Data
---
*Content truncated.*
More by feiskyer
View all skills by feiskyer →You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
pdf-to-markdown
aliceisjustplaying
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
Related MCP Servers
Browse all serversEmpower AI with the Exa MCP Server—an AI research tool for real-time web search, academic data, and smarter, up-to-date
Access shadcn/ui v4 components, blocks, and demos for rapid React UI library development. Seamless integration and sourc
Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search, and Drive with AI. Comprehensive Googl
Access official Microsoft Docs instantly for up-to-date info. Integrates with ms word and ms word online for seamless wo
Rtfmbro is an MCP server for config management tools—get real-time, version-specific docs from GitHub for Python, Node.j
GraphQL Forge automates tool creation from any GraphQL API, offering seamless integration and intelligent caching for Gi
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.