Awesome-omni-skill spec-requirements
Generate comprehensive requirements definition documents with technology selection and improvement suggestions
install
source · Clone the upstream repo
git clone https://github.com/diegosouzapw/awesome-omni-skill
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/diegosouzapw/awesome-omni-skill "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/development/spec-requirements" ~/.claude/skills/diegosouzapw-awesome-omni-skill-spec-requirements && rm -rf "$T"
manifest:
skills/development/spec-requirements/SKILL.mdsource content
Spec Requirements
Generate comprehensive requirements definition documents with technology selection, improvement suggestions, and EARS format acceptance criteria.
Usage
/spec:requirements <system_name> [options]
Options
| Option | Short | Description | Example |
|---|---|---|---|
| | Mode (new-creation/reverse-engineering) | |
| | Enable product backlog format | |
| | Epic name for backlog structure | |
| Include story point estimation | | |
| | Application name | |
| | Function/feature name | |
| | Output file path | |
| | Technology stack | |
| | Priority level (low/medium/high/critical) | |
| | Scope type (mvp/full/enterprise) | |
| Include improvement suggestions | | |
| Include implementation examples | | |
| Template type | | |
| Interactive clarification mode | |
Templates
| Template | Description |
|---|---|
| General purpose with EARS format |
| User story format with acceptance criteria |
| Detailed specification document |
| Full backlog with epics, features, stories |
Tool Priorities
ALWAYS prioritize mcp__serena__ tools:
File Operations (Serena MCP First)
→mcp__serena__find_file
(fallback)Read
→mcp__serena__search_for_pattern
(fallback)Grep
→mcp__serena__list_dir
(fallback)LS
Code Analysis (Serena MCP)
mcp__serena__get_symbols_overviewmcp__serena__find_referencing_symbols
Context7 Integration
For technology documentation:
- Frontend: React, Vue, Angular
- Backend: Node.js, Express, FastAPI
- Database: PostgreSQL, MongoDB, Redis
Modes
New Creation Mode (Default)
Generate requirements from specifications and user input.
Reverse Engineering Mode
Analyze existing codebase to extract requirements:
- Component Discovery (controllers, services, models)
- Feature Extraction (user-facing functionality)
- User Story Generation (features to stories)
EARS Format
Acceptance criteria use EARS (Easy Approach to Requirements Syntax):
- WHEN [event] THEN [system] SHALL [response]
- IF [precondition] THEN [system] SHALL [response]
- WHILE [condition] THE SYSTEM SHALL [behavior]
- WHERE [context] THE SYSTEM SHALL [behavior]
Examples
# Basic requirements /spec:requirements "E-commerce Platform" -a "Web Store" -t "react,nodejs" # MVP with suggestions /spec:requirements "Social Media App" -s mvp --suggest # Interactive hearing mode /spec:requirements "Mobile App" --hearing # Reverse engineering with backlog /spec:requirements "User Management" -m reverse-engineering -b -e "Auth Epic" # Full enterprise with examples /spec:requirements "CRM System" -s enterprise -t "react,nodejs,postgresql" --examples
Output Structure
- Header Information: Timestamp, system name, priority, scope
- Functional Requirements: Core features, user scenarios (EARS format)
- Non-Functional Requirements: Performance, security, availability
- Technical Specifications: Architecture, tech stack, integrations
- Additional Sections: Examples, suggestions (if enabled)