Read requirements markdown and generate detailed technical specifications. Analyzes requirements, clarifies ambiguities, and updates the specs document. Use when user has written requirements and wants to generate specs.
Generates detailed technical specifications by analyzing requirements markdown files and clarifying ambiguities.
/plugin marketplace add datamaker-kr/synapse-claude-marketplace/plugin install sdd-helper@synapse-marketplaceThis skill is limited to using the following tools:
Part of the spec-manager agent. This skill analyzes requirements and generates detailed technical specifications.
The user provides a task slug (or task title) as arguments: $ARGUMENTS
If no arguments are provided:
*/requirements.md files in specs/ directoryIf a task title (not slug) is provided, convert it to a slug to find the matching files.
specs/{slug}/requirements.md/init-specs firstCheck that requirements are sufficiently detailed:
If requirements are incomplete or too vague, inform the user about what's missing and ask them to fill in the gaps before proceeding. Do NOT generate specs from empty templates.
Perform thorough analysis of the requirements:
If analysis reveals ambiguities, conflicts, or gaps:
Example clarifications:
Update specs/{slug}/specs.md with comprehensive technical specifications:
# Specs: {Original Task Title}
> Created: {original date}
> Updated: {YYYY-MM-DD}
> Status: Draft
> Requirements: [requirements.md](./requirements.md)
## Overview
{Brief technical overview of what will be built, derived from requirements}
## Technical Specifications
### TS-1: {Spec Name} (from FR-1)
- **Description**: {Technical description}
- **Components Involved**: {List of components/modules}
- **Data Flow**: {How data moves through the system}
- **Implementation Approach**: {High-level approach}
- **Constraints**: {Technical constraints}
### TS-2: {Spec Name} (from FR-2)
{Same structure}
## Architecture
### Component Design
{Describe the components that need to be created or modified}
### Data Flow
{Describe how data flows through the system for this feature}
### Integration Points
{How this feature integrates with existing systems}
## Data Models
### {Model Name}
| Field | Type | Description | Constraints |
|-------|------|-------------|-------------|
| | | | |
## API / Interface Design
### {Endpoint/Function Name}
- **Method**: {GET/POST/etc. or function signature}
- **Path**: {URL path or module path}
- **Input**: {Request body/parameters}
- **Output**: {Response format}
- **Errors**: {Possible error responses}
## Error Handling
| Scenario | Handling Strategy | User Impact |
|----------|-------------------|-------------|
| | | |
## Dependencies
### External
- {Library/service}: {Purpose} - {Version/notes}
### Internal
- {Module/component}: {How it's used}
## Security Considerations
- {Security concern and mitigation}
## Performance Considerations
- {Performance concern and mitigation}
## Open Questions
- {Any remaining unresolved questions}
## Clarification Log
| # | Question | Answer | Date |
|---|----------|--------|------|
| 1 | {Question asked} | {Answer received} | {Date} |
After generating specs, display a summary:
Specs generated for: "{Original Task Title}"
Updated: specs/{slug}/specs.md
Summary:
- {N} technical specifications derived from {M} requirements
- {X} components identified
- {Y} API endpoints/interfaces defined
- {Z} open questions remaining
Please review the generated specs in specs/{slug}/specs.md
If you need to clarify or modify anything, discuss it here.
When specs are finalized, run:
/plan-with-specs {slug}
If the user requests changes or has questions about the generated specs:
If the user requests changes to requirements during this process:
specs/{slug}/requirements.md with the changesspecs/{slug}/specs.md reflecting the changesspecs/{slug}/plans.md status to "Pending (specs updated)"/plan-with-specsSearch, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.