Autonomously create and implement a complete spec workflow with multi-agent collaboration, bypassing manual review steps through intelligent consensus-building
Autonomously implements full software specs through multi-agent collaboration without requiring user review at any stage.
npx claudepluginhub uniswap/ai-toolkitThis skill is limited to using the following tools:
FULLY AUTONOMOUS spec-driven development that NEVER prompts the user for review. Creates requirements, design, and tasks documents through consensus-building between specialized agents, then implements each task with continuous quality validation.
This command automates the entire spec workflow WITHOUT ANY USER INTERACTION:
CRITICAL: This command is designed to run COMPLETELY AUTONOMOUSLY. It will:
Accept natural language description and extract:
feature: The feature or task description to implementskip_final_review: Optional flag to skip final user review (default: false)project_path: Optional project path (defaults to current working directory)spec_name: Optional spec name (auto-generated from feature if not provided)steering_context: Optional flag to load steering documents (default: true)parallel_execution: Optional flag for parallel task execution (default: true)quality_threshold: Quality threshold for agent consensus (default: 0.8)Examples:
/auto-spec user authentication with OAuth2 and JWT tokens/auto-spec add real-time notifications using WebSockets --skip-final-review/auto-spec implement event-driven order processing systemExecute autonomous spec-driven development workflow with multi-agent collaboration.
mcp__spec-workflow__request-approval toolLoad Project Context
mcp__spec-workflow__get-steering-context if steering documents existmcp__spec-workflow__get-template-context to understand document formatsFeature Analysis
Initial Requirements Generation
mcp__spec-workflow__spec-workflow-guide to understand workflowmcp__spec-workflow__create-spec-docMulti-Agent Requirements Review (INSTEAD of user review)
Initial Design Generation
Multi-Agent Design Review (INSTEAD of user review)
Task Decomposition
mcp__spec-workflow__create-spec-doc to create tasks documentTask Validation (INSTEAD of user review)
For each task in the implementation plan:
Task Implementation
mcp__spec-workflow__manage-tasksQuality Validation Loop (INSTEAD of user review)
Task Completion
Create comprehensive summary including:
# Autonomous Spec Implementation: [Feature Name]
## Implementation Summary
- Spec Name: [spec-name]
- Total Tasks: [X completed / Y total]
- Execution Time: [duration]
- Quality Score: [X/10]
## Key Decisions and Rationale
[List major architectural choices with reasoning]
## Testing Guide
- Unit Tests: [X% coverage]
- Integration Tests: [Y scenarios]
## Next Steps
[Recommended follow-up actions]
/auto-spec add user profile picture upload with image resizing
/auto-spec implement event-driven microservices architecture for order processing
/auto-spec refactor authentication system --quality-threshold=0.9
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.
Search, 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.
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.