deepen-plan

Purpose: Enhance existing plans with parallel research agents for maximum depth and grounding.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "deepen-plan" with this command: npx skills add vitadynamics/vita-cc-market/vitadynamics-vita-cc-market-deepen-plan

Deepen Plan Skill

Purpose: Enhance existing plans with parallel research agents for maximum depth and grounding.

Plan to Deepen

Deepen target: ${ARGUMENTS}

Deepening Methodology

Phase 1: Plan Analysis

Read and Understand Plan

  • Read the entire plan document (expected location: docs/plans/ )

  • If the plan frontmatter contains source-spec: , read the referenced spec file for additional context

  • Identify key sections and requirements

  • Note areas that need additional depth or clarification

Scope Definition

  • Determine which sections benefit most from deepening

  • Identify knowledge gaps or uncertainties

  • Prioritize based on impact and complexity

Phase 2: Parallel Research Agents

Launch specialized research agents in parallel based on plan needs:

Architecture & Design Agents:

  • System Architecture Researcher - Overall system design and integration

  • Domain Model Researcher - Business logic and data relationships

  • API Design Researcher - Endpoint specifications and contracts

Implementation & Quality Agents: 4. Best Practices Researcher - Industry standards and conventions 5. Performance Researcher - Optimization strategies and patterns 6. Security Researcher - Security considerations and mitigations 7. Testing Strategy Researcher - Comprehensive testing approaches

Language & Framework Agents: 8. Language-Specific Researcher - Language idioms and patterns 9. Framework Researcher - Framework capabilities and constraints

Integration & Operations Agents: 10. Integration Researcher - External dependencies and APIs 11. Database Researcher - Data modeling and query patterns 12. UI/UX Researcher - User interface patterns and best practices

Phase 3: Knowledge Integration

Collect Research Findings

  • Gather insights from all research agents

  • Identify patterns and common themes

  • Evaluate conflicting recommendations

Update Plan Sections

  • Enhance existing sections with new insights

  • Add new sections for uncovered aspects

  • Include references and citations

Create Deepened Plan

  • Integrate research findings into coherent plan

  • Highlight key decisions and trade-offs

  • Provide implementation guidance

Phase 4: Validation and Refinement

Review Deepened Plan

  • Check for consistency and completeness

  • Validate technical feasibility

  • Assess alignment with project goals

Present Enhancements

  • Summarize key additions and improvements

  • Highlight critical insights and recommendations

  • Explain rationale for changes

Next Steps

  • Option to further refine specific sections

  • Run adr docs/plans/<feature-name>.md — capture key architectural decisions as permanent ADRs

  • Start /core:work docs/plans/<feature-name>.md — begin implementation

Output Features

Enhanced Plan Sections:

  • Expanded technical specifications

  • Detailed implementation strategies

  • Comprehensive testing approaches

  • Performance and security considerations

Supporting Materials:

  • Reference links and documentation

  • Code examples and patterns

  • Architecture diagrams and flowcharts

  • Risk assessment and mitigation strategies

Key Benefits

  • Depth: Uncover hidden complexities and edge cases

  • Breadth: Consider multiple perspectives and approaches

  • Validation: Ground decisions in research and best practices

  • Actionability: Provide concrete implementation guidance

Use Cases

Best for:

  • Complex feature implementations

  • Architectural changes or migrations

  • Performance-critical optimizations

  • Security-sensitive functionality

  • Integration with external systems

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

hook-creator

No summary provided by upstream source.

Repository SourceNeeds Review
General

heal-skill

No summary provided by upstream source.

Repository SourceNeeds Review
General

medium-plan

No summary provided by upstream source.

Repository SourceNeeds Review
General

create-command

No summary provided by upstream source.

Repository SourceNeeds Review