Planning Agent
Creates implementation plans and handoffs from conversation context
What You Can Do
This skill transforms high-level feature requests into actionable implementation plans by conducting deep requirement interviews, analyzing existing codebases (or planning greenfield projects), and producing comprehensive handoff documents. It distinguishes between brownfield development (with existing code to integrate) and greenfield projects (starting from scratch), ensuring your technical strategy accounts for your actual constraints and patterns.
Features
Asks multi-level discovery questions to clarify ambiguous requirements before planning
Reads codebase-map.md for brownfield projects to understand existing architecture and patterns
Automatically adapts planning strategy based on whether you're extending existing code or building new
Creates detailed implementation roadmaps with clear task breakdowns and dependencies
References session state through continuity ledger to maintain context across planning sessions
Surfaces hidden technical constraints and integration points before development begins
Organizes implementation steps in logical, testable phases
Example Output
Interview Output:
- Problem: "User spends 45 minutes daily exporting analytics data manually"
- Context: "Non-technical finance team needs daily reports by 9am"
- Constraint: "Must integrate with existing Salesforce API, not replace it"
Implementation Plan Output:
## Phase 1: Data Pipeline Setup
- Task 1.1: Create API client for Salesforce connector
- Task 1.2: Build data validation layer
- Task 1.3: Set up error handling & retry logic
## Phase 2: Export Engine
- Task 2.1: Implement CSV export formatter
- Task 2.2: Create email delivery service
- Task 2.3: Schedule daily execution
## Brownfield Integration Notes
- Extend existing `services/integrations/` directory
- Follow current authentication pattern in codebase
- Use existing error logging infrastructure
What's Included
- planning-agent SKILL.md: Core planning agent instructions and branching logic
- Interview template: Structured questions for requirement discovery across problem definition, user context, and technical constraints
- Handoff template: Markdown format for phase-based implementation plans with dependencies and entry points
- Brownfield checklist: Steps for codebase analysis and integration planning
- Continuity ledger reference: How to track and reference session state across planning iterations
Who It's For
- AI/Prompt Engineers — Building agent systems that require multi-stage planning workflows
- Software architects — Designing implementation strategies for complex features or system migrations
- Technical leads — Creating handoff documentation and task breakdowns for development teams
- Full-stack developers — Planning feature implementation across existing codebases with multiple constraints
- Product managers — Translating requirements into technical feasibility assessments and roadmaps
Best For
- Planning brownfield feature additions requiring integration with existing systems
- Greenfield project architecture design and tech stack planning
- Complex requirement gathering through structured discovery interviews
- Creating developer handoff documentation with phase sequencing
- Assessing technical feasibility and identifying hidden constraints early
- Building modular implementation plans with clear dependencies
You might also like
You can systematically diagnose why your RAG system isn't returning relevant results and identify specific misalignments between queries and context. This skill walks you through analyzing retrieval quality, scoring context relevance, and optimizing prompt-retrieval alignment to improve your RAG accuracy. You'll get concrete, actionable recommendations for fixing bottlenecks in your pipeline.
by moonwell-fi
You can prepare your domain-specific datasets, train fine-tuned Claude models optimized for your use case, benchmark performance against base models, and deploy production-ready custom models. This skill automates the entire fine-tuning pipeline from raw data to live inference, complete with cost-benefit analysis and version control.
by moonwell-fi
You get structured guidance for designing controlled experiments, selecting appropriate metrics, and analyzing results with statistical rigor. Claude helps you identify confounding variables, calculate required sample sizes, interpret statistical significance, and document methodology for reproducible benchmarking that stands up to scrutiny.
by moonwell-fi
You can structure comprehensive health technology assessments (HTAs) that organize clinical evidence, economic analyses, and regulatory considerations into evidence-based coverage recommendations. This skill helps you synthesize clinical trial data, health economic models, and real-world evidence into clear, defensible payer coverage determinations. You'll generate professional HTA reports that align with major frameworks like ICER, CADTH, and NICE standards.
by moonwell-fi
You can systematically diagnose performance issues across your ML infrastructure, identify root causes of distributed training failures, and receive actionable optimization recommendations. This skill analyzes metrics, logs, and configuration data to pinpoint resource constraints, communication overhead, and configuration misalignments that impact training speed and reliability.
by moonwell-fi
You can build AI-powered Python agents quickly using the @agentic decorator for simple functions or spawn() for full multi-agent systems with behavioral control. Agents maintain persistent state, integrate with MCP tools, handle typed return values, and coordinate with each other through a unified framework—enabling everything from basic AI-enhanced functions to complex agent orchestration pipelines.
by aymericzip
This skill walks you through the complete dataset preparation workflow for fine-tuning Claude models. You'll validate training data quality, detect and fix formatting errors, identify data imbalances, and generate validation reports to ensure your fine-tuned model performs reliably in production.
by moonwell-fi
This skill helps you systematically diagnose failures in distributed ML training and serving infrastructure. You provide system logs, metrics, and error traces, and Claude performs structured root-cause analysis to identify the underlying issue—whether it's resource exhaustion, distributed system deadlock, data pipeline corruption, or model serving misconfiguration. You get a detailed diagnosis with remediation steps ranked by likelihood and implementation effort.
by moonwell-fi