Coding

project-planning

Try it

Converts a specification into a phased, dependency-ordered implementation plan. Use after specification is complete and before execution begins

What it does

Converts a specification into a phased, dependency-ordered implementation plan. Use after specification is complete and before execution begins

The skill document

Night Market Skill — ported from claude-night-market/attune. For the full experience with agents, hooks, and commands, install the Claude Code plugin.

Delegation

For detailed task planning workflows, this skill delegates to spec-kit:task-planning as the canonical implementation. Use this skill for quick planning needs; use spec-kit for comprehensive project plans.

When To Use

  • After specification phase completes
  • Need to design system architecture
  • Need task breakdown for implementation
  • Planning sprints and resource allocation
  • Converting requirements into actionable tasks
  • Defining component interfaces and dependencies

When NOT To Use

  • No specification exists yet (use Skill(attune:project-specification) first)
  • Still exploring problem space (use Skill(attune:project-brainstorming) instead)
  • Ready to execute existing plan (use Skill(attune:project-execution) instead)
  • Need to adjust running project (update plan incrementally, don't restart)

Integration

With superpowers:

  • Uses Skill(superpowers:writing-plans) for structured planning
  • Applies checkpoint-based execution patterns
  • Uses dependency analysis framework

Without superpowers:

  • Standalone planning methodology
  • Task breakdown templates
  • Dependency tracking patterns

Quality Checks

Before completing plan:

  • ✅ All architecture components documented
  • ✅ File Structure section present before tasks
  • ✅ All task files appear in File Structure table
  • ✅ All FRs mapped to tasks
  • ✅ All tasks have acceptance criteria
  • ✅ Dependencies are acyclic
  • ✅ Effort estimates provided
  • ✅ Critical path identified
  • ✅ Risks assessed with mitigations
  • ✅ Sprints balanced by capacity

Post-Completion: Workflow Continuation (REQUIRED)

Automatic Trigger: After Quality Checks pass and docs/implementation-plan.md is saved, MUST auto-invoke the next phase.

When continuation is invoked:

  1. Verify docs/implementation-plan.md exists and is non-empty
  2. Display checkpoint message to user:
    Implementation plan complete. Saved to docs/implementation-plan.md.
    Proceeding to execution phase...
    
  3. Invoke next phase:
    Skill(attune:project-execution)
    

Bypass Conditions (ONLY skip continuation if ANY true):

  • --standalone flag was provided by the user
  • docs/implementation-plan.md does not exist or is empty (phase failed)
  • User explicitly requests to stop after planning

Do NOT prompt the user for confirmation — this is a lightweight checkpoint, not an interactive gate. The user can always interrupt if needed.

  • Skill(superpowers:writing-plans) - Planning methodology (if available)
  • Skill(spec-kit:task-planning) - Task breakdown (if available)
  • Skill(attune:project-specification) - Previous phase
  • Skill(attune:project-execution) - AUTO-INVOKED next phase after planning
  • Skill(attune:mission-orchestrator) - Full lifecycle orchestration
  • /attune:blueprint - Invoke this skill
  • /attune:execute - Next step in workflow

Examples

See /attune:blueprint command documentation for complete examples.

Troubleshooting

Common Issues

If you find circular dependencies in your task graph, break one of the tasks into smaller sub-tasks. If sprint capacity is consistently exceeded, re-estimate tasks using the Fibonacci scale or reduce sprint scope.

Related skills

Executes implementation plans with progress tracking, checkpoint validation, and quality gates. Use after planning is complete and tasks are ready to implement

25 installs

Scaffolds new projects with git, CI/CD workflows, pre-commit hooks, and build config

26 installs

Guides project ideation via Socratic questioning to produce a validated brief. Use before specification when requirements are unclear

24 installs

Configures pre-commit hooks for linting, type checking, formatting, and testing

25 installs

Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release

23 installs

Manage a personal recipe collection as local markdown files: capture, scale, convert, substitute, plan, and cost.

by Iván