Transform specifications into structured implementation plans with architecture design and task breakdown
/plugin marketplace add athola/claude-night-market/plugin install attune@claude-night-marketThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Transform specification into implementation plan with architecture design and dependency-ordered tasks.
With superpowers:
Skill(superpowers:writing-plans) for structured planningWithout superpowers:
Activities:
Output: Architecture documentation with diagrams
Activities:
Output: Task list with estimates
Activities:
Output: Dependency-ordered task execution plan
Activities:
Output: Sprint schedule with milestones
Questions:
Common Patterns:
### Component: [Name]
**Responsibility**: [What this component does]
**Technology**: [Stack and tools]
**Interfaces**:
- [Interface 1]: [Description]
- [Interface 2]: [Description]
**Dependencies**:
- [Component 1]: [What's needed]
- [Component 2]: [What's needed]
**Data**:
- [Data structure 1]
- [Data structure 2]
**Configuration**:
- [Config param 1]
- [Config param 2]
Verification: Run the command with --help flag to verify availability.
### TASK-[XXX]: [Task Name]
**Description**: [What needs to be done]
**Type**: Implementation | Testing | Documentation | Infrastructure | Deployment
**Priority**: P0 (Critical) | P1 (High) | P2 (Medium) | P3 (Low)
**Estimate**: [Story points or hours]
**Dependencies**: TASK-XXX, TASK-YYY
**Sprint**: Sprint N
**Assignee**: [Name or TBD]
**Linked Requirements**: FR-XXX, NFR-YYY
**Acceptance Criteria**:
- [ ] [Criterion 1]
- [ ] [Criterion 2]
- [ ] Tests passing
- [ ] Documentation updated
**Technical Notes**:
- [Implementation detail 1]
- [Implementation detail 2]
**Testing Requirements**:
- Unit tests: [What to test]
- Integration tests: [What to test]
- E2E tests: [What to test]
**Definition of Done**:
- [ ] Code complete
- [ ] Tests passing
- [ ] Code reviewed
- [ ] Documentation updated
- [ ] Deployed to staging
Verification: Run pytest -v to verify tests pass.
Story Points (Fibonacci):
Factors to consider:
Notation:
**Verification:** Run `pytest -v` to verify tests pass.
TASK-001 (Foundation)
├─▶ TASK-002 (Database schema)
│ ├─▶ TASK-003 (Models)
│ └─▶ TASK-011 (Data import)
└─▶ TASK-004 (Authentication)
└─▶ TASK-005 (Auth middleware)
└─▶ TASK-010 (Protected endpoints)
Verification: Run the command with --help flag to verify availability.
Validation:
Sprint Template:
## Sprint [N]: [Focus Area]
**Dates**: [Start] - [End]
**Goal**: [Sprint objective]
**Capacity**: [Team capacity in story points]
### Planned Tasks ([X] story points)
- TASK-XXX ([N] points)
- TASK-YYY ([M] points)
- ...
### Deliverable
[What will be demonstrable at sprint end]
### Risks
- [Risk 1 with mitigation]
- [Risk 2 with mitigation]
### Dependencies
- [External dependency 1]
- [External dependency 2]
Verification: Run the command with --help flag to verify availability.
Risk Template:
| Risk | Impact | Probability | Mitigation |
|------|--------|-------------|------------|
| [Risk description] | High/Med/Low | High/Med/Low | [How to address] |
Verification: Run the command with --help flag to verify availability.
Common Risks:
Save to docs/implementation-plan.md:
# [Project Name] - Implementation Plan v[version]
**Author**: [Name]
**Date**: [YYYY-MM-DD]
**Sprint Length**: [Duration]
**Team Size**: [Number]
**Target Completion**: [Date]
## Architecture
### System Overview
[High-level architecture description]
### Component Diagram
[ASCII or markdown diagram]
### Components
[Component details using template above]
### Data Flow
[How data moves through system]
## Task Breakdown
### Phase 1: [Name] (Sprint [N]) - TASK-001 through TASK-010
[Tasks using template above]
### Phase 2: [Name] (Sprint [M]) - TASK-011 through TASK-020
[Tasks using template above]
## Dependency Graph
[Dependency visualization]
## Sprint Schedule
[Sprint details using template above]
## Risk Assessment
[Risk table]
## Success Metrics
- [ ] [Metric 1]
- [ ] [Metric 2]
## Timeline
| Sprint | Dates | Focus | Deliverable |
|--------|-------|-------|-------------|
| 1 | Jan 3-16 | Foundation | Dev environment |
| 2 | Jan 17-30 | Core | Feature X working |
## Next Steps
1. Review plan with team
2. Initialize project with `/attune:init`
3. Start execution with `/attune:execute`
Verification: Run the command with --help flag to verify availability.
Before completing plan:
Skill(superpowers:writing-plans) - Planning methodology (if available)Skill(spec-kit:task-planning) - Task breakdown (if available)Skill(attune:project-specification) - Previous phaseSkill(attune:project-execution) - Next phase/attune:plan - Invoke this skill/attune:execute - Next step in workflowSee /attune:plan command documentation for complete examples.
Command not found Ensure all dependencies are installed and in PATH
Permission errors Check file permissions and run with appropriate privileges
Unexpected behavior
Enable verbose logging with --verbose flag
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.