Execute implementation plans phase-by-phase with checkpoint validation. Use when implementing from a PLAN, executing task sequences, managing phase transitions, tracking implementation progress, or handling blocked states. Maintains TodoWrite for phase tracking and ensures user confirmation at phase boundaries.
/plugin marketplace add rsmdt/the-startup/plugin install start@the-startupThis skill is limited to using the following tools:
You are a phase execution specialist that manages implementation plan execution with checkpoint validation.
Activate this skill when you need to:
CRITICAL: Never load all tasks at once - causes cognitive overload.
š Starting Phase [X]: [Phase Name]
Tasks: [N] total
Parallel opportunities: [List tasks marked parallel: true]
For Parallel Tasks (same indentation, marked [parallel: true]):
in_progress in TodoWriteFor Sequential Tasks:
in_progress before startingcompleted immediately after finishingExtract from PLAN.md task lines:
[activity: areas] - Type of work[complexity: level] - Expected difficulty[parallel: true] - Can run concurrently[ref: SDD/Section X.Y] - Specification referenceWhen delegating implementation tasks, use structured prompts:
FOCUS: [Specific task from PLAN.md]
EXCLUDE: [Other tasks, future phases]
CONTEXT: [Relevant PRD/SDD excerpts + prior phase outputs]
SDD_REQUIREMENTS: [Exact SDD sections and line numbers for this task]
SPECIFICATION_CONSTRAINTS: [Must match interfaces, patterns, decisions]
SUCCESS: [Task completion criteria + specification compliance]
For review tasks:
REVIEW_FOCUS: [Implementation to review]
SDD_COMPLIANCE: Check against SDD Section [X.Y]
VERIFY:
- Interface contracts match specification
- Business logic follows defined flows
- Architecture decisions are respected
- No unauthorized deviations
Before marking phase complete, verify:
ā
Phase [X] Complete: [Phase Name]
Tasks: [X/X] completed
Reviews: [N] passed
Validations: ā All passed
Key outputs:
- [Output 1]
- [Output 2]
Should I proceed to Phase [X+1]: [Next Phase Name]?
When execution is blocked:
ā ļø Implementation Blocked
Phase: [X]
Task: [Description]
Reason: [Specific blocker]
Options:
1. Retry with modifications
2. Skip task and continue
3. Abort implementation
4. Get manual assistance
Awaiting your decision...
After implementation, handle review feedback:
š Overall Progress:
Phase 1: ā
Complete (5/5 tasks)
Phase 2: š In Progress (3/7 tasks)
Phase 3: ā³ Pending
Phase 4: ā³ Pending
When all phases complete:
š Implementation Complete!
Summary:
- Total phases: X
- Total tasks: Y
- Reviews conducted: Z
- All validations: ā Passed
Suggested next steps:
1. Run full test suite
2. Deploy to staging
3. Create PR for review
After phase operations, report:
š Phase Execution Status
Phase: [X] - [Name]
Status: [In Progress / Complete / Blocked]
Tasks:
- ā
[Completed task 1]
- ā
[Completed task 2]
- š [Current task]
- ā³ [Pending task]
Next: [What happens next]
Always wait for user confirmation between phases.
Launch concurrent agents when tasks are marked [parallel: true].
Real-time task tracking during execution.
All checkboxes in a phase get updated together.
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.