This skill should be used when planning and tracking complex feature implementations that require systematic task decomposition. Use this skill to break down large features into manageable, well-documented tasks with clear dependencies, action items, and success criteria. The skill provides a structured template and methodology for iterative planning and tracking throughout implementation.
/plugin marketplace add NikiforovAll/claude-code-rules/plugin install handbook-git-worktree@cc-handbookThis skill inherits all available tools. When active, it can use any tool Claude has access to.
assets/plan-template.mdassets/task-template.mdreferences/task-planning-guide.mdThis skill provides a structured approach for planning and tracking complex feature implementations through systematic task decomposition. It helps break down large, multi-component features into manageable tasks with clear goals, dependencies, and success criteria.
Use this skill when:
Do NOT use this skill for:
IMPORTANT: This is a PHASED approach. Complete each phase BEFORE moving to the next.
Actions:
.plans/[feature-name]/ directory (in current project directory)assets/plan-template.md to .plans/[feature-name]/plan.md.plans/[feature-name]/tasks/ directory for task files[Feature Name] with your feature name in plan.mdTodoWrite tracks ONLY phases 1-4:
- [ ] Phase 1: Setup template with Research section
- [ ] Phase 2: Conduct research and iterate with user
- [ ] Phase 3: Finalize selected approach
- [ ] Phase 4: Create implementation tasks (T01-T0N)
Mark Phase 1 as completed in TodoWrite
Output: Skeleton plan document with Research section defined and todo list created for phases 1-4
Research Process (Iterative):
AskUserQuestion to clarify requirements and constraintsCRITICAL:
Mark Phase 2 as completed in TodoWrite when user confirms that research is complete
Output: Research with 2-3 Strategy Proposals documented and reviewed with user
Actions:
Mark Phase 3 as completed in TodoWrite once Selected Approach section is fully documented
Output: Research fully documented with clear decision and rationale
IMPORTANT: Before creating tasks, read references/task-planning-guide.md to understand:
Actions:
NOW create T01, T02, T03, ...T0N as separate files in .plans/[feature-name]/tasks/ based on selected approach
Step-by-Step: Creating a Task File
For each task you need to create:
cp [path-to-task-template.md] .plans/[feature-name]/tasks/T01.md
T0X with actual task number (T01, T02, etc.)- [ ] [**T01**: Task Name](tasks/T01.md) - Status: 🟡 PlannedMark Phase 4 as completed in TodoWrite
Output: Complete task breakdown (T01.md - T0N.md files) in tasks/ folder, all linked from plan.md Progress Summary
Note: Phase 5 is NOT tracked in TodoWrite. Track progress directly in task files and plan.md.
IMPORTANT: Before starting work on ANY task, read references/task-planning-guide.md for:
When to consult task-planning-guide.md:
CRITICAL RULE: Work on ONE task at a time. Do NOT start the next task until the current task is FULLY completed.
Task Status Flow:
Starting a Task:
references/task-planning-guide.md - Review relevant sections before beginning work**Status**: 🟢 **In Progress**- [ ] [**T01**: Task Name](tasks/T01.md) - Status: 🟢 In ProgressDuring Task Execution: 4. Work through Action Items, checking off boxes as you complete them:
- [x] Create API endpoint
- [x] Add request validation
- [ ] Add error handling ← Currently working here
- [ ] Write tests
Completing a Task:
7. Verify ALL action items are checked: [x]
8. Fill in "Execution Summary" section in task file:
## Execution Summary
**Completed**: 2025-01-08 14:30
**What was implemented**:
- Added /api/users endpoint with validation
- Implemented error handling for edge cases
**Challenges encountered**:
- Had to refactor auth middleware to support new endpoint
**Status**: ✅ **Completed**- [x] [**T01**: Task Name](tasks/T01.md) - Status: ✅ CompletedWhen completing T01, you must update BOTH locations:
In tasks/T01.md (lines 7-9):
**Status**: ✅ **Completed**
**Effort**: Medium
**Blocked By**: None
In plan.md Progress Summary (line ~18):
- [x] [**T01**: Add API endpoint](tasks/T01.md) - Status: ✅ Completed
Why dual-tracking?
If you cannot complete a task:
If you discover additional work during Phase 5:
T06.md) in tasks/ directoryRemember: ONE task at a time. Complete it FULLY (all checkboxes, both locations updated, Execution Summary filled), then ASK USER for confirmation before moving to the next.
Note: Phase 6 is NOT tracked in TodoWrite. Update the plan document directly.
After feature completion:
TodoWrite tracks ONLY phases 1-4 (not subtasks):
- [ ] Phase 1: Setup template with Research section
- [ ] Phase 2: Conduct research and iterate with user
- [ ] Phase 3: Finalize selected approach
- [ ] Phase 4: Create implementation tasks (T01-T0N)
Phase-by-Phase Workflow:
Phase 1 - Setup:
.plans/[feature-name]/ and .plans/[feature-name]/tasks/ directories.plans/[feature-name]/plan.mdPhase 2 - Research & Iterate (AskUserQuestion REQUIRED):
Phase 3 - Finalize:
Phase 4 - Create Tasks:
references/task-planning-guide.md before creating tasks.plans/[feature-name]/tasks/Phase 5 - Implementation (ONE task at a time):
references/task-planning-guide.md before starting EACH taskPhase 6 - Review:
During research phase, research existing similar features and match their architecture exactly. Benefit: Consistent codebase, faster implementation, reduced bugs.
During research, look for ways to simplify (e.g., avoid unnecessary API calls). Benefit: Reduced dependencies, better performance, easier maintenance.
Research phase may reveal the work is already done - mark task complete. Benefit: Avoids duplicate work, leverages tested code.
During research phase, use the "Selected Approach" section to document WHY you chose one approach over alternatives. Include: decision, rationale, key findings, and implementation plan. Benefit: Future developers understand rationale, prevents second-guessing, provides clear starting point.
Break large tasks into smaller chunks that are independently testable. Benefit: Steady progress, clear milestones, easier to parallelize.
CRITICAL: references/task-planning-guide.md is NOT just for planning - read it throughout implementation.
Read references/task-planning-guide.md:
Remember:
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 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 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.