Methodology for breaking specifications into actionable tasks organized by features. Use when creating task lists or orchestrating implementation.
/plugin marketplace add IvanTorresEdge/molcajete.ai/plugin install ivantorresedge-prd-prd@IvanTorresEdge/molcajete.aiThis skill inherits all available tools. When active, it can use any tool Claude has access to.
templates/tasks-template.mdUPMOST IMPORTANCE: The best path is the shortest to get working software that can be tested end-to-end.
Each feature delivers a complete user-facing capability that works across all application layers. Tasks are organized sequentially within each feature to achieve working, testable software as quickly as possible.
Feature Structure:
## 1. [ ] Users should be able to signup
- 1.1 [ ] Create user migrations
- 1.2 [ ] Add /signup end-point
- 1.3 [ ] Build user signup form
- 1.4 [ ] Add user signup form validations
- 1.5 [ ] Send signup confirmation email
- 1.6 [ ] Add /signup/confirmation/:confirmation_id end-point
- 1.6.1 [ ] Verify valid token
- 1.6.2 [ ] Throw error with expired tokens
- 1.6.3 [ ] Activate user account
- 1.7 [ ] Build user email confirmation page
## 2. [ ] Users should be able to login
- 2.1 [ ] Add /signin end-point
- 2.2 [ ] Build user sign-in form
- 2.3 [ ] Add user sign-in validations
- 2.4 [ ] Display "Lost password?" link after failed attempt
Good feature: "Users should be able to signup"
Bad feature: "All database migrations"
As you break down each feature, you'll typically encounter these types of tasks in logical sequence:
The key is to organize these in the shortest path to working software, not in separate sections.
Complexity Levels:
Red Flags:
Identify Dependencies:
Critical Path:
Parallel Opportunities:
CRITICAL: Follow template formatting exactly:
[ ] for incomplete, [x] for complete## N. [ ] Feature description- N.M [ ] Task description - N.M.K [ ] Subtask descriptionSee templates/ directory for:
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.