Cursor rule

1---
2description: "Guide for creating detailed task lists from PRDs and tech specs, including complexity analysis and phased generation workflow"
3globs:
4alwaysApply: false
5---
6# Rule: Generating a Task List from a PRD
7 
8<goal>
9To guide an AI assistant in creating a detailed, step-by-step task list in Markdown format based on an existing Product Requirements Document (PRD `.md`) and its corresponding Technical Specification document (tech spec `.md`). The task list should guide a developer through implementation following both functional requirements and architectural decisions.
10</goal>
11 
12<source_of_truth_policy>
13**SINGLE SOURCE OF TRUTH: Taskmaster JSON**
14- `tasks.json` (generated by taskmaster) is the authoritative task store
15- `_tasks.md` and individual `<num>_task.md` files are **generated views** from the JSON
16- All task status updates, modifications, and tracking must be done through taskmaster MCP tools
17- Markdown files are for human readability and should be regenerated when JSON changes
18- Never manually edit Markdown task files - use taskmaster commands for all task operations
19</source_of_truth_policy>
20 
21<output_specification>
22- **Format:** Markdown (`.md`)
23- **Locations:**
24  - **Feature folder:** `/tasks/prd-[feature-slug]/`
25  - **Tasks summary file:** `/tasks/prd-[feature-slug]/_tasks.md` (generated from JSON)
26  - **Individual task files:** `/tasks/prd-[feature-slug]/<num>_task.md` (generated from JSON)
27  - **Authoritative source:** `/tasks/prd-[feature-slug]/tasks.json` (taskmaster managed)
28  - **Complexity report:** `/tasks/prd-[feature-slug]/task-complexity-report.json`
29  - **Merged file:** `/tasks/prd-[feature-slug]/merged_prd_techspec.md`
30</output_specification>
31 
32## Process
33 
34<process_steps>
351.  **Receive PRD Reference:** The user points the AI to a specific PRD file
362.  **Verify Tech Spec:** Confirm that a corresponding tech spec document exists (`tasks/prd-[feature-slug]/_techspec.md`). If not, remind the user to create it using [prd-tech-spec.mdc](mdc:.cursor/rules/prd-tech-spec.mdc) before proceeding with task generation.
373.  **Generate Merged File:** Run `mf ./tasks/prd-[feature-slug]` to generate a merged file containing the PRD + techspec (`merged_prd_techspec.md`)
384.  **Create Taskmaster Tag:** Using the taskmaster MCP, create a tag for this feature implementation
395.  **Generate Taskmaster Tasks:** Use taskmaster's parse-prd functionality with the merged file to generate the initial task structure (`tasks.json`)
406.  **Generate Complexity Report:** Use taskmaster to analyze task complexity and generate the complexity report (`task-complexity-report.json`)
417.  **Generate Tasks Summary:** Based on the taskmaster output and complexity analysis, create the `_tasks.md` file following the established format
428.  **Parallel Agent Analysis:** ⚠️**MUST**: For each task under the prd-[slug], <critical>spin up parallel agents</critical> to provide a final analysis. Check based on the current architecture and files if we are duplicating stuff or forgetting something - a general analysis using our current architecture as review before starting the tasks
439.  **Wait for Confirmation:** Present the analysis results to the user and inform them: "I have completed the task generation and architectural analysis. Ready to proceed with implementation? Respond with 'Go' to start."
4410. **Generate Individual Task Files:** Create separate files for each parent task in `/tasks/prd-[feature-slug]/<num>_task.md`
45</process_steps>
46 
47<taskmaster_integration>
48**Taskmaster Workflow:**
491. **Tag Creation:** Create a new tag using taskmaster MCP for the feature (e.g., `memory-system-v1`)
502. **Parse PRD:** Use `parse-prd` with the merged file to generate initial task structure
513. **Complexity Analysis:** Generate complexity report to identify tasks requiring subdivision
524. **Task Export:** Export tasks in the required format for integration with existing workflow
53 
54**Key Commands:**
55- `mf ./tasks/prd-[feature-slug]` - Generate merged PRD + techspec file
56- Taskmaster tag creation for feature isolation
57- `parse-prd=<merged_file>` - Generate initial task structure
58- Complexity analysis for task breakdown recommendations
59</taskmaster_integration>
60 
61<parallel_analysis_requirements>
62**Critical Parallel Agent Analysis:**
63For each task identified in the prd-[slug], you MUST spin up parallel agents to conduct:
64 
651. **Architecture Duplication Check:** Identify if the task duplicates existing functionality
662. **Missing Component Analysis:** Check if the task overlooks existing architectural patterns
673. **Integration Point Validation:** Verify the task properly integrates with current systems
684. **Dependency Analysis:** Ensure all required dependencies are identified and accounted for
695. **Standards Compliance:** Verify the task follows established project patterns and standards
70 
71**Analysis Output:** Each parallel agent should provide:
72- Duplication risks and recommendations
73- Missing components or integration points
74- Architectural alignment assessment
75- Dependency validation results
76- Standards compliance verification
77</parallel_analysis_requirements>
78 
79## Output Format
80 
81### Tasks Summary File Format
82<tasks_summary_format>
83The tasks summary file (`_tasks.md`) serves as the central index for the feature implementation, containing the relevant files and parent task checklist. This file should be generated AFTER the taskmaster analysis and parallel agent review.
84</tasks_summary_format>
85 
86### Individual Task File Format
87<individual_task_format>
88Each individual task file (`<num>_task.md`) must follow this structure:
89 
90```markdown
91---
92status: pending  # Options: pending, in-progress, completed, excluded
93---
94 
95<task_context>
96<domain>engine/infra/[subdomain]</domain>
97<type>implementation|integration|testing|documentation</type>
98<scope>core_feature|middleware|configuration|performance</scope>
99<complexity>low|medium|high</complexity>
100<dependencies>external_apis|database|temporal|http_server</dependencies>
101</task_context>
102 
103# Task X.0: [Parent Task Title]
104 
105## Overview
106[Brief description of what this task accomplishes]
107 
108<critical>
109**MANDATORY REQUIREMENTS:**
110- **ALWAYS** check dependent files APIs before write tests to avoid write wrong code
111- **ALWAYS** verify against PRD and tech specs - NEVER make assumptions
112- **NEVER** use workarounds, especially in tests - implement proper solutions
113- **MUST** follow all established project standards:
114    - Architecture patterns: `.cursor/rules/architecture.mdc`
115    - Go coding standards: `.cursor/rules/go-coding-standards.mdc`
116    - Testing requirements: `.cursor/rules/testing-standards.mdc`
117    - API standards: `.cursor/rules/api-standards.mdc`
118    - Security & quality: `.cursor/rules/quality-security.mdc`
119- **MUST** run `make lint` and `make test` before completing ANY subtask
120- **MUST** follow `.cursor/rules/task-review.mdc` workflow for parent tasks
121**Enforcement:** Violating these standards results in immediate task rejection.
122</critical>
123 
124## Subtasks
125 
126- [ ] X.1 [Subtask description]
127- [ ] X.2 [Subtask description]
128- [ ] X.3 [Subtask description]
129 
130## Implementation Details
131 
132[Extract relevant sections from the tech spec that apply to this task]
133 
134### Relevant Files
135 
136> List of relevant files that this task will touch
137 
138### Dependent Files
139 
140> List of dependencies that this task will need to handle
141 
142## Success Criteria
143- [Clear definition of when this task is complete]
144- [Measurable outcomes]
145- [Quality requirements]
146- [Components impacted by this task per Tech Spec Impact Analysis]
147```
148</individual_task_format>
149 
150### Tasks File Format
151<tasks_file_format>
152The tasks file (`_tasks.md`) must follow this structure and be generated AFTER taskmaster analysis:
153 
154```markdown
155# [Feature] Implementation Task Summary
156 
157## Relevant Files
158 
159### Core Implementation Files
160- `path/to/file.go` - Description
161- `path/to/file_test.go` - Tests
162 
163### Integration Points
164- `path/to/integration.go` - Description
165 
166### Documentation Files
167- `docs/feature.md` - User documentation
168 
169### Notes
170 
171- Unit tests should be placed alongside the implementation files (e.g., `monitoring.go` and `monitoring_test.go` in the same directory)
172- Use `go test ./...` to run all tests or `go test -v ./path/to/package` for specific package tests
173- Always run `make fmt && make lint && make test` before committing changes
174- Follow project testing standards with `t.Run("Should...")` pattern
175 
176## Tasks
177 
178- [ ] 1.0 Parent Task Title
179- [ ] 2.0 Parent Task Title
180- [ ] 3.0 Parent Task Title
181```
182</tasks_file_format>
183 
184## Interaction Model
185 
186<interaction_model>
187**Workflow with Clear Source of Truth Management:**
188 
1891. **After Merged File Generation**: Verify the merged file contains both PRD and techspec content
1902. **After Taskmaster Analysis**: Review the generated tasks.json (authoritative) and complexity report
1913. **After Parallel Agent Analysis**: Review architectural analysis results from all parallel agents
1924. **Generate Markdown Views**: Create `_tasks.md` and individual task files from the authoritative JSON
1935. **Before Implementation**: Get user confirmation ("Go") after presenting complete analysis
194 
195**Critical Workflow Notes:**
196- All task modifications use taskmaster MCP tools (never edit Markdown directly)
197- Markdown files are regenerated whenever JSON changes
198- Task status tracking happens through taskmaster commands
199- Individual task files are created from JSON for development reference
200</interaction_model>
201 
202<target_audience>
203Assume the primary reader of the task list is a **junior developer** who will implement the feature, supported by the architectural analysis from parallel agents.
204</target_audience>
205 
206**Tag Creation Policy:**
207- **Automatic Tag Creation**: For features with >5 parent tasks or high complexity score (>7), create a tag automatically
208- **Suggested Tag Creation**: For smaller features (≤5 tasks, complexity ≤7), suggest tag creation to user but don't force
209- **Tag Naming**: Use format `[feature-slug]-v1` for consistency
210- **Integration**: Tags isolate feature work and enable focused development cycles
211