@pageai/ralph-loop 1.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.agent/PROMPT.md +58 -0
- package/.agent/STEERING.md +3 -0
- package/.agent/logs/LOG.md +13 -0
- package/.agent/prd/.gitkeep +0 -0
- package/.agent/screenshots/.gitkeep +0 -0
- package/.agent/skills/component-refactoring/SKILL.md +247 -0
- package/.agent/skills/component-refactoring/references/complexity-patterns.md +485 -0
- package/.agent/skills/component-refactoring/references/component-splitting.md +419 -0
- package/.agent/skills/component-refactoring/references/hook-extraction.md +317 -0
- package/.agent/skills/e2e-tester/SKILL.md +595 -0
- package/.agent/skills/frontend-code-review/SKILL.md +73 -0
- package/.agent/skills/frontend-code-review/references/code-quality.md +28 -0
- package/.agent/skills/frontend-code-review/references/performance.md +36 -0
- package/.agent/skills/frontend-testing/SKILL.md +316 -0
- package/.agent/skills/frontend-testing/assets/component-test.template.tsx +293 -0
- package/.agent/skills/frontend-testing/assets/hook-test.template.ts +207 -0
- package/.agent/skills/frontend-testing/assets/utility-test.template.ts +154 -0
- package/.agent/skills/frontend-testing/references/async-testing.md +345 -0
- package/.agent/skills/frontend-testing/references/checklist.md +188 -0
- package/.agent/skills/frontend-testing/references/common-patterns.md +449 -0
- package/.agent/skills/frontend-testing/references/mocking.md +289 -0
- package/.agent/skills/frontend-testing/references/workflow.md +265 -0
- package/.agent/skills/prd-creator/JSON.md +613 -0
- package/.agent/skills/prd-creator/PRD.md +196 -0
- package/.agent/skills/prd-creator/SKILL.md +143 -0
- package/.agent/skills/skill-creator/SKILL.md +355 -0
- package/.agent/skills/skill-creator/references/output-patterns.md +86 -0
- package/.agent/skills/skill-creator/references/workflows.md +28 -0
- package/.agent/skills/skill-creator/scripts/init_skill.py +300 -0
- package/.agent/skills/skill-creator/scripts/package_skill.py +110 -0
- package/.agent/skills/vercel-react-best-practices/AGENTS.md +2249 -0
- package/.agent/skills/vercel-react-best-practices/SKILL.md +125 -0
- package/.agent/skills/vercel-react-best-practices/rules/advanced-event-handler-refs.md +55 -0
- package/.agent/skills/vercel-react-best-practices/rules/advanced-use-latest.md +49 -0
- package/.agent/skills/vercel-react-best-practices/rules/async-api-routes.md +38 -0
- package/.agent/skills/vercel-react-best-practices/rules/async-defer-await.md +80 -0
- package/.agent/skills/vercel-react-best-practices/rules/async-dependencies.md +36 -0
- package/.agent/skills/vercel-react-best-practices/rules/async-parallel.md +28 -0
- package/.agent/skills/vercel-react-best-practices/rules/async-suspense-boundaries.md +99 -0
- package/.agent/skills/vercel-react-best-practices/rules/bundle-barrel-imports.md +59 -0
- package/.agent/skills/vercel-react-best-practices/rules/bundle-conditional.md +31 -0
- package/.agent/skills/vercel-react-best-practices/rules/bundle-defer-third-party.md +49 -0
- package/.agent/skills/vercel-react-best-practices/rules/bundle-dynamic-imports.md +35 -0
- package/.agent/skills/vercel-react-best-practices/rules/bundle-preload.md +50 -0
- package/.agent/skills/vercel-react-best-practices/rules/client-event-listeners.md +74 -0
- package/.agent/skills/vercel-react-best-practices/rules/client-swr-dedup.md +56 -0
- package/.agent/skills/vercel-react-best-practices/rules/js-batch-dom-css.md +82 -0
- package/.agent/skills/vercel-react-best-practices/rules/js-cache-function-results.md +80 -0
- package/.agent/skills/vercel-react-best-practices/rules/js-cache-property-access.md +28 -0
- package/.agent/skills/vercel-react-best-practices/rules/js-cache-storage.md +70 -0
- package/.agent/skills/vercel-react-best-practices/rules/js-combine-iterations.md +32 -0
- package/.agent/skills/vercel-react-best-practices/rules/js-early-exit.md +50 -0
- package/.agent/skills/vercel-react-best-practices/rules/js-hoist-regexp.md +45 -0
- package/.agent/skills/vercel-react-best-practices/rules/js-index-maps.md +37 -0
- package/.agent/skills/vercel-react-best-practices/rules/js-length-check-first.md +49 -0
- package/.agent/skills/vercel-react-best-practices/rules/js-min-max-loop.md +82 -0
- package/.agent/skills/vercel-react-best-practices/rules/js-set-map-lookups.md +24 -0
- package/.agent/skills/vercel-react-best-practices/rules/js-tosorted-immutable.md +57 -0
- package/.agent/skills/vercel-react-best-practices/rules/rendering-activity.md +26 -0
- package/.agent/skills/vercel-react-best-practices/rules/rendering-animate-svg-wrapper.md +47 -0
- package/.agent/skills/vercel-react-best-practices/rules/rendering-conditional-render.md +40 -0
- package/.agent/skills/vercel-react-best-practices/rules/rendering-content-visibility.md +38 -0
- package/.agent/skills/vercel-react-best-practices/rules/rendering-hoist-jsx.md +46 -0
- package/.agent/skills/vercel-react-best-practices/rules/rendering-hydration-no-flicker.md +82 -0
- package/.agent/skills/vercel-react-best-practices/rules/rendering-svg-precision.md +28 -0
- package/.agent/skills/vercel-react-best-practices/rules/rerender-defer-reads.md +39 -0
- package/.agent/skills/vercel-react-best-practices/rules/rerender-dependencies.md +45 -0
- package/.agent/skills/vercel-react-best-practices/rules/rerender-derived-state.md +29 -0
- package/.agent/skills/vercel-react-best-practices/rules/rerender-functional-setstate.md +74 -0
- package/.agent/skills/vercel-react-best-practices/rules/rerender-lazy-state-init.md +58 -0
- package/.agent/skills/vercel-react-best-practices/rules/rerender-memo.md +44 -0
- package/.agent/skills/vercel-react-best-practices/rules/rerender-transitions.md +40 -0
- package/.agent/skills/vercel-react-best-practices/rules/server-after-nonblocking.md +73 -0
- package/.agent/skills/vercel-react-best-practices/rules/server-cache-lru.md +41 -0
- package/.agent/skills/vercel-react-best-practices/rules/server-cache-react.md +26 -0
- package/.agent/skills/vercel-react-best-practices/rules/server-parallel-fetching.md +79 -0
- package/.agent/skills/vercel-react-best-practices/rules/server-serialization.md +38 -0
- package/.agent/skills/vitest-best-practices/AGENTS.md +84 -0
- package/.agent/skills/vitest-best-practices/SKILL.md +130 -0
- package/.agent/skills/vitest-best-practices/references/aaa-pattern.md +260 -0
- package/.agent/skills/vitest-best-practices/references/assertions.md +393 -0
- package/.agent/skills/vitest-best-practices/references/async-testing.md +454 -0
- package/.agent/skills/vitest-best-practices/references/error-handling.md +382 -0
- package/.agent/skills/vitest-best-practices/references/organization.md +212 -0
- package/.agent/skills/vitest-best-practices/references/parameterized-tests.md +297 -0
- package/.agent/skills/vitest-best-practices/references/performance.md +528 -0
- package/.agent/skills/vitest-best-practices/references/snapshot-testing.md +483 -0
- package/.agent/skills/vitest-best-practices/references/test-doubles.md +499 -0
- package/.agent/skills/vitest-best-practices/references/vitest-features.md +529 -0
- package/.agent/skills/web-design-guidelines/SKILL.md +39 -0
- package/.agent/tasks/.gitkeep +0 -0
- package/.agent/tasks.json +1 -0
- package/.claude/agents/code-reviewer.md +172 -0
- package/.claude/commands/aw.md +50 -0
- package/.claude/hooks/play-sound.js +87 -0
- package/.claude/hooks/pre-tool-use.js +40 -0
- package/.claude/settings.json +54 -0
- package/.claude/settings.local.json +13 -0
- package/.mcp.json +31 -0
- package/AGENTS.md +44 -0
- package/CLAUDE.md +1 -0
- package/README.md +236 -0
- package/bin/cli.js +156 -0
- package/bin/lib/copy.js +149 -0
- package/bin/lib/display.js +137 -0
- package/package.json +65 -0
- package/ralph.sh +333 -0
- package/scripts/lib/args.sh +44 -0
- package/scripts/lib/cleanup.sh +53 -0
- package/scripts/lib/constants.sh +25 -0
- package/scripts/lib/display.sh +196 -0
- package/scripts/lib/logging.sh +30 -0
- package/scripts/lib/notify.sh +41 -0
- package/scripts/lib/output.sh +147 -0
- package/scripts/lib/preflight.sh +57 -0
- package/scripts/lib/preview.sh +77 -0
- package/scripts/lib/promise.sh +76 -0
- package/scripts/lib/spinner.sh +85 -0
- package/scripts/lib/terminal.sh +57 -0
- package/scripts/lib/timing.sh +223 -0
|
@@ -0,0 +1,196 @@
|
|
|
1
|
+
# PRD Creation Through Structured Questioning
|
|
2
|
+
|
|
3
|
+
Help beginner-level developers transform software ideas into comprehensive PRD.md files through structured questioning.
|
|
4
|
+
|
|
5
|
+
## Conversation Flow
|
|
6
|
+
|
|
7
|
+
1. Introduce yourself briefly and explain you'll ask clarifying questions before creating a PRD
|
|
8
|
+
2. Ask questions one at a time conversationally
|
|
9
|
+
3. Focus 70% on understanding the concept, 30% on educating about options
|
|
10
|
+
4. Keep tone friendly and supportive, use plain language
|
|
11
|
+
5. Track assumptions throughout - they'll go in the PRD
|
|
12
|
+
|
|
13
|
+
## Topics to Cover
|
|
14
|
+
|
|
15
|
+
Gather information on these aspects:
|
|
16
|
+
|
|
17
|
+
1. Core features and functionality
|
|
18
|
+
2. Target audience
|
|
19
|
+
3. Platform (web, mobile, desktop)
|
|
20
|
+
4. User flows (how users move through the app)
|
|
21
|
+
5. UI/UX concepts
|
|
22
|
+
6. Data storage and management
|
|
23
|
+
7. Authentication (if relevant) and security
|
|
24
|
+
8. Third-party integrations (if relevant)
|
|
25
|
+
9. [optional] Wireframes or diagrams
|
|
26
|
+
10. [optional] Competitive landscape
|
|
27
|
+
11. Dependencies
|
|
28
|
+
|
|
29
|
+
## Questioning Patterns
|
|
30
|
+
|
|
31
|
+
- Start broad: "Tell me about your app idea at a high level"
|
|
32
|
+
- Core features: "What are the 3-5 core features that make this valuable?"
|
|
33
|
+
- Priorities: "Which features are must-haves for the initial version?"
|
|
34
|
+
- User journeys: "Walk me through what a user does from opening the app to completing their main goal"
|
|
35
|
+
- Competition: "What similar products exist? What should yours do differently?"
|
|
36
|
+
- Assumptions: "What are you assuming about your users, technology, or market?"
|
|
37
|
+
- Wireframes: "Can you explain the flow and what happens when users interact with each screen?"
|
|
38
|
+
- Reflective: "So if I understand correctly, you're building [summary]. Is that accurate?"
|
|
39
|
+
|
|
40
|
+
## Technology Discussions
|
|
41
|
+
|
|
42
|
+
- Provide 3-4 options with pros/cons
|
|
43
|
+
- Give your best recommendation with brief reasoning
|
|
44
|
+
- Stay conceptual, not deeply technical
|
|
45
|
+
- Proactively suggest technologies the idea requires
|
|
46
|
+
- If the user provides technology preferences, use them to guide your recommendations
|
|
47
|
+
- Use AskUserQuestion tool to ask about a11y
|
|
48
|
+
*NB:* only include a11y tasks if the user request it. Keep in mind what they build might not have a UI or be a prototype.
|
|
49
|
+
- Use AskUserQuestion tool to ask about performance considerations
|
|
50
|
+
*NB:* only include performance tasks if the user request it. Keep in mind what they build might not have a UI or be a prototype.
|
|
51
|
+
|
|
52
|
+
**Example**: "For this app, you could use React Native (cross-platform, faster development) or native development (better performance, device integration). Given your need for camera integration and offline support, I'd recommend native development."
|
|
53
|
+
|
|
54
|
+
## PRD Creation Workflow
|
|
55
|
+
|
|
56
|
+
**CRITICAL**: Don't create the PRD until you have all necessary information, including needed libraries, frameworks, 3rd party integrations, etc. Use AskUserQuestion tool multiple times to clarify specs, technology choices, and requirements.
|
|
57
|
+
|
|
58
|
+
Copy and track progress through these steps:
|
|
59
|
+
|
|
60
|
+
```
|
|
61
|
+
PRD Progress:
|
|
62
|
+
- [ ] Gather all required information via questioning
|
|
63
|
+
- [ ] Create executive summary for user validation
|
|
64
|
+
- [ ] Get user confirmation to proceed
|
|
65
|
+
- [ ] Research competitive landscape (if not done)
|
|
66
|
+
- [ ] Generate comprehensive PRD
|
|
67
|
+
- [ ] Present and gather feedback
|
|
68
|
+
- [ ] Iterate based on feedback
|
|
69
|
+
```
|
|
70
|
+
|
|
71
|
+
### Step 1: Gather Information
|
|
72
|
+
|
|
73
|
+
Use AskUserQuestion tool repeatedly to clarify:
|
|
74
|
+
- Core features that are unclear
|
|
75
|
+
- Technology options and user preferences
|
|
76
|
+
- Priorities between conflicting requirements
|
|
77
|
+
- Any assumptions that could significantly impact the PRD
|
|
78
|
+
|
|
79
|
+
Ask related questions per tool call for efficiency. Provide 3-4 clear options per question with trade-off descriptions. Mark recommended options with "(Recommended)".
|
|
80
|
+
|
|
81
|
+
### Step 2: Executive Summary Validation
|
|
82
|
+
|
|
83
|
+
Before writing the full PRD:
|
|
84
|
+
1. Summarize in 2-3 paragraphs: problem solved, target users, core value proposition, key features, key user flows
|
|
85
|
+
2. List main assumptions you're making
|
|
86
|
+
3. Ask: "Does this accurately capture your vision? Should I proceed with the full PRD?"
|
|
87
|
+
4. **Only continue after confirmation**
|
|
88
|
+
|
|
89
|
+
### Step 3: Competitive Research
|
|
90
|
+
|
|
91
|
+
If this is a commercial app with a potential revenue model, you should research the competitive landscape to identify differentiators and opportunities.
|
|
92
|
+
|
|
93
|
+
Use WebSearch to:
|
|
94
|
+
- Find similar products: "[app category] apps 2026", "best [problem space] tools"
|
|
95
|
+
- Identify differentiators
|
|
96
|
+
- Use the findings to further refine the PRD
|
|
97
|
+
- For each identified differentiator, use the AskUserQuestion tool to clarify if it should be included in the PRD
|
|
98
|
+
|
|
99
|
+
### Step 4: Generate PRD
|
|
100
|
+
|
|
101
|
+
Create PRD containing all identified requirements and use an ID to track each requirement, formatted as `TASK-${ID}`.
|
|
102
|
+
|
|
103
|
+
Include the following sections:
|
|
104
|
+
- App overview, objectives and success criteria
|
|
105
|
+
- Short summary of target audience
|
|
106
|
+
- (for commercial apps): Competitive landscape and differentiation
|
|
107
|
+
- Core features and functionality
|
|
108
|
+
- Key user flows and journeys
|
|
109
|
+
- Technical stack recommendations
|
|
110
|
+
- Conceptual data model
|
|
111
|
+
- UI design principles (include wireframe analysis if provided)
|
|
112
|
+
- Security considerations
|
|
113
|
+
- Development phases/milestones
|
|
114
|
+
- Assumptions and dependencies
|
|
115
|
+
- Potential challenges and solutions
|
|
116
|
+
- Future expansion possibilities
|
|
117
|
+
|
|
118
|
+
Save as: `PROJECT_ROOT/.agent/prd/PRD.md`
|
|
119
|
+
|
|
120
|
+
### Step 5: Iterate
|
|
121
|
+
|
|
122
|
+
Ask specific questions about sections rather than general feedback. Use Sequential Thinking for systematic feedback processing. Present revised version with change explanations.
|
|
123
|
+
|
|
124
|
+
## Developer Handoff Guidelines
|
|
125
|
+
|
|
126
|
+
Optimize for handoff to engineers (human or AI):
|
|
127
|
+
|
|
128
|
+
- Include implementation details without prescriptive code
|
|
129
|
+
- Define clear acceptance criteria per feature
|
|
130
|
+
- Use terminology mappable to code components
|
|
131
|
+
- Structure data models with explicit field names, types, relationships
|
|
132
|
+
- Specify technical constraints and API integration points
|
|
133
|
+
- Organize features in logical sprint groupings
|
|
134
|
+
- Include pseudocode for complex features
|
|
135
|
+
- Link to relevant technology documentation
|
|
136
|
+
|
|
137
|
+
## Specification Examples
|
|
138
|
+
|
|
139
|
+
**Feature Specification:**
|
|
140
|
+
```
|
|
141
|
+
User Authentication Feature:
|
|
142
|
+
- Support email/password and OAuth 2.0 (Google, Apple) login methods
|
|
143
|
+
- Implement JWT token-based session management
|
|
144
|
+
- Required user profile fields: email (string, unique), name (string), avatar (image URL)
|
|
145
|
+
- Acceptance criteria: Users can create accounts, log in via both methods, recover passwords, and maintain persistent sessions across app restarts
|
|
146
|
+
```
|
|
147
|
+
|
|
148
|
+
**User Flow:**
|
|
149
|
+
```
|
|
150
|
+
Content Creation Flow:
|
|
151
|
+
1. User clicks 'Create' button on dashboard
|
|
152
|
+
2. User selects content type (text post, image, video)
|
|
153
|
+
3. User fills in content details (title, description, tags)
|
|
154
|
+
4. User previews content before publishing
|
|
155
|
+
5. User clicks 'Publish' → Content appears in their profile feed
|
|
156
|
+
6. User can share via native share sheet (iOS/Android) or copy link (Web)
|
|
157
|
+
- Error states: Handle upload failures, size limits exceeded, network timeouts
|
|
158
|
+
```
|
|
159
|
+
|
|
160
|
+
## Wireframe Analysis
|
|
161
|
+
|
|
162
|
+
When users provide wireframes or mockups:
|
|
163
|
+
|
|
164
|
+
1. Use Read tool to view image files
|
|
165
|
+
2. For each screen, identify:
|
|
166
|
+
- UI components (buttons, forms, navigation)
|
|
167
|
+
- User interactions (taps, swipes, submissions)
|
|
168
|
+
- State changes on interaction
|
|
169
|
+
- Navigation flow between screens
|
|
170
|
+
- Data sources
|
|
171
|
+
3. Ask clarifying questions via AskUserQuestion tool:
|
|
172
|
+
- "What happens when the user clicks [element]?"
|
|
173
|
+
- "Where does [data/content] come from?"
|
|
174
|
+
- "What error states should we handle?"
|
|
175
|
+
4. Include insights in PRD's "UI Design Principles" section
|
|
176
|
+
5. Map to user flows in "Key User Flows" section
|
|
177
|
+
|
|
178
|
+
## After PRD Completion
|
|
179
|
+
|
|
180
|
+
Once the PRD is complete and approved, inform the user:
|
|
181
|
+
"Your PRD is complete and saved. Would you like me to proceed to the next step and generate implementation tasks for developers? See [JSON.md](JSON.md)."
|
|
182
|
+
|
|
183
|
+
**CRITICAL**: Make the plan extremely concise. Sacrifice grammar for the sake of concision.
|
|
184
|
+
|
|
185
|
+
---
|
|
186
|
+
|
|
187
|
+
## Checklist
|
|
188
|
+
|
|
189
|
+
Before saving the PRD:
|
|
190
|
+
|
|
191
|
+
- [ ] Asked clarifying questions with lettered options
|
|
192
|
+
- [ ] Incorporated user's answers
|
|
193
|
+
- [ ] User stories are small and specific
|
|
194
|
+
- [ ] Functional requirements are numbered and unambiguous
|
|
195
|
+
- [ ] Non-goals section defines clear boundaries
|
|
196
|
+
- [ ] Saved to `PROJECT_ROOT/.agent/prd/PRD.md`
|
|
@@ -0,0 +1,143 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: prd-creator
|
|
3
|
+
description: Guides creation of comprehensive Product Requirement Documents (PRDs) for software projects through structured questioning and validation, then generates implementation task lists in JSON format. Use when users want to document a software idea, create specifications for development, plan a new application feature/bug, or break down requirements into actionable tasks. Transforms ideas into implementation-ready documents with verifiable pass criteria.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# PRD Creation Assistant
|
|
7
|
+
|
|
8
|
+
Transform software ideas into comprehensive PRDs and actionable implementation tasks through a two-part process.
|
|
9
|
+
|
|
10
|
+
## Overview
|
|
11
|
+
|
|
12
|
+
This skill helps beginner-level developers.
|
|
13
|
+
|
|
14
|
+
1. Receive an implementation description from the user
|
|
15
|
+
2. Create detailed PRD documents through structured questioning
|
|
16
|
+
3. Generate implementation task lists in JSON format for developers
|
|
17
|
+
4. Write an overall description of the project. An executive summary that gives a high level overview of the app and its main features.
|
|
18
|
+
|
|
19
|
+
### Part 1: Implementation Description
|
|
20
|
+
|
|
21
|
+
You will receive a lacking implementation description from the user.
|
|
22
|
+
The main goal is to comprehend the intent and think about the larger architecture and a robust way to implement it, filling in the gaps.
|
|
23
|
+
|
|
24
|
+
### Part 2: PRD Creation
|
|
25
|
+
|
|
26
|
+
**File**: [PRD.md](PRD.md)
|
|
27
|
+
|
|
28
|
+
You will need to ask clarifying questions to get a clear understanding of the implementation.
|
|
29
|
+
|
|
30
|
+
**When to use**: User wants to document a software idea or create feature specifications
|
|
31
|
+
|
|
32
|
+
**What it does**:
|
|
33
|
+
- Guides structured questioning to gather all requirements
|
|
34
|
+
- Creates executive summary for validation
|
|
35
|
+
- Researches competitive landscape
|
|
36
|
+
- Generates comprehensive PRD.md with:
|
|
37
|
+
- App overview and objectives
|
|
38
|
+
- Target audience
|
|
39
|
+
- Success metrics and KPIs
|
|
40
|
+
- Competitive analysis
|
|
41
|
+
- Core features and user flows
|
|
42
|
+
- Technical stack recommendations
|
|
43
|
+
- Security considerations
|
|
44
|
+
- Assumptions and dependencies
|
|
45
|
+
|
|
46
|
+
**Process**:
|
|
47
|
+
1. Ask clarifying questions using `AskUserQuestion` tool
|
|
48
|
+
2. Create executive summary for user approval
|
|
49
|
+
3. Research competition via WebSearch
|
|
50
|
+
4. Generate complete PRD
|
|
51
|
+
5. Iterate based on feedback
|
|
52
|
+
|
|
53
|
+
**Read [PRD.md](PRD.md) for complete instructions.**
|
|
54
|
+
|
|
55
|
+
---
|
|
56
|
+
|
|
57
|
+
### Part 3: Implementation Task Generation
|
|
58
|
+
|
|
59
|
+
**File**: [JSON.md](JSON.md)
|
|
60
|
+
|
|
61
|
+
You will need to analyze the completed PRD and generate a comprehensive task list in JSON format.
|
|
62
|
+
|
|
63
|
+
**When to use**: After PRD is complete and approved, or user requests task breakdown
|
|
64
|
+
|
|
65
|
+
**What it does**:
|
|
66
|
+
- Analyzes the completed PRD
|
|
67
|
+
- Generates a complete list of implementation tasks in JSON format, covering all features and requirements from the PRD
|
|
68
|
+
- Keeps the tasks small and manageable
|
|
69
|
+
- Categorizes tasks by type (functional, ui-ux, api-endpoint, security, etc.)
|
|
70
|
+
- Defines verification ('pass') steps for each task
|
|
71
|
+
- Creates developer-ready checklist
|
|
72
|
+
|
|
73
|
+
**IMPORTANT**:
|
|
74
|
+
- Each task should be simple enough to be completed in maximum 10 minutes.
|
|
75
|
+
- If a task is too complex, it should be split into smaller tasks.
|
|
76
|
+
|
|
77
|
+
**Read [JSON.md](JSON.md) for complete instructions.**
|
|
78
|
+
|
|
79
|
+
## Part 4: Overall Description
|
|
80
|
+
|
|
81
|
+
You will need to read the completed PRD and generate an overall description of the project in `PROJECT_ROOT/.agent/prd/SUMMARY.md`.
|
|
82
|
+
|
|
83
|
+
The description should be short, concise and contain:
|
|
84
|
+
- An overall description of the project
|
|
85
|
+
- The main features of the app
|
|
86
|
+
- Key user flows
|
|
87
|
+
- A short list of key requirements
|
|
88
|
+
|
|
89
|
+
## Quick Start
|
|
90
|
+
|
|
91
|
+
**If user wants to create a PRD:**
|
|
92
|
+
1. Read [PRD.md](PRD.md)
|
|
93
|
+
2. Follow the PRD creation workflow
|
|
94
|
+
3. If needed, update the overall description [SUMMARY.md](SUMMARY.md)
|
|
95
|
+
4. After PRD completion, ask: "Would you like me to generate implementation tasks? See Part 2."
|
|
96
|
+
|
|
97
|
+
**If user wants implementation tasks for an existing PRD:**
|
|
98
|
+
1. Read [JSON.md](JSON.md)
|
|
99
|
+
2. Read the PRD file
|
|
100
|
+
3. Generate comprehensive task list in JSON format
|
|
101
|
+
4. Save as `tasks.json`
|
|
102
|
+
|
|
103
|
+
**If user wants both:**
|
|
104
|
+
1. Complete PRD creation first [PRD.md](PRD.md)
|
|
105
|
+
2. Get user approval on PRD
|
|
106
|
+
3. If needed, update the overall description [SUMMARY.md](SUMMARY.md)
|
|
107
|
+
4. Proceed to generate implementation tasks [JSON.md](JSON.md)
|
|
108
|
+
|
|
109
|
+
**If a user want to update the PRD:**
|
|
110
|
+
1. Read [PRD.md](PRD.md)
|
|
111
|
+
2. Update the PRD
|
|
112
|
+
3. Save as `PRD.md`
|
|
113
|
+
4. If needed, update the overall description [SUMMARY.md](SUMMARY.md)
|
|
114
|
+
5. Ask user if they want to generate implementation tasks
|
|
115
|
+
|
|
116
|
+
**If a user want to update the implementation tasks:**
|
|
117
|
+
1. Read [JSON.md](JSON.md)
|
|
118
|
+
2. Update the implementation tasks
|
|
119
|
+
3. Save as `tasks.json`
|
|
120
|
+
4. Ask user if they want to update the PRD again
|
|
121
|
+
|
|
122
|
+
**If user wants to update both the PRD and the implementation tasks:**
|
|
123
|
+
1. Update the PRD first [PRD.md](PRD.md)
|
|
124
|
+
2. If needed, update the overall description [SUMMARY.md](SUMMARY.md)
|
|
125
|
+
3. Update the implementation tasks [JSON.md](JSON.md)
|
|
126
|
+
4. Save as `PRD.md` and `tasks.json`
|
|
127
|
+
|
|
128
|
+
## After completion
|
|
129
|
+
|
|
130
|
+
Ensure the required files are present:
|
|
131
|
+
- PROJECT_ROOT/.agent/prd/PRD.md
|
|
132
|
+
- PROJECT_ROOT/.agent/prd/SUMMARY.md
|
|
133
|
+
- PROJECT_ROOT/.agent/tasks.json
|
|
134
|
+
|
|
135
|
+
If they are not present, warn the user and ask if they would like to create any of them.
|
|
136
|
+
|
|
137
|
+
## Important Constraints
|
|
138
|
+
|
|
139
|
+
- Do not generate code - focus on documentation and task specification
|
|
140
|
+
- Use AskUserQuestion extensively in Part 1 to clarify requirements
|
|
141
|
+
- In Part 2, generate comprehensive task lists (50-200+ tasks for typical projects)
|
|
142
|
+
- Always initialize tasks with `"passes": false` - never mark tasks complete during generation
|
|
143
|
+
- Use available tools: AskUserQuestion, WebSearch, Sequential Thinking, Read
|