Agent skill
idea-duc01226-easyplatform
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/idea-duc01226-easyplatform
SKILL.md
[IMPORTANT] Use
TaskCreateto break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI may ask user whether to skip.
Quick Summary
Goal: Capture raw product ideas as structured backlog artifacts with project module context.
MANDATORY IMPORTANT MUST Plan ToDo Task to READ the following project-specific reference doc:
project-structure-reference.md-- project patterns and structureIf file not found, search for: project documentation, coding standards, architecture docs.
Workflow:
- Gather Info — Ask about the idea, problem, value, and target users
- Generate Artifact — Create idea file with ID (IDEA-YYMMDD-NNN) and draft status
- Detect Module — Auto-match to project module, load feature context from docs
- Validate — Interview user to confirm problem statement, scope, stakeholders
- Suggest Next — Point to
/refinefor PBI creation
Key Rules:
- Output to
team-artifacts/ideas/{YYMMDD}-{role}-idea-{slug}.md - Validation step is mandatory, not optional
- Auto-detect module silently; only prompt when ambiguous
Idea Capture
Capture raw ideas as structured artifacts for backlog consideration.
When to Use
- User has new feature concept
- Stakeholder request needs documentation
- Quick capture without full refinement
Quick Reference
Workflow
- Activate
product-ownerskill - Gather idea details (problem, value, scope, target users)
- Generate artifact with ID and draft status
- Detect related project module (dynamic discovery)
- Load feature context from
docs/business-features/ - Save artifact to
team-artifacts/ideas/ - Validate idea (MANDATORY) - Interview user to confirm problem statement, scope, and stakeholders
- Suggest next:
/refine {idea-file}
Output
- Path:
team-artifacts/ideas/{YYMMDD}-{role}-idea-{slug}.md - ID Pattern:
IDEA-{YYMMDD}-{NNN}(sequential)
Related
- Role Skill:
product-owner - Command:
/idea - Next Step:
/refine
Template
See: team-artifacts/templates/idea-template.md
Detailed Workflow
Step 1: Gather Information
- If no title provided, ask: "What's the idea in one sentence?"
- Ask: "What problem does this solve?"
- Ask: "Who benefits from this?"
- Ask: "Any initial scope thoughts?"
Step 2: Generate Artifact
- Create idea file using template
- Generate ID:
IDEA-{YYMMDD}-{NNN}(sequential) - Set status:
draft
Step 3: Capture Details
- Document problem statement
- List expected value
- Identify target users
Step 4: Detect Project Module
Dynamic Discovery:
- Run:
Glob("docs/business-features/*/README.md") - Extract module names from paths (e.g., ServiceB, ServiceA, SupportingServices)
- Match idea keywords against module keywords (reference:
.claude/skills/shared/module-detection-keywords.md)
Detection Approach (silent auto-detect):
- Auto-detect without showing confidence levels
- Only prompt when ambiguous or no clear match
- Multi-module: Load ALL detected modules
If module detected:
- Read
docs/business-features/{module}/README.md(first 200 lines for overview) - Extract feature list from Quick Navigation section
- Add to idea frontmatter:
module: {detected_module}related_features: [Feature1, Feature2]
If ambiguous/not detected:
- Run Glob to get current module list
- Prompt: "Which project module?" + list Glob results + "Cross-cutting/Infrastructure"
Multi-module detection:
- If 2+ modules detected, load ALL modules (no primary prompt)
- Add all to
related_featureslist
Step 5: Load Feature Context
Once module detected:
- Read module README overview section (~2K tokens)
- Identify closest matching feature(s) from feature list
- Read corresponding feature doc or
.ai.mdfile (3-5K tokens) - Extract:
- Related entities
- Existing business rules (BR-{MOD}-XXX)
- Test case patterns (TC-{MOD}-XXX)
Token Budget: Target 8-12K tokens total for feature context.
Step 6: Save Artifact
- Path:
team-artifacts/ideas/{YYMMDD}-{role}-idea-{slug}.md - Role: Infer from context or ask
- Include domain context if detected
Step 7: Suggest Next Step
- Output: "Idea captured! To refine into a PBI, run:
/refine {filename}" - If domain module detected: "Module context from {module} will be used during refinement."
Validation Step (MANDATORY)
After capturing the idea, validate with user. This step is NOT optional.
Question Categories
| Category | Example Question |
|---|---|
| Problem | "Is the problem statement clear and user-focused?" |
| Value | "What's the expected business value or user benefit?" |
| Scope | "Any scope boundaries to clarify now?" |
| Stakeholders | "Who else should review this idea?" |
Process
- Generate 2-3 questions focused on problem clarity, scope, and stakeholders
- Use
AskUserQuestiontool to interview with specific questions:- "Is the problem statement clear and user-focused?"
- "Any scope boundaries to clarify now?"
- "Who else should review this idea?"
- Document in idea artifact under
## Validation Summary - Update idea based on answers
Validation Output Format
## Validation Summary
**Validated:** {date}
### Confirmed
- {decision}: {user choice}
### Action Items
- [ ] {follow-up if any}
Domain Context Output Format
When a project module is detected, include this section in the idea artifact:
## Domain Context (Project Features)
### Module
{module_name}
### Related Features
- {Feature1} - [docs link]
- {Feature2} - [docs link]
### Domain Entities
- **Primary:** {Entity1}, {Entity2}
- **Related:** {Entity3}
### Existing Business Rules
- BR-{MOD}-XXX: {Brief description}
Example
/idea "Dark mode toggle for settings"
Creates: team-artifacts/ideas/260119-po-idea-dark-mode-toggle.md
/idea "Add goal progress tracking notification"
Creates with ServiceB context: team-artifacts/ideas/260119-po-idea-goal-progress-notification.md
IMPORTANT Task Planning Notes (MUST FOLLOW)
- Always plan and break work into many small todo tasks
- Always add a final review todo task to verify work quality and identify fixes/enhancements
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?