Skill for systematic requirements capture, decomposition, and traceability
Systematically captures, decomposes, and traces mechanical design requirements to ensure verifiable design intent.
npx claudepluginhub a5c-ai/babysitterThis skill is limited to using the following tools:
The Requirements Flow-Down skill provides systematic capabilities for capturing, decomposing, and tracing requirements throughout the mechanical design process, ensuring design intent is properly communicated and verified.
Level 1: Stakeholder Requirements
- What the customer/user needs
- High-level, solution-independent
- Source: Customer specifications, standards
Level 2: System Requirements
- What the system must do
- Allocated from stakeholder requirements
- Source: System engineering
Level 3: Subsystem Requirements
- What each subsystem must do
- Allocated from system requirements
- Source: Architecture trade studies
Level 4: Component Requirements
- What each component must do
- Allocated from subsystem requirements
- Source: Detailed design
| Type | Description | Example |
|---|---|---|
| Functional | What the system does | "Shall lift 500 kg" |
| Performance | How well it performs | "Lifting time < 30 sec" |
| Interface | Connections to other systems | "Shall mate with Type A connector" |
| Environmental | Operating conditions | "Shall operate at -40 to +85 C" |
| Physical | Size, weight, shape | "Shall weigh < 25 kg" |
| Reliability | Failure characteristics | "MTBF > 10,000 hours" |
| Maintainability | Service characteristics | "Shall be serviceable in field" |
| Safety | Hazard prevention | "Shall prevent pinch points" |
Each requirement should have:
- Unique identifier (REQ-XXX-XXXX)
- Requirement text (shall statement)
- Rationale (why needed)
- Source (parent requirement or stakeholder)
- Priority (must have, should have, nice to have)
- Verification method (analysis, test, inspection, demo)
- Owner (responsible engineer)
- Status (draft, approved, verified)
Good requirement characteristics (SMART):
- Specific: Unambiguous and clear
- Measurable: Quantifiable acceptance criteria
- Achievable: Technically feasible
- Relevant: Traces to stakeholder need
- Traceable: Links up and down hierarchy
Bad: "The system shall be easy to use"
Good: "The system shall be operable by one person
without tools within 5 minutes of training"
Parse Parent Requirement
Allocate to Children
Derive Supporting Requirements
Parent: "System shall weigh < 100 kg"
Children:
- Structure: < 40 kg (40%)
- Mechanism: < 25 kg (25%)
- Electronics: < 15 kg (15%)
- Cabling: < 10 kg (10%)
- Margin: 10 kg (10%)
Requirements Verification Matrix (RVM):
| Req ID | Requirement Text | Source | Verification Method | Evidence |
|--------|------------------|--------|---------------------|----------|
| REQ-001 | Shall lift 500 kg | SRS-001 | Test | Test Report TR-001 |
| REQ-002 | Shall operate at -40C | SRS-002 | Test | Test Report TR-002 |
| REQ-003 | Shall weigh < 25 kg | SRS-003 | Inspection | FAI-001 |
| Method | Application | Evidence |
|---|---|---|
| Analysis | Calculations, simulations | Analysis report |
| Test | Physical testing | Test report |
| Inspection | Visual/dimensional check | Inspection report |
| Demonstration | Functional demo | Demo record |
Mechanical standards flow-down:
1. Identify applicable standards (contract, regulatory)
2. Extract applicable requirements from standards
3. Create derived requirements with standard reference
4. Track compliance through verification
| Domain | Standards |
|---|---|
| Structural | ASME BPVC, AWS D1.1, AISC |
| Materials | ASTM, SAE AMS, MMPDS |
| Drawing | ASME Y14.5, ASME Y14.100 |
| Quality | ISO 9001, AS9100 |
| Safety | OSHA, ANSI, ISO 13849 |
| Environmental | MIL-STD-810, IEC 60068 |
1. Change request submitted
2. Impact assessment
- Technical impact
- Cost impact
- Schedule impact
- Downstream requirements
3. Review and approval
4. Implementation
5. Verification of change
6. Update traceability
{
"source_documents": {
"customer_spec": "string",
"applicable_standards": "array",
"interface_documents": "array"
},
"system_context": {
"system_name": "string",
"subsystems": "array",
"interfaces": "array"
},
"requirement_level": "stakeholder|system|subsystem|component"
}
{
"requirements_set": [
{
"id": "string",
"text": "string",
"type": "functional|performance|interface|environmental|physical",
"source": "string",
"parent": "string",
"verification_method": "analysis|test|inspection|demonstration",
"owner": "string",
"priority": "must|should|nice",
"status": "draft|approved|verified"
}
],
"traceability_matrix": {
"upward": "matrix of parent links",
"downward": "matrix of child links",
"verification": "matrix of evidence links"
},
"budgets": {
"mass": "object of allocations",
"power": "object of allocations",
"cost": "object of allocations"
},
"open_items": "array of TBD/TBR items"
}
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
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.