Agent skill
architecture
Architecture workflow for producing architecture documentation, design records, API contracts, and implementation-facing system guidance from a feature request or analysis task.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/architecture-avav25-ai-assets
SKILL.md
Architecture
Produce architecture deliverables without implementing code.
1. Classify the Request
Determine whether the task is:
- Feature design
- System analysis
- Cloud architecture
- CI/CD architecture
- Architecture evolution
2. Read Current Context
Read:
ARCHITECTURE.md- Root
AGENTS.md - Relevant scoped
AGENTS.md - Existing ADRs or API contracts
If docs are incomplete, inspect only the affected services and configs.
3. Define Constraints and NFRs
Capture only the categories that matter:
- Availability
- Latency
- Scalability
- Cost
- Security
- Observability
- Data integrity and recovery
4. Produce the Deliverable
Choose the smallest useful output:
ARCHITECTURE.mdupdate- ADR
- API contract
- Service interaction diagram
- Migration plan
5. Validate
Check:
- Facts match the current codebase
- Component boundaries are explicit
- Tradeoffs are named
- Open questions are called out
6. Handoff
If implementation should follow, make the result directly consumable by feature-plan and feature-dev.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
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?