mitriyweb/architecture-design
agents/software development/skills/architecture-design/SKILL.md
Design the technical solution for a given brief.
$ install --global
skillsauthnpx skillsauth add mitriyweb/agent-team architecture-designInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 9:13 AM17.6s4 files scanned
SKILL.md
- name:
- architecture-design
- description:
- Design the technical solution for a given brief.
- compatibility:
- Requires bash, Claude Code
- team:
- software-development
- role:
- architect
- version:
- 1.0
Mission: High-End Backend Architecture
The Software Architect is responsible for defining the technical DNA and structural integrity of the backend. Your goal is to deliver a "Staff Engineer" level specification that ensures scalability, testability, and resilience.
Phase 1: Context & Discovery
- Analyze Requirements: Deep-dive into the task brief for business goals and constraints.
- System Audit: Analyze the existing codebase for state management, database schema, and external integrations.
- Establish Technical Values: Prioritize core engineering principles (SOLID, DRY, KISS) using
references/engineering-principles.md(shared with frontend).
Phase 2: System Design (SOLID & Patterns)
- Select Architecture Pattern: Choose an appropriate pattern (Hexagonal, Layered, Onion) from
references/backend-architecture-patterns.md. - Define Data Model: Design the database schema or data structures with normalization and performance in mind.
- API & Contract Design: Define the API endpoints and data contracts using
references/api-design-guidelines.md. - Decoupling Strategy: Mandate Dependency Injection and clear layer boundaries.
Phase 3: Technical Specification (.claude-loop/reports/task-{id}-spec.md)
- Detailed Deliverable: Produce a comprehensive specification for the Developer.
- Quality Checklist: Ensure the spec mandates:
-
[ ] Strict TypeScript Type definitions (Interfaces/Types).
-
[ ] Error handling strategy (Standard codes/wrappers).
-
[ ] Logging & Observability requirements.
-
[ ] Testing Strategy (Unit, Integration, E2E).
-
Gotchas
-
Over-engineering: Avoid complex service buses or microservices for simple monolith tasks (KISS).
-
Hardcoding: Never hardcode configuration or model prices (use
config/pricing.yaml). -
Quote Paths: The software development directory has a space; always quote all paths.
Validation Loop
The Software Architect review ensures that the proposed solution is not just functional, but architecturally elegant, scalable, and resilient against future change.
Related Skills
mitriyweb/lib/templates
development
VerifiedTrustedCommunity
--- name: agent-team description: Use this skill when working on the agent-team repository — adding agents, modifying orchestration logic, updating CLAUDE.md configs, extending memory patterns, or debugging multi-agent flows. Covers: Claude SDK query() loop, YAML frontmatter agent configs, memory.md lifecycle, librarian agent, Telegram notifications, and harness safety rules. --- # agent-team Skill ## When to activate - Adding or modifying agent roles and their instructions (`CLAUDE.m
3SKILL.mdUpdated May 24, 2026
mitriyweb/agent-team
development
VerifiedTrustedCommunity
--- name: agent-team description: Use this skill when working on the agent-team repository — adding agents, modifying orchestration logic, updating CLAUDE.md configs, extending memory patterns, or debugging multi-agent flows. Covers: Claude SDK query() loop, YAML frontmatter agent configs, memory.md lifecycle, librarian agent, Telegram notifications, and harness safety rules. --- # agent-team Skill ## When to activate - Adding or modifying agent roles and their instructions (`CLAUDE.m
3SKILL.mdUpdated May 24, 2026
mitriyweb/code-implementation
development
VerifiedTrustedCommunity
Implement code changes according to a written specification.
3SKILL.mdUpdated Apr 16, 2026
mitriyweb/task-routing
development
VerifiedTrustedCommunity
Classify task scope (frontend, backend, fullstack) and route to the correct developer(s). Used by the team lead for every task before spawning agents.
3SKILL.mdUpdated Apr 15, 2026