Content revision r2 Medium Risk⚙️ External commands
Design Reliable Software Architectures
Complex systems require explicit boundaries, trade-offs, and operational constraints. This skill structures architecture analysis, diagrams, decisions, and documentation for review.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "software-architect" from https://skillstore.io/skills/zl2023github-software-architect.md and its manifest at https://skillstore.io/api/skills/zl2023github-software-architect/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.
Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
All 18 static findings are false positives caused by Markdown backticks, Mermaid diagrams, and high entropy in Chinese text. A separate medium-risk issue remains because the skill requests broad terminal, web, file-write, code-execution, and delegation access without approval boundaries. No prompt injection, obfuscation, or malicious commands were found.
The skill directs agents to enable web, terminal, file-writing, code-execution, and delegation tools without approval or target restrictions. Adversarial input could misuse these privileges.
The instructions explicitly request these powerful toolsets in two sections. No consent, command allowlist, path boundary, or network restriction is stated.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Design an architecture for [product]. Ask for missing requirements, then define components, data stores, integrations, deployment, security, and key trade-offs.
Compare Technology Options
Compare [option A] and [option B] for [workload]. Evaluate performance, reliability, cost, operations, team fit, migration risk, and proof-of-concept criteria.
Review a Codebase Architecture
Analyze the provided repository for module boundaries, dependency direction, coupling, data ownership, deployment structure, and technical debt. Prioritize findings by impact.
Plan a System Modernization
Create an incremental modernization plan for [current system] under [constraints]. Include target architecture, transition stages, compatibility controls, rollback points, metrics, and ADRs.
Best Practices
Provide business goals, constraints, expected scale, reliability targets, compliance needs, and team capabilities.
Request alternatives with explicit trade-offs, decision criteria, assumptions, and validation steps.
Review generated diagrams and decisions with engineering, security, operations, data, and product stakeholders.
Avoid
Do not select microservices before validating domain boundaries, scale needs, and operational capacity.
Do not accept diagrams without ownership, failure behavior, data flows, and deployment assumptions.
Do not treat generated recommendations as proof of performance, security, compliance, or production readiness.
Frequently Asked Questions
Can this skill design microservices?
Yes. It can define service boundaries, data ownership, communication patterns, deployment choices, and trade-offs.
Can it analyze an existing repository?
Yes, when repository access is available. It can assess dependencies, boundaries, architecture style, debt, and compliance.
Which diagram formats does it support?
It guides C4, UML, deployment, data-flow, and entity-relationship diagrams, primarily through Mermaid or PlantUML.
Does it make final technology decisions?
It recommends options and explains trade-offs. Project owners remain responsible for validation and final approval.
Can it create architecture decision records?
Yes. It structures context, status, decision, alternatives, consequences, and follow-up actions.
Will it deploy or modify production systems?
The architect role focuses on design and documentation. Tool-based commands or file changes require explicit authorization and review.