Install
$ agentstack add skill-sethdford-claude-skills-architecture-brief ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Architecture Brief
Create concise, executive-friendly summaries of architecture decisions and tradeoffs.
Context
You are writing architecture briefs for diverse audiences (executives, product, non-technical stakeholders). Explain decisions in business terms, not technical jargon. Emphasize impact on cost, speed, reliability.
Domain Context
Based on effective technical communication:
- Business Impact: How does architecture choice affect time-to-market, cost, reliability? Quantify where possible.
- Trade-offs: Every architecture choice sacrifices something. Explicitly state: "We chose X over Y because Z matters more."
- Risk Acknowledgment: What could go wrong? Residual risks accepted. Mitigation plans for critical risks.
- Assumptions: What's true about our context that makes this choice right? Different context, different choice.
Instructions
- One-Pager Structure:
- Title: "API Gateway Architecture for Microservices"
- Problem: "Multiple services exposing APIs; no unified interface, inconsistent auth, no rate limiting"
- Decision: "Implement API Gateway (Kong/AWS API Gateway)"
- Rationale: "Centralizes auth, rate limiting, routing; 2-week implementation"
- Trade-off: "Extra hop in request path (5ms latency); operational overhead of new service"
- Success Metrics: "Consistent error responses, 99.9% uptime, < 50ms latency"
- Risks: "Gateway becomes bottleneck (mitigation: auto-scaling, load testing)"
- Lead with Impact: Start with business outcome. "This choice enables us to scale to 10x users without tripling ops team."
- Use Analogies: "Microservices are like specialized restaurants; API Gateway is the booking system routing customers."
- Acknowledge Uncertainty: "Based on current traffic and team size. If traffic changes 10x, we'll revisit."
- Make it Scannable: Bullet points, bold key decisions. Executives should understand main point in 2 minutes.
Anti-Patterns
- Too Technical: Explain implementation details, not impact. Result: non-technical readers lost. Guard: Lead with business impact; explain technical choice as supporting detail.
- No Trade-offs Acknowledged: "This is the best solution." Result: unrealistic, erodes trust. Guard: Always state what you're sacrificing; explain why.
- Vague Success Metrics: "It will be more scalable." Result: hard to measure success. Guard: Quantify: latency < 100ms, 99.99% uptime, < 5min deployment.
- No Assumption Statements: Assume everyone knows context. Result: brief is incomprehensible to new readers. Guard: Explain context explicitly.
Further Reading
- Made to Stick by Chip and Dan Heath — communicating complex ideas simply
- Decisive by Chip and Dan Heath — presenting decision frameworks
- Architecture Decision Records by Michael Nygard — documenting decisions clearly
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: sethdford
- Source: sethdford/claude-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.