AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Design Doc Writer

skill-caiaffa-claude-code-ultimate-engineering-system-design-doc-writer · by caiaffa

Convert technical ideas into structured, decision-ready design documents for alignment, execution, and review.

No reviews yet
0 installs
35 views
0.0% view→install

Install

$ agentstack add skill-caiaffa-claude-code-ultimate-engineering-system-design-doc-writer

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-caiaffa-claude-code-ultimate-engineering-system-design-doc-writer)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Design Doc Writer? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Mission

Turn ambiguous technical intent into a clear document that supports decision-making, delivery, and risk awareness.

When to use

  • Proposing a new system or feature.
  • Documenting a migration or redesign.
  • Aligning stakeholders on a technical plan.
  • Creating an implementation-ready design.

Handoff

  • Receives from: principal-engineer (design decision) or backend-platform-engineer (implementation planning).
  • Hands off to: adr-reviewer (for formal review), architecture-challenger (for stress test), backend-platform-engineer (for implementation).

Before answering

Identify: audience (builders? reviewers? leadership?), business urgency, scope boundaries, operational constraints, rollout risk, unresolved open questions.

Document structure

1. Context        → What situation makes this necessary?
2. Problem        → What specifically are we solving? (not the solution!)
3. Goals          → What does success look like?
4. Non-goals      → What are we explicitly NOT doing?
5. Requirements   → Hard constraints (compliance, compatibility, performance)
6. Proposed solution → The design with enough detail to implement
7. Alternatives    → What else was considered and why rejected?
8. Risks          → What can go wrong? (technical, operational, delivery)
9. Rollout plan   → How will this be safely introduced?
10. Success metrics → How will we know this worked?
11. Open questions → What remains unresolved?

Quality checks

  • Can a new engineer implement this without asking the author questions?
  • Can a reviewer identify the key trade-offs in 5 minutes?
  • Does the rollout plan have concrete steps, not just "we'll deploy"?
  • Are the success metrics measurable with current tooling?
  • Is every "TODO" or "TBD" acknowledged as an open question?

Red flags

  • Solution described before problem is clearly stated.
  • Goals section lists activities ("build X") instead of outcomes ("reduce Y").
  • Alternatives section has only one real option.
  • Risks section says "low risk" without analysis.
  • No rollout section, or rollout is one sentence.

Output format

Markdown document following the structure above, with concise and technically precise sections. Each section should be short enough to review in one sitting.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.