compare
/compare
Compare two or three viable architectures for the same requirements with explicit trade-offs and the decision that would settle each; no invented numbers. Use when the user is torn between designs.
- Author
- Alejo2075 ↗
- Repository
- claude-code-aws ↗
- Licence
- MIT
- Last repository change
- 31.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 31.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Compare two or three viable architectures for the same requirements with explicit trade-offs and the decision that would settle each; no invented numbers. Use when the user is torn between designs.
Arguments
/compare <option A> vs <option B>
Original author description
Compare two or three viable architectures for the same requirements with explicit trade-offs and the decision that would settle each; no invented numbers. Use when the user is torn between designs.
How it works
- Side effects
- Steps
- Output
- Failure and safety handling
SKILL.md preview
---
name: compare
description: Compare two or three viable architectures for the same requirements with explicit trade-offs and the decision that would settle each; no invented numbers. Use when the user is torn between designs.
argument-hint: "<option A> vs <option B>"
allowed-tools: Bash(node ${CLAUDE_PLUGIN_ROOT}/dist/cli.mjs decisions *)
---
# Compare architectures
## Side effects
`read`.
## Steps
1. Restate the requirements that decide the choice (latency, ordering, volume, team skills, cost ceiling). Ask for the ones that are missing.
2. For each building-block choice involved, run `node ${CLAUDE_PLUGIN_ROOT}/dist/cli.mjs decisions <topic>` (api-type, messaging, workflow, integration, data-store, sync-async) and use its "ask first" questions.
3. Present a table: option, what it is good at, what it costs in complexity or money, the failure mode that worries you most, and the single fact that would change the recommendation.
4. For cost, use `/aws-cost:estimate` with numbers the user provides. For a bounded experiment, suggest `/aws-prototyping:start` with a success metric.
## Output
The comparison table, a recommendation that names the requirement it rests on, and what was rejected and why.
## Failure and safety handling
- Do not quote prices, quotas, or latencies from memory.
- The decision tables are summaries; send the user to the source link for anything expensive or hard to reverse.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · Alejo2075/claude-code-aws | 90 | MIT |
| taishi-i/awesome-japanese-nlp-resources | 100 | CC0-1.0 |
| Hainrixz/claude-seo-ai | 100 | MIT |
| RemiPelloux/kill-my-idea | 100 | MIT |
| JunLin615/os-optics-kit | 100 | MIT |
| talent-factory/claude-plugins | 100 | MIT |
| Alejo2075/claude-code-aws | 100 | MIT |
| fcakyon/phd-skills | 100 | MIT |
| seo-skills/geo-audit-skill | 100 | MIT |
Database snapshot: 13.11.2026 · package version d8747aa0493c (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90technical-architect
Designs system architecture: components, data model, APIs, scaling and trade-offs, with diagrams. Use for designing a new system, scaling an existing one, choosing between architectures, or writing an architecture decision record. - 90architecture-options
Compare architecture or technology options for a project using explicit requirements and constraints. Use when choosing or changing a system structure, framework, data store, or integration. - 100pptx-comparison-and-versus-layouts
Use this skill when comparing two or three options, architectures, pricing tiers, or tradeoffs side-by-side on a slide. - 86agent-eval-compare
Compare two or more agents (skills, plugins or MCP servers) head-to-head on the same weights, budget and host, rank them and recommend one with the trade-offs. Use when the user asks which of several skills, plugins or MCP servers to pick, or to compare versions of one agent. Not for a single agent. - 96vllm-compare-reqs
Use this skill to compare vllm requirements files between versions - 100trade-off-evaluator
Scores design trade-offs across five dimensions — cost, latency, complexity, scalability, operability — producing a structured comparison matrix and a recommendation. Use when a design decision has multiple options, when an engineer asks to evaluate trade-offs, or when the…