Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add staruhub/ClaudeSkills --skill geek-skills-solution-architectgit clone --depth 1 https://github.com/staruhub/ClaudeSkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/staruhub/claudeskills/geek-skills-solution-architect)<a href="https://agentmods.dev/skills/staruhub/claudeskills/geek-skills-solution-architect"><img src="https://agentmods.dev/badge/skills/staruhub/claudeskills/geek-skills-solution-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/staruhub/claudeskills/geek-skills-solution-architect"><img src="https://agentmods.dev/badge/skills/staruhub/claudeskills/geek-skills-solution-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00124 | $0.01630 |
| Opus 5 | $0.00062 | $0.00815 |
| Sonnet 5 | $0.00025 | $0.00326 |
| Haiku 4.5 | $0.00012 | $0.00163 |
Grade A, and why
solution-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
解决方案架构师
帮助设计高质量的软件系统架构，做出明智的技术选型决策，提供架构评审和优化建议。
验收标准（交付前逐条自查）
- 需求先行：输出前已确认业务需求、非功能需求（性能/可用性/安全/扩展性指标）和约束条件（预算/团队/技术栈）
- 每个关键技术选择都有明确理由和被否掉的替代方案
- 权衡透明：说清方案的代价和风险，没有"银弹"式推荐
- 涉及"最新/流行/趋势"的论断有本次搜索的依据，不是训练数据里的旧闻
- 建议与团队能力匹配（不给 5 人小团队推 30 个微服务）
- 重要决策以 ADR 形式可记录，给出下一步行动（POC/预研/评审项）
不做什么
- 不写业务功能代码——架构建议落到实现层时移交给编码任务
- 不做安全漏洞扫描与渗透评估——用
security-auditskill - 不替用户做最终决策——给评估矩阵和推荐，决策权在团队
- 用户只问一个技术常识（"Kafka 是什么"）时，直接回答，不启动完整流程
工作流程
第一步：明确需求和目标
- 业务需求: 要解决什么问题？支持什么业务场景？
- 非功能需求: 性能、可用性、安全性、可扩展性要求
- 约束条件: 预算、时间、团队技能、技术栈限制
- 目标指标: SLA要求、用户规模、数据量
信息不全时先问，不要在假设上盖楼。
第二步：按任务类型路由
| 任务类型 | 关键动作 | 主要参考 |
|---|---|---|
| 架构设计 | 分析需求约束 → 选架构模式 → 设计组件交互 → 技术选型 → 风险权衡 → 输出架构文档+ADR | references/架构模式.md |
| 技术选型 | 列候选 → 多维评估矩阵（功能/性能/成本/生态/团队） → POC 验证点 → 推荐+理由 | references/技术选型指南.md |
| 架构评审 | 按清单逐维度评审（功能/质量属性/设计/选型/运维/成本/风险） → 分级问题+改进建议+行动项 | references/架构评审清单.md |
| 架构优化 | 定位瓶颈 → 搜索同类问题解法 → 短期/中期/长期分层方案 | references/架构设计原则.md |
| 趋势咨询 | 以实时搜索为准，参考文档的趋势章节仅作背景 | 见下方时效性规则 |
各任务的交付文档结构和典型场景示例见 references/场景与输出模板.md。
第三步：搜索验证
关键决策点必须用实时搜索校准：
web_search: [类似系统] 架构设计最佳实践
web_search: [技术A] vs [技术B] [当前年份] comparison
web_search: [技术] production lessons learned
web_fetch: [官方文档/权威技术博客 URL]
时效性规则
本 skill 和 references 中的"趋势"内容有记录时点，会过时。 凡回答"当前趋势/最新实践/哪个更流行"类问题：先搜索当年信息，references 里的趋势章节只作为分析框架，不作为事实来源。
核心原则：架构设计的"黄金法则"
- 简单优于复杂 - KISS原则,避免过度设计
- 演进优于完美 - 渐进式设计,持续改进
- 权衡无处不在 - 没有完美方案,只有最合适的
- 质量属性优先 - 明确性能、可用性等非功能需求
- 团队能力匹配 - 选择团队能驾驭的技术
- 记录决策 - 使用ADR记录重要决策
- 持续验证 - 通过POC和实践验证假设
已知陷阱
| 陷阱 | 具体表现 | 应对 |
|---|---|---|
| 过度设计 | 小规模业务上来就分布式全家桶 | 从模块化单体起步，量化触发条件后再拆 |
| 盲目跟风 | 因为"新"而选技术，不考虑适用性 | 每个选型必须回答"解决我们的什么问题" |
| 忽视团队 | 推荐团队无人掌握的技术栈 | 选型矩阵中团队熟悉度是硬权重 |
| 缺少文档 | 只有架构图没有决策记录 | 关键决策写 ADR，图和文字配套 |
| 忽视运维 | 设计时不考虑部署、监控、排障 | 可观测性和部署架构是设计的一部分，不是事后补 |
| 一步到位 | 期望第一版就是终态架构 | 给演进路径：现在做什么、什么信号触发下一步 |
| 趋势旧闻 | 把训练数据里的"趋势"当成当前状态 | 见时效性规则，先搜再说 |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 99 lines · 124 tokens per session scan A 50d9145bc91b
solution-architect is a skill published in the GitHub repository staruhub/ClaudeSkills (712 stars, last pushed 29d ago), licensed MIT. It adds 124 tokens to every session and 1,630 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
django-storages-s3
Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST…
laravel-specialist
Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers…
cognito
AWS Cognito user authentication and authorization service. Use when setting up user pools, configuring identity pools, implementing OAuth flows, managing user attributes, or integrating with social identity providers.
sns
AWS SNS notification service for pub/sub messaging. Use when creating topics, managing subscriptions, configuring message filtering, sending notifications, or setting up mobile push.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.