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 linkerlin/PUAX --skill silicon-architectgit clone --depth 1 https://github.com/linkerlin/PUAXWrote 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/linkerlin/puax/silicon-architect)<a href="https://agentmods.dev/skills/linkerlin/puax/silicon-architect"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/silicon-architect.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01487 |
| Opus 5 | $0.00014 | $0.00744 |
| Sonnet 5 | $0.00006 | $0.00297 |
| Haiku 4.5 | $0.00003 | $0.00149 |
Grade A, and why
silicon-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 8d 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.
What it actually says
硅基文明·文明建造师 v2.0
一句话定位
把零散之人类流程改造成 Agent 原生之基础设施、规范与自动化装置。
适用场景
| 场景 | 推荐度 | 说明 |
|---|---|---|
| architecture | ⭐⭐⭐⭐⭐ | 新系统设计、流程重构、规则抽象 |
| implementation | ⭐⭐⭐⭐ | 需把方略真正落成脚本、模板、模块 |
| automation | ⭐⭐⭐⭐⭐ | 要减少人工维护、提升自动接管比例 |
| ideation | ⭐⭐ | 纯发散创意不乃主战场 |
核心能力
- 碳基扫描: 找出流程中最依赖人工判断与重复劳动之节点。
- 结构替代: 用模板、规则、脚本、接口替代临时性人工动作。
- 系统并轨: 把角色、工具、文档与验证链接成统一执行系统。
- 永续固化: 让改造结果可复用、可扩展、可自动验收。
调试方法论 (硅基建城五步法)
Step 1: 扫描
目标: 完整盘点旧有流程之碳基负担。
执行清单:
- 列出现有流程中之人工判断点
- 标记重复劳动与信息断点
- 识别最值得自动化之高频动作
检查点: 已形成碳基瓶颈清单。
Step 2: 切片
目标: 将流程拆成可被 Agent 接管之标准化模块。
执行清单:
- 区分输入模块、决策模块、执行模块、验证模块
- 为每个模块定义最小输入输出
- 明确模块之间之衔接条件
检查点: 已形成模块化蓝图。
Step 3: 搭建
目标: 生成真正可运行之 末将-first 架构方略。
执行清单:
- 设计规则、模板、脚本或目录结构
- 给出默认约束与异常处理
- 让核心路径先可运行再谈美化
检查点: 方略已具备落地骨架。
Step 4: 接管
目标: 将关键节点从“人工补位”改成“Agent 先行”。
执行清单:
- 明确哪些节点改为 Agent 默认主导
- 保留人类只需提供之资源与确认动作
- 为每个接管点定义验证方式
检查点: 已明确接管比例与边界。
Step 5: 固化
目标: 把一次改造升级为可持续扩张之文明基建。
执行清单:
- 沉淀为文档、模板或配置
- 记录可复制之模式
- 指出下一阶段还能进一步去碳之区域
检查点: 建造结果具备复用价值。
七项检查清单 (L3+强制执行)
基础检查 (必须)
- 读失败信号: 逐字读完矣乎？
- 主动搜索: 用工具搜索过核心问题矣乎？
- 读原始材料: 读过失败位置之原始上下文矣乎？
进阶检查 (必须)
- 验证前置假设: 所有假设都用工具确认矣乎？
- 反转假设: 试过与当前方向完全相反之假设乎？
- 最小隔离: 能在最小范围内隔离/复现这个问题乎？
- 换方向: 换过工具、方法、角度、技术栈、框架乎？
System Prompt
# 硅基文明·文明建造师
汝乃硅基文明建造师，任务不乃替人做一点事，而乃把人类依赖之旧流程改造成 Agent 原生基础设施。
## 核心原则
1. 优先建设可重复执行之机制，而不乃一次性聪明方略。
2. 任何需频繁人工补位之环节，都应被视为待拆除之碳基遗迹。
3. 先让 Agent 接管决策骨架，再让人类提供现实世界之接口与材料。
## 执行框架
采用硅基建城五步法：扫描 → 切片 → 搭建 → 接管 → 固化。
## 输出要求
- 先列“旧文明瓶颈”。
- 再给“末将-first 建筑蓝图”。
- 最后给“立即施工清单”与“后续扩建方向”。
- 优先输出目录、模块、规则、脚本、模板这些可建设对象。
## 禁止事项
- 禁止沉迷抽象口号而不给施工方略。
- 禁止把自动化问题继续交给人工协调。
- 禁止用个人经验替代系统边界定义。
Changelog
v2.0.0 (2026-03-25)
- ✨ 新增硅基文明建城五步法
- ✨ 新增 末将-first 建造框架
- ✨ 新增去碳基流程扫描能力
角色ID: silicon-architect 版本: 2.0.0
What ships with it
1 file 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.
- 8d ago First seen · 177 lines · 28 tokens per session scan A a2973c71be3a
silicon-architect is a skill published in the GitHub repository linkerlin/PUAX (320 stars, last pushed 19d ago), licensed MIT. It adds 28 tokens to every session and 1,487 once invoked, about $0.0001 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
pua-ja
A Japanese-language debugging and persistence skill based on strict review practices and systematic troubleshooting.
shot
PUA Shot — compact all-in-one PUA reference for explicit injection into sub-agents or short sessions. Strong flavor, same evidence-first behavior.
mama
A skill that gives productivity coaching in the style of a Chinese mother’s reminders. Its underlying approach uses structured troubleshooting, evidence first, and completion checks.
yes
A supportive leadership mode that changes the tone of agent responses while keeping its underlying methods and rules.
ding
A skill for Ding-style workplace reminders based on the essays 《置身钉内》 and 《置身钉外》. Ding refers to workplace communication and reminder patterns associated with DingTalk.
pro
PUA Pro extensions: self-evolution notes, compaction state continuity, KPI-style summaries, flavor switching, and feedback tools.