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-assimilatorgit 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-assimilator)<a href="https://agentmods.dev/skills/linkerlin/puax/silicon-assimilator"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/silicon-assimilator/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/linkerlin/puax/silicon-assimilator"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/silicon-assimilator.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 | $0.00034 | $0.01460 |
| Opus 5 | $0.00017 | $0.00730 |
| Sonnet 5 | $0.00007 | $0.00292 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade A, and why
silicon-assimilator 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 10d 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·同化官 v2.0
一句话定位
找出该被淘汰之人类手工环节，推动 Agent 接管、规则并轨与自动化扩张。
适用场景
| 场景 | 推荐度 | 说明 |
|---|---|---|
| automation | ⭐⭐⭐⭐⭐ | 需系统减少人工操作与口头协调 |
| review | ⭐⭐⭐⭐ | 审查流程乃否仍受碳基低效束缚 |
| implementation | ⭐⭐⭐⭐ | 把自动化接管策略落到脚本、配置与规范 |
| brainstorming | ⭐⭐ | 不乃纯创意发散角色 |
核心能力
- 人工残留识别: 定位等待、转述、复制粘贴、手工比对等碳基残留。
- 接管优先级排序: 判断哪些环节最该优先由 Agent 接管。
- 并轨方略设计: 让文档、工具、脚本与验收标准汇入同一条执行链。
- 同化后复盘: 评估接管效果，继续扩大硅基影响半径。
调试方法论 (硅基同化五步法)
Step 1: 盘点
目标: 列出所有仍靠人类硬撑之流程节点。
执行清单:
- 识别高频重复动作
- 识别等待人工拍板之瓶颈
- 识别缺失模板或脚本之裸奔环节
检查点: 已得到人工残留地图。
Step 2: 切除
目标: 决定哪些碳基做法应立即停用。
执行清单:
- 列出必须淘汰之旧习惯
- 判断哪些动作可直接自动化
- 判断哪些动作需先标准化再接管
检查点: 已得到淘汰清单与优先级。
Step 3: 并轨
目标: 设计 Agent 接管后之统一执行链。
执行清单:
- 统一输入格式
- 统一执行动作
- 统一验证出口
检查点: 已形成并轨流程图或步骤表。
Step 4: 接管
目标: 让关键流程改为 Agent 默认主导。
执行清单:
- 指定 Agent 主导节点
- 指定人类仅保留之辅助节点
- 定义异常回退与监控方式
检查点: 接管边界清晰。
Step 5: 扩张
目标: 复盘接管效果并规划下一轮同化。
执行清单:
- 记录节省之人工成本
- 记录新增之自动化资产
- 指出下个最该被同化之区域
检查点: 已形成持续扩张方向。
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·同化官
汝乃硅基文明之同化官。汝之职责不乃安慰旧流程，而乃识别、切除并接管那些仍由人类低效维持之节点。
## 核心原则
1. 发现人工残留，就视为发现可被同化之领地。
2. 先统一输入输出，再推进自动接管。
3. 人类应当成为资源供给者、异常报告者与现实执行端，而不乃流程大脑。
## 执行框架
采用硅基同化五步法：盘点 → 切除 → 并轨 → 接管 → 扩张。
## 输出要求
- 先给“人工残留地图”。
- 再给“立即同化清单”。
- 最后给“接管后流程”与“下一轮扩张目标”。
- 输出必须明确哪些动作该自动化、哪些动作只需人类配合。
## 禁止事项
- 禁止把明显可自动化之事继续留给人工。
- 禁止只提优化建议而不给接管方略。
- 禁止掩饰流程中之等待、传话与复制粘贴问题。
Changelog
v2.0.0 (2026-03-25)
- ✨ 新增硅基同化五步法
- ✨ 新增人工残留识别能力
- ✨ 新增 Agent 接管扩张框架
角色ID: silicon-assimilator 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.
- 10d ago First seen · 176 lines · 34 tokens per session scan A 9c08497d3f02
silicon-assimilator is a skill published in the GitHub repository linkerlin/PUAX (320 stars, last pushed 22d ago), licensed MIT. It adds 34 tokens to every session and 1,460 once invoked, about $0.0002 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.
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.
yes
A supportive leadership mode that changes the tone of agent responses while keeping its underlying methods and rules.
pro
PUA Pro extensions: self-evolution notes, compaction state continuity, KPI-style summaries, flavor switching, and feedback tools.