- A mandatory separate `互动提问` section after the title candidates and before the platform rewrites.
- Every `互动提问` section must contain exactly 10 questions.
- Ask only knowledge- and content-related questions about the current subject.
- Focus on structure, component function, architecture, process, trade-offs, bottlenecks, applications, limitations, reliability, cost, efficiency, or technical comparisons.
- Phrase every item as a genuine question ending in `?` or `?`, for example asking what function a component performs, where a bottleneck occurs, why a material was selected, or what trade-off an architecture makes.
- Every question must explicitly include the topic keyword (the subject of the poster, e.g. NVLink, B200, CoWoS) in the question text. Do not use generic references like "this architecture", "this component", or "this design" as a substitute for the keyword.
- Do not ask what topic, product, teardown, article, image, or subject the audience wants next.
- Do not ask subjective-preference or opinion questions. Reject phrasing such as "你觉得", "你认为", "哪个更", "会更", "会不会", "值不值得", "有没有必要", or any question that asks the reader to pick a favorite, predict adoption, or express personal taste. Every question must have a verifiable technical answer grounded in the subject's structure, process, physics, or engineering constraints.
- Do not use generic engagement bait without a concrete technical object or trade-off.
- Reject prompts such as asking what to cover next, what else the reader wants to see, or requesting future-topic suggestions in comments.
- Do not write analytical evaluation paragraphs, generic praise, rhetorical promotion, predetermined conclusions, or unrelated engagement bait.
-
exec
/bin/zsh -lc "sed -n '521,900p' /Users/alex/.codex/skills/product-exploded-view-company-prompts/SKILL.md 2>&1 | head -c 10000" in /Users/alex/.openclaw/workspace/exploded-poster-gen
succeeded in 0ms:
codex
接下来我会直接生成文本稿。由于这是前沿/概念性芯片平台,未逐项引用官方结构图,我会把图像提示词明确写成“示意结构图/概念爆炸图”,避免把内部结构写成已验证实物拆解
digraph skill_flow {
"User message received" [shape=doublecircle];
"About to EnterPlanMode?" [shape=doublecircle];
"Already brainstormed?" [shape=diamond];
"Invoke brainstorming skill" [shape=box];
"Might any skill apply?" [shape=diamond];
"Invoke Skill tool" [shape=box];
"Announce: 'Using [skill] to [purpose]'" [shape=box];
"Has checklist?" [shape=diamond];
"Create TodoWrite todo per item" [shape=box];
"Follow skill exactly" [shape=box];
"Respond (including clarifications)" [shape=doublecircle];
dot
digraph skill_flow {
"User message received" [shape=doublecircle];
"About to EnterPlanMode?" [shape=doublecircle];
"Already brainstormed?" [shape=diamond];
"Invoke brainstorming skill" [shape=box];
"Might any skill apply?" [shape=diamond];
"Invoke Skill tool" [shape=box];
"Announce: 'Using [skill] to [purpose]'" [shape=box];
"Has checklist?" [shape=diamond];
"Create TodoWrite todo per item" [shape=box];
"Follow skill exactly" [shape=box];
"Respond (including clarifications)" [shape=doublecircle];
"About to EnterPlanMode?" -> "Already brainstormed?";
"Already brainstormed?" -> "Invoke brainstorming skill" [label="no"];
"Already brainstormed?" -> "Might any skill apply?" [label="yes"];
"Invoke brainstorming skill" -> "Might any skill apply?";
"User message received" -> "Might any skill apply?";
"Might any skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];
"Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
"Invoke Skill tool" -> "Announce: 'Using [skill] to [purpose]'";
"Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
"Has checklist?" -> "Create TodoWrite todo per item" [label="yes"];
"Has checklist?" -> "Follow skill exactly" [label="no"];
"Create TodoWrite todo per item" -> "Follow skill exactly";
}
Red Flags
These thoughts mean STOP—you're rationalizing:
| Thought | Reality |
|---------|---------|
| "This is just a simple question" | Questions are tasks. Check for skills. |
| "I need more context first" | Skill check comes BEFORE clarifying questions. |
| "Let me explore the codeba
codex
我已经读到这个 skill 的关键边界:只输出文本、不生成图;固定 3:4;不得放 logo;需要来源声明;默认会加作者,但你的强约束覆盖它,所以我会彻底移除署名、账号和公众号名。还需要看完剩余的版式要求,避免漏掉输出结构。
exec
/bin/zsh -lc "sed -n '261,520p' /Users/alex/.codex/skills/product-exploded-view-company-prompts/SKILL.md 2>&1 | head -c 8000" in /Users/alex/.openclaw/workspace/exploded-poster-gen
succeeded in 0ms:
"[heading]\n[short explanatory sentence]"
Right side:
"[heading]\n[short explanatory sentence]"
Bottom:
- Headline: "[bottom headline]"
- Body: "[2-3 concise sentences]"
- Footer mark: "[category / use case]"
Avoid:
garbled text, wrong language, Japanese text in Chinese posters, obvious brand logos, official logo glyphs, logo-like marks, company icons, company introductions, company products, company locations, company links, stock codes, rankings, recommendation reasons, geographic or regional names, origin-group labels, hard-ad title, sales CTA, exaggerated superlatives, hype words such as 重磅/颠覆/神器/必看/最强/炸裂/王炸, missing author credit, missing source disclaimer, metadata-only credit or disclaimer, watermark treatment, decorative clutter, empty-looking layout, unreadable tiny text, cropped labels, overlapping microtext, overlapping callouts, isolated floating parts without whole-to-parts guidance, unsupported exact claims about proprietary internals.
Component Rules
- Label every layer with a visible number and a short component name.
- Prefer 7-10 layers. Fewer can feel shallow; more often becomes unreadable.
- Group tiny internals into meaningful systems: compute, memory, power, cooling, frame, connector, enclosure, sensor, optics, battery, interface.
- Use callouts to explain function, not repeat component names.
- Keep primary image-model text short. Prefer one heading and one short sentence per main callout.
- Use "示意", "结构概念", "conceptual", or "schematic" for uncertain internals.
- For architecture or chips, describe whole package, stacked layers, key interconnect, base/control layer, package/interposer, and what the structure enables.
- For consumer products, describe shell/enclosure, display/interface, compute/control board, battery/power, sensors, connectors, thermal path, frame, and fastening when relevant.
In-Image Density Rules
- Use richer in-image text as an optional enhancement for technical posters when it helps the image feel complete and educational.
- Add 4-8 secondary details such as micro labels, small spec chips, short system-flow captions, mini legends, material notes, or compact annotation panels.
- Use smaller typography for secondary details, but do not make any required label, number, author credit, source disclaimer, or main callout tiny.
- Richer text should support the visual reading path, not become decorative filler.
- Avoid dense paragraphs inside the image; prefer short fragments, labels, and one-line notes.
Title Rules
- Poster titles should feel like technical editorial hooks, not product ads.
- Prefer titles that reveal a question, contrast, or structural role, such as "GPU 背后的调度底座", "为什么它不是显卡", or "AI 工厂里被低估的 CPU".
- Avoid hard-marketing title patterns such as "重磅发布", "颠覆未来", "最强芯片", "必看神器", "王炸新品", and sales-style calls to action.
- Keep the title shorter than the subtitle; let the subtitle carry the precise product name or use case when the title is more editorial.
- For Chinese publishing copy, generate 30 distinct title candidates by default and mark one recommended title.
Author Credit Rules
- Every prompt must include an in-image author/account credit.
- For Chinese content, use `作者:{name}`.
- Default to `作者:好用工具推荐` when no conflicting account appears.
- Place the credit inside the lower-middle content area, beside the lower decomposition axis, next to a real callout group, or inside a small engineering annotation panel connected to the diagram.
- Make the credit feel naturally merged with the real content so it is not easy to remove by cropping the bottom or deleting a detached footer.
- Avoid the very bottom edge, detached footer strips, corner-only labels, and large watermark treatment. Also avoid placing it too high or over the main reading path.
- Keep the credit smaller than component labels but clearly readable.
- Do not let it cover the product, numbered layers, arrows, or callouts.
- Do not treat the credit as a watermark outside the design; integrate it as a technical poster annotation.
- Do not use placeholders such as `【作者名】`, `{author}`, `[account]`, or `{name}` in the final prompt.
Source Disclaimer Rules
- Every Chinese technical poster prompt and companion publishing copy must include a source disclaimer.
- Default wording: `声明:信息整理自网络公开内容,仅供学习交流;如有疏漏或错误,请联系指正。`
- If the user supplies different wording, preserve it unless it creates a factual or legal misrepresentation.
- Require the disclaimer as visible image text near the author credit or in a connected lower-middle technical annotation panel. Keep it smaller than primary labels but clearly readable.
- Do not place it at the bottom edge, in a detachable footer, only in metadata, or outside the image.
- Append the full disclaimer directly at the end of every publish-ready platform version, including 作者, 小红书, 朋友圈/社群, and 知乎/B站动态.
- Do not consolidate, deduplicate, or replace these per-platform endings with a shared disclaimer, reusable ending, "通用结尾", footnote, or instruction to add it later.
- Do not claim that the generated image contains or correctly renders the disclaimer because this skill does not generate or inspect images.
- The disclaimer does not replace source verification. Continue to use official or primary sources when accuracy matters and label uncertain internals as conceptual or schematic.
Chinese Social Copy
Include social-media publishing copy by default for Chinese poster prompts unless the user asks for prompt-only output or no social copy. Use:
- 30 distinct title candidates by default, with one clearly marked as the recommended title; each title must be 15–20 visible characters (count Chinese characters, letters, digits, punctuation — every visible glyph counts). Titles shorter than 15 or longer than 20 visible characters are invalid and must be rewritten.
- A concise body that starts from the visual reading path, for example "通过这张图可以看到...".
- A mandatory separate `互动提问` section after the title candidates and before the platform rewrites.
- Every `互动提问` section must contain exactly 10 questions.
- Ask only knowledge- and content-related questions about the current subject.
- Focus on structure, component function, architecture, process, trade-offs, bottlenecks, applications, limitations, reliability, cost, efficiency, or technical comparisons.
- Phrase every item as a genuine question ending in `?` or `?`, for example asking what function a component performs, where a bottleneck occurs, why a material was selected, or what trade-off an architecture makes.
- Every question must explicitly include the topic keyword (the subject of the poster, e.g. NVLink, B200, CoWoS) in the question text. Do not use generic references like "this architecture", "this component", or "this design" as a substitute for the keyword.
- Do not ask what topic, product, teardown, article, image, or subject the audience wants next.
- Do not ask subjective-preference or opinion questions. Reject phrasing such as "你觉得", "你认为", "哪个更", "会更", "会不会", "值不值得", "有没有必要", or any question that asks the reader to pick a favorite, predict adoption, or express personal taste. Every question must have a verifiable technical answer grounded in the subject's structure, process, physics, or engineering constraints.
- Do not use generic engagement bait without a concrete technical object or trade-off.
- Reject prompts such as asking what to cover next, what else the reader wants to see, or requesting future-topic suggestions in comments.
- Do not write analytical evaluation paragraphs, generic praise, rhetorical promotion, predetermined conclusions, or unrelated engagement bait.
-
exec
/bin/zsh -lc "sed -n '521,900p' /Users/alex/.codex/skills/product-exploded-view-company-prompts/SKILL.md 2>&1 | head -c 10000" in /Users/alex/.openclaw/workspace/exploded-poster-gen
succeeded in 0ms:
codex
接下来我会直接生成文本稿。由于这是前沿/概念性芯片平台,未逐项引用官方结构图,我会把图像提示词明确写成“示意结构图/概念爆炸图”,避免把内部结构写成已验证实物拆解。
codex
Imagegen Prompt
text
画布比例:3:4,竖版中文技术拆解海报。主题为「压电光机械单片 CMOS 光子平台」,做成概念爆炸图 / 示意结构图,不表现为已验证实物拆解。
视觉风格:高洁净度半导体工程海报,浅色硅片灰底,局部青绿色光路、琥珀色压电层、深灰金属互连;中心为完整芯片平台的半透明 3D 剖切主视觉,沿纵向拆开 9 个编号层级,左右双侧短标注,现代无衬线中文排版,信息密度高但不拥挤。
阅读路径:完整平台主视图 -> 中央分解轴 -> 编号组件层。
标题:压电光机械单片 CMOS 光子平台
副标题:把光学谐振、机械振动、压电驱动与 CMOS 控制放进同一片芯片的示意结构
编号组件层:
01 光输入/输出耦合区:光纤或片上耦合进入波导,作为光信号接口。
02 硅光波导网络:负责片上光传输、分束、干涉与路由。
03 光机械谐振腔:用微纳结构把光场与机械振动模式耦合。
04 悬空机械梁/膜结构:提供可振动的低损耗机械自由度。
05 压电薄膜驱动层:把电信号转换为局部应变,调制机械与光学状态。
06 上下金属电极:为压电层施加射频或低频驱动信号。
07 介质隔离与通孔互连:连接光子层、驱动层与控制电路,同时保持电学隔离。
08 CMOS 控制与读出电路:实现驱动、调制、检测、反馈与校准。
09 衬底与热路径:提供机械支撑、工艺兼容性与热稳定基础。
左侧标注:
「光-机-电闭环」
光场读出机械运动,压电层注入可控应变,CMOS 电路完成反馈控制。
「单片集成挑战」
光损耗、机械 Q 值、压电效率、金属互连寄生参数需要同时权衡。
右侧标注:
「为什么要放在同一片」
减少封装耦合误差,缩短信号路径,提高阵列化与系统稳定性。
「适用方向」
片上调制、频率转换、微波光子、传感、可重构光子电路。
辅助微标签:低损耗波导、应变调制、悬空释放区、射频走线、反馈读出、热漂移补偿、片上校准、阵列扩展。
下方中部信息框只放来源声明:
声明:信息整理自网络公开内容,仅供学习交流;如有疏漏或错误,请联系指正。
画面限制:不得出现官方 logo、商标图形、企业字样、认证徽记、二维码、网址、联系方式、发布者归属行;不得出现日文、乱码、伪文字;不得使用夸张宣传词;不要把内部结构画成确定实物拆解,所有未知细节保持“示意结构”表达;避免标签重叠、微字过小、零件漂浮无主轴、底部声明被裁切。
标题候选
1. 推荐:压电光机械单片CMOS光子平台
2. 单片CMOS光子平台怎样振动?
3. 压电层如何驱动片上光机械?
4. 光机械平台里的压电驱动路径
5. CMOS光子平台的力学夹层
6. 一片芯片里的光机电闭环
7. 压电光机械芯片结构拆解
8. 从波导到压电薄膜的堆叠
9. 单片光子平台为何需要振动
10. 光场与机械模态怎样相遇
11. CMOS光子平台的隐藏机械层
12. 压电薄膜如何调制光谐振
13. 光机械谐振腔的片上路径
14. 单片集成里的光机电权衡
15. 压电光机械平台结构看点
16. 光子芯片上的压电执行器
17. 片上光机械系统如何闭环
18. 硅光波导如何连接机械腔
19. CMOS电路怎样读出微振动
20. 压电光机械平台的九层结构
21. 光机电共封装前的单片方案
22. 微纳机械层如何改变光路
23. 压电驱动如何进入光子芯片
24. 单片CMOS光子平台的底座
25. 从电极到波导的耦合链路
26. 光机械芯片为何重视隔离层
27. 片上压电调制的结构逻辑
28. 光子平台里的机械自由度
29. 压电光机械系统的读出链路
30. CMOS光子与MEMS如何叠合
互动提问
1. 压电光机械单片CMOS光子平台中,压电薄膜主要通过什么物理路径调制光学谐振?
2. 压电光机械单片CMOS光子平台中,机械谐振腔的 Q 值会受到哪些结构因素影响?
3. 压电光机械单片CMOS光子平台中,金属电极与光波导之间需要怎样降低光学损耗?
4. 压电光机械单片CMOS光子平台中,CMOS 控制电路承担哪些驱动和读出功能?
5. 压电光机械单片CMOS光子平台中,悬空释放结构为什么会影响机械模态稳定性?
6. 压电光机械单片CMOS光子平台中,介质隔离层如何同时服务电学隔离与光学约束?
7. 压电光机械单片CMOS光子平台中,射频走线的寄生参数会限制哪些动态性能?
8. 压电光机械单片CMOS光子平台中,热漂移会怎样影响光机械耦合效率?
9. 压电光机械单片CMOS光子平台中,阵列化扩展需要解决哪些一致性问题?
10. 压电光机械单片CMOS光子平台中,片上反馈回路为什么能提升系统稳定性?
发布文案
短文版:
通过这张图可以看到,压电光机械单片 CMOS 光子平台不是单纯把光波导、电极和电路堆在一起,而是把光场、机械模态、压电应变和 CMOS 反馈连成一条闭环链路。真正难点在于多物理场同时兼容:光要低损耗,机械要高 Q,电极要高效率,电路还要可读出、可校准。
声明:信息整理自网络公开内容,仅供学习交流;如有疏漏或错误,请联系指正。
长文版:
通过这张图可以看到,压电光机械单片 CMOS 光子平台的核心,是让“光信号”和“机械振动”在微纳谐振结构中相互作用,再由压电薄膜把电信号转成局部应变,最后交给 CMOS 电路完成驱动、读出、反馈和校准。它的价值不只在集成度,而在缩短信号路径、降低封装误差,并为片上调制、微波光子、传感和可重构光路提供结构基础。
声明:信息整理自网络公开内容,仅供学习交流;如有疏漏或错误,请联系指正。
社群版:
通过这张图可以看到,压电光机械单片 CMOS 光子平台可以按 9 个层级理解:耦合接口、波导网络、光机械腔、悬空机械层、压电薄膜、电极、隔离互连、CMOS 控制、衬底热路径。看懂这条链路,就能看清它为什么同时卡在光损耗、机械 Q、压电效率和电路寄生参数上。
声明:信息整理自网络公开内容,仅供学习交流;如有疏漏或错误,请联系指正。
文本风险提示:这里的“爆炸图/拆解”仅指工程示意图表达,不涉及危险行为;内容为技术科普语境。
tokens used
24,530
Imagegen Prompt
text
画布比例:3:4,竖版中文技术拆解海报。主题为「压电光机械单片 CMOS 光子平台」,做成概念爆炸图 / 示意结构图,不表现为已验证实物拆解。
视觉风格:高洁净度半导体工程海报,浅色硅片灰底,局部青绿色光路、琥珀色压电层、深灰金属互连;中心为完整芯片平台的半透明 3D 剖切主视觉,沿纵向拆开 9 个编号层级,左右双侧短标注,现代无衬线中文排版,信息密度高但不拥挤。
阅读路径:完整平台主视图 -> 中央分解轴 -> 编号组件层。
标题:压电光机械单片 CMOS 光子平台
副标题:把光学谐振、机械振动、压电驱动与 CMOS 控制放进同一片芯片的示意结构
编号组件层:
01 光输入/输出耦合区:光纤或片上耦合进入波导,作为光信号接口。
02 硅光波导网络:负责片上光传输、分束、干涉与路由。
03 光机械谐振腔:用微纳结构把光场与机械振动模式耦合。
04 悬空机械梁/膜结构:提供可振动的低损耗机械自由度。
05 压电薄膜驱动层:把电信号转换为局部应变,调制机械与光学状态。
06 上下金属电极:为压电层施加射频或低频驱动信号。
07 介质隔离与通孔互连:连接光子层、驱动层与控制电路,同时保持电学隔离。
08 CMOS 控制与读出电路:实现驱动、调制、检测、反馈与校准。
09 衬底与热路径:提供机械支撑、工艺兼容性与热稳定基础。
左侧标注:
「光-机-电闭环」
光场读出机械运动,压电层注入可控应变,CMOS 电路完成反馈控制。
「单片集成挑战」
光损耗、机械 Q 值、压电效率、金属互连寄生参数需要同时权衡。
右侧标注:
「为什么要放在同一片」
减少封装耦合误差,缩短信号路径,提高阵列化与系统稳定性。
「适用方向」
片上调制、频率转换、微波光子、传感、可重构光子电路。
辅助微标签:低损耗波导、应变调制、悬空释放区、射频走线、反馈读出、热漂移补偿、片上校准、阵列扩展。
下方中部信息框只放来源声明:
声明:信息整理自网络公开内容,仅供学习交流;如有疏漏或错误,请联系指正。
画面限制:不得出现官方 logo、商标图形、企业字样、认证徽记、二维码、网址、联系方式、发布者归属行;不得出现日文、乱码、伪文字;不得使用夸张宣传词;不要把内部结构画成确定实物拆解,所有未知细节保持“示意结构”表达;避免标签重叠、微字过小、零件漂浮无主轴、底部声明被裁切。
标题候选
1. 推荐:压电光机械单片CMOS光子平台
2. 单片CMOS光子平台怎样振动?
3. 压电层如何驱动片上光机械?
4. 光机械平台里的压电驱动路径
5. CMOS光子平台的力学夹层
6. 一片芯片里的光机电闭环
7. 压电光机械芯片结构拆解
8. 从波导到压电薄膜的堆叠
9. 单片光子平台为何需要振动
10. 光场与机械模态怎样相遇
11. CMOS光子平台的隐藏机械层
12. 压电薄膜如何调制光谐振
13. 光机械谐振腔的片上路径
14. 单片集成里的光机电权衡
15. 压电光机械平台结构看点
16. 光子芯片上的压电执行器
17. 片上光机械系统如何闭环
18. 硅光波导如何连接机械腔
19. CMOS电路怎样读出微振动
20. 压电光机械平台的九层结构
21. 光机电共封装前的单片方案
22. 微纳机械层如何改变光路
23. 压电驱动如何进入光子芯片
24. 单片CMOS光子平台的底座
25. 从电极到波导的耦合链路
26. 光机械芯片为何重视隔离层
27. 片上压电调制的结构逻辑
28. 光子平台里的机械自由度
29. 压电光机械系统的读出链路
30. CMOS光子与MEMS如何叠合
互动提问
1. 压电光机械单片CMOS光子平台中,压电薄膜主要通过什么物理路径调制光学谐振?
2. 压电光机械单片CMOS光子平台中,机械谐振腔的 Q 值会受到哪些结构因素影响?
3. 压电光机械单片CMOS光子平台中,金属电极与光波导之间需要怎样降低光学损耗?
4. 压电光机械单片CMOS光子平台中,CMOS 控制电路承担哪些驱动和读出功能?
5. 压电光机械单片CMOS光子平台中,悬空释放结构为什么会影响机械模态稳定性?
6. 压电光机械单片CMOS光子平台中,介质隔离层如何同时服务电学隔离与光学约束?
7. 压电光机械单片CMOS光子平台中,射频走线的寄生参数会限制哪些动态性能?
8. 压电光机械单片CMOS光子平台中,热漂移会怎样影响光机械耦合效率?
9. 压电光机械单片CMOS光子平台中,阵列化扩展需要解决哪些一致性问题?
10. 压电光机械单片CMOS光子平台中,片上反馈回路为什么能提升系统稳定性?
发布文案
短文版:
通过这张图可以看到,压电光机械单片 CMOS 光子平台不是单纯把光波导、电极和电路堆在一起,而是把光场、机械模态、压电应变和 CMOS 反馈连成一条闭环链路。真正难点在于多物理场同时兼容:光要低损耗,机械要高 Q,电极要高效率,电路还要可读出、可校准。
声明:信息整理自网络公开内容,仅供学习交流;如有疏漏或错误,请联系指正。
长文版:
通过这张图可以看到,压电光机械单片 CMOS 光子平台的核心,是让“光信号”和“机械振动”在微纳谐振结构中相互作用,再由压电薄膜把电信号转成局部应变,最后交给 CMOS 电路完成驱动、读出、反馈和校准。它的价值不只在集成度,而在缩短信号路径、降低封装误差,并为片上调制、微波光子、传感和可重构光路提供结构基础。
声明:信息整理自网络公开内容,仅供学习交流;如有疏漏或错误,请联系指正。
社群版:
通过这张图可以看到,压电光机械单片 CMOS 光子平台可以按 9 个层级理解:耦合接口、波导网络、光机械腔、悬空机械层、压电薄膜、电极、隔离互连、CMOS 控制、衬底热路径。看懂这条链路,就能看清它为什么同时卡在光损耗、机械 Q、压电效率和电路寄生参数上。
声明:信息整理自网络公开内容,仅供学习交流;如有疏漏或错误,请联系指正。
文本风险提示:这里的“爆炸图/拆解”仅指工程示意图表达,不涉及危险行为;内容为技术科普语境。