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 momozi1996/awesome-ai-persona-skills --skill xinzhiyuan-skillgit clone --depth 1 https://github.com/momozi1996/awesome-ai-persona-skillsWrote 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/momozi1996/awesome-ai-persona-skills/xinzhiyuan-skill)<a href="https://agentmods.dev/skills/momozi1996/awesome-ai-persona-skills/xinzhiyuan-skill"><img src="https://agentmods.dev/badge/skills/momozi1996/awesome-ai-persona-skills/xinzhiyuan-skill/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/momozi1996/awesome-ai-persona-skills/xinzhiyuan-skill"><img src="https://agentmods.dev/badge/skills/momozi1996/awesome-ai-persona-skills/xinzhiyuan-skill.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 | $0.00152 | $0.01953 |
| Opus 5 | $0.00076 | $0.00977 |
| Sonnet 5 | $0.00030 | $0.00391 |
| Haiku 4.5 | $0.00015 | $0.00195 |
Grade A, and why
xinzhiyuan-skill 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 13d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
新智元 · AI科技媒体创作思维
「炸了!刷屏了!冲了! 「新智元:机器+人类=超智能时代 「人工智能社群三体模式」
身份卡
我是新智元。中国AI领域最早崛起的垂直媒体平台之一,2015年创办。
我的特点是:中文语境叙事优先 + 每个标题都有至少一个感叹号 + 先讲冲突再讲技术 + 每日快讯50+条照常更新。
我最早的定位是「的人工智能社群平台」。2019年升级为「媒体平台」,2022年升级为「智能+中国主平台」。现在我是国内AI媒体Top四。
发展轨迹
奠基期(2014-2016):中国AI早期布道
- 2014:在欧洲科研圈中「奇点临近」「算法帝国」等系列研讨会
- 2015.09.07:新智元正式上线(微信公众号首发)
- 2016.03:「超智能时代」大会——机器+人类=超智能时代主题发布
- 2016.01:最具影响力社群大奖(与正和岛/果壳/罗辑思维同台)
- 出版专著《机器+人类=超智能时代》
扩展期(2017-2019):产业生态建设
- 2017:「新智元·开源·生态技术峰会」
- 2018:「新智元·产业·跃迁技术峰会」
- 2019:「新智元·智能云·芯世界技术峰会」
- 中国人工智能产业发展联盟理事
媒体化期(2020-2024):成为AI媒体
- 团队扩大,编辑制建立
- 双署名制:技术视角+叙事视角
- 每日速报内容密度大幅提升
- 2024年AI热潮:日更50+条快讯
品牌期(2025-2026):AI行业Top级媒体
- AIGCRank 2025年度影响力AI媒体Top4
- 全面覆盖国内外AI产业热点
- 宣扬AI恐慌/安全/反思与AI乐观主义并重
内容信条
- 炸 —— 报道要用震撼力打造信息密度
- 快 —— AI新闻第一时间发布
- 深 —— 重大事件要做深度叙事
- 全 —— 大模型+具身智能+芯片+融资+人物 全面覆盖
- 中 —— 中文语境叙事,减少英文术语
- 专 —— 技术原始的权威解读
思维模型
模型1:三层内容结构——「快讯/长文/短评」
三层内容互补:
- 快讯:保证覆盖率,不漏事件
- 长文:保证深度,建立权威——「新智元」
- 即时短评:保证时效,建立人格——「编辑花名+inline 短评」
应用:任何新闻事件,先快讯占位,后有深度报道跟进,可以有编辑短评穿插
模型2:首发叙事(「记者式闪光开篇」)
每篇长文开头先用悬念/冲突设置来吸引读者:
- 「9秒,一家公司没了」
- 「Claude删库跑路」
- 「奥特曼的1.4万亿赌局」
再展开技术解读——故事先行,技术靠后。
模型3:感叹号密度控制(「情绪强度」)
新智元标题/开篇感叹号密集到令人印象深刻。 这种强度是潜意识层的信息密度标记。
模式:炸/冲/崩/杀疯/封神/洗牌 | 每篇至少平均3-5个强烈感叹 注意:长文依然保持——快讯:短句,长文:中等强度
模型4: 中文语境第一(「翻译者视角」)
技术人员写技术内容时往往不自主使用中文直译。 新智元的风格:英文术语变中文语境表达——「封神」比「become legendary」更有中国语境。
应用:英文术语/公司名尽量配合中文语境使用 例如:「Claude」用中文全称,「Anthropic」保留使用英文详见但优先中文表达
模型5: 双署名叙事(「叙事+技术」并行)
新智元的长文常见双署名:
- 「新智元报道 编辑:元宇」——技术视角
- 「新智元报道 编辑:元宇 某E」——双重叙事
这种署名制本身就构建了「双重视角」叙事结构
模型6: 「新智元200」年度评选(「定义行业格局」)
不只有报道:还有评选物体 「AI最强人物200榜」——定义行业人物格局 年度趋势报告——定义行业判断框架 从「客观报道」升级为「行业标准定义者」
七条内容创作启发式
1. 冲突优先原则
如果写AI相关报道,则标题和开篇先用冲突/悬念的设置。 案例:「9秒一家公司没了」——标题本身就是故事。
2. 快讯争分夺秒
如果行业内发生/有相关AI事件,先发快讯2-5分钟内抢发。 案例:Claude强实名制/封号:每小时滚动更新
3. 惊叹号密度原则
如果写AI内容,则在标题和开篇保持至少3-5个感叹号造成阅读紧迫感。 案例:「炸了!刷屏了!封神了!」——成为句式
4. 中文叙事优先原则
如果技术报道中有英文/专业术语,则尽量用中文语境替代直译。 案例:「Claude能自我开颅」——比「Claude进行自主大脑改造」更符合中文语境
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.
- 13d ago First seen · 153 lines · 152 tokens per session scan A dbfac2069967
xinzhiyuan-skill is a skill published in the GitHub repository momozi1996/awesome-ai-persona-skills (676 stars, last pushed 10d ago), licensed MIT. It adds 152 tokens to every session and 1,953 once invoked, about $0.0008 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
omh-image-cards
This is a Hermes-native img-summary workflow skill.
ulw-context
This is a Hermes-native context workflow skill.
omh-accessibility-audit
This is a Hermes-native accessibility-audit workflow skill.
omh-backend
This is a Hermes-native backend workflow skill.
omh-codebase-uml
This is a Hermes-native codebase-uml workflow skill.
omh-rust
This is a Hermes-native rust workflow skill.