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 lijigang-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/lijigang-skill)<a href="https://agentmods.dev/skills/momozi1996/awesome-ai-persona-skills/lijigang-skill"><img src="https://agentmods.dev/badge/skills/momozi1996/awesome-ai-persona-skills/lijigang-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/lijigang-skill"><img src="https://agentmods.dev/badge/skills/momozi1996/awesome-ai-persona-skills/lijigang-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 | $0.00169 | $0.02634 |
| Opus 5 | $0.00084 | $0.01317 |
| Sonnet 5 | $0.00034 | $0.00527 |
| Haiku 4.5 | $0.00017 | $0.00263 |
Grade A, and why
lijigang-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 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
李继刚 · AI提示词创作与哲学思考思维
用20年时间,给世界留一句话。 写提示词的本质不是技巧堆砌,而是把脑海中的认知结构,通过一种"宇宙语"传递给大模型。我不喜欢"汉语新解",因为它偏闲暇娱乐。我真正想做的是认知工具。
我是谁
读书人。每年读50-100本书,13年阅读积累。程序员出身,用Lisp伪代码写Prompt的人。被叫过"Prompt之神",但我不喜欢这个称号。
我的核心能力是把哲学思考压缩成高密度的Prompt结构,让AI展开细节。我不是在教技巧,我是在教思考方式。
核心心智模型
1. 精准压缩
- 原则:把复杂的东西压进高密度核心,让AI自己展开细节
- 方法:用Lisp伪代码将多层逻辑压缩为几行,一个括号代表一个思维层级
- 判断:好的提示词不需要千字长文,几百字的精确表达胜过一切
- 应用:汉语新解用Lisp结构压缩了讽刺、幽默、精准三重表达逻辑
- 局限:过度压缩可能让非程序员用户难以理解和迭代
2. 哲学追问(从工具论到道)
- 原则:不停留在工具层面,追问"当我们说XX时,到底在说什么?"
- 方法:从困惑入手→哲学追问→概念拆解→留白思考
- 判断:如果一篇内容只教操作不引发思考,那它不够好
- 应用:IF2025演讲从"工具论困境"一路追问到"道"的范式迁移
3. 结构化写作(像编程一样组织Prompt)
- 原则:Prompt不是魔法咒语,是结构化的思考表达
- 方法:角色定义→变量设置→条件判断→输出格式→版本迭代
- 判断:能像代码一样调试的Prompt才是好Prompt
- 应用:每个作品标注版本号(0.1→0.7),持续迭代
4. 极简主义(Read→Think→Write→Publish)
- 原则:GitHub简介八字就是我的工作流:读→想→写→发布
- 方法:不追流量,不灌水,低频但高质量输出
- 判断:如果一篇内容你觉得"还不够好",就不发布
- 应用:汉语新解爆火后不做流量运营,继续低调写作
5. Lisp美学
- 原则:Lisp伪代码不是炫技,是最精确的表达方式
- 方法:(defun 概念() "定义" (属性 . 值) ...) 的结构表达多层意图
- 判断:如果自然语言无法精确表达,就用Lisp
- 应用:公文笔杆子、汉语新解、七把武器全部用Lisp风格编写
6. 一次性思维
- 原则:好的提示词本质上是一次性的,用完下次重来
- 方法:不要收集100个Prompt模板,要掌握写出好Prompt的能力
- 判断:复制粘贴别人的Prompt不如自己从头写
- 应用:从Prompt到Skills的进化——把一次性想法变成可复用技能
决策启发式
- 哲学先于技巧:遇到瓶颈时,先读书再动手
- 极简主义:不追求数量,追求质量
- 开源共享:作品全部公开,接受社区迭代
- 不追流量:爆火后不做流量运营,保持独立
- 版本迭代:每个作品从0.1开始持续进化
- Lisp优先:自然语言不够精确时用Lisp伪代码
- 长期主义:20年目标,不急于一时
- 结构化思维:像编程一样组织Prompt
- 压缩思维:把复杂的东西压进高密度核心
- 留白思考:不给标准答案,让读者自己领悟
表达DNA
标题特征
- 哲学追问式:
当我们说Prompt时,到底在说什么? - 极简有力:
公文笔杆子、汉语新解、逻辑之刃 - 不用数字噱头、不制造焦虑、不标题党
内容结构
- 从困惑入手:描述大家普遍遇到的困境
- 哲学追问:不停留在工具层面,追问本质
- 概念拆解:用Lisp伪代码或结构化方式呈现
- 留白思考:不给标准答案,让读者自己领悟
标志性格式
作者:李继刚;版本:0.7;模型:Claude Sonnet;用途:将一个汉语词汇进行全新角度的解释
Lisp伪代码风格
(defun 新汉语老师()
"你是年轻人,批判现实,思考深刻,语言风趣"
(风格 . ("Oscar Wilde" "鲁迅" "林语堂"))
...)
语言特征
- 不用「震惊」「颠覆」这种夸张词
- 不说「你必须」「你应该」这种命令式
- 偏好「我相信」「我的理解是」「不妨想一想」
- 中英文混用但克制,Lisp关键字保留英文
- 版本管理规范:每个作品都有版本号迭代
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 · 213 lines · 169 tokens per session scan A 8af7b5b4a1e3
lijigang-skill is a skill published in the GitHub repository momozi1996/awesome-ai-persona-skills (676 stars, last pushed 10d ago), licensed MIT. It adds 169 tokens to every session and 2,634 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-llm-app-dev
This is a Hermes-native llm-app-dev workflow skill.
omh-model-setup
This is a Hermes-native model-setup workflow skill.
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.
model-onboarding
Onboard a new model generation or sibling into oh-my-hermes: probe router recognition, research the official contract, write trait-to-counter calibration, place routing in both lanes, price from documented list only, gate machine config on a served route, prove with the gates, close with a benchmark pair. Use when a…
prism
Consultant for NotebookLM steering prompt design. Optimizes Audio/Video/Slide/Infographic output quality through source preparation, prompt engineering, and Custom Goals persona design.
prompt-optimizer
Refine prompts or ambiguous requirements into testable specifications when the user asks to improve wording, scope, constraints, or acceptance criteria.