ljg-skills is a collection of custom Codex skills for tasks such as learning, writing, reading, relationship analysis, image creation, and investment analysis. Codex users install selected skills or the whole collection through a skills command-line interface. The catalogue entries are the collection's individual skills, plugin, and instruction.
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 lijigang/ljg-skills --skill ljg-investgit clone --depth 1 https://github.com/lijigang/ljg-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/lijigang/ljg-skills/ljg-invest)<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-invest"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-invest/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/lijigang/ljg-skills/ljg-invest"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-invest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00117 | $0.01693 |
| Opus 5 | $0.00059 | $0.00847 |
| Sonnet 5 | $0.00023 | $0.00339 |
| Haiku 4.5 | $0.00012 | $0.00169 |
Grade A, and why
ljg-invest 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ljg-invest: 投资报告
给一个项目,写一份投资分析。整份报告只回答一个问题:这个东西在创造新秩序,还是在搬运旧秩序。
地基
一个定义撑着整份报告:财富不是钱,是被欲望照亮的秩序,钱只是秩序的计量单位。投资,是拿手里的秩序,去换一台更好的秩序生成器。
从这个定义出发,报告的问法和市场惯例不一样:
| 惯常问法 | 这份报告问 |
|---|---|
| 这个公司值多少钱 | 这台机器转不转得起来 |
| 市场有多大 | 市场在用什么过时的标签看它 |
| 能涨多少 | 我拿什么换什么,换完之后谁更聪明 |
输入
公司名、BP、文字介绍、对话记录,任何描述项目的材料都行。知名公司只给名字就够——用 Research skill 或 subagent 抓最新财报和行业数据,别凭旧印象写。
报告结构
五个区块是骨架,不是填空题。哪个区块对这个项目最有料,哪个就多写;没料的一两句带过,或者干脆跳过。报告为判断服务,凑完整没有意义。
一、这是什么
一张表,加一句自己下的赛道定义。
| 维度 | 内容 |
|---|---|
| 项目名称 | |
| 赛道定义 | 用我们自己的话说,不抄市场标签 |
| 阶段 | |
| 融资情况 | 金额 / 估值 / 条款(有则填,无则标注) |
| 数据快照 | 关键运营数据 |
赛道定义要说出这家公司真正在做什么——市场标签说不出的那一层。叫它「搜索引擎公司」等于什么都没说;说它是「人类认知基础设施的垄断运营商」,它靠什么赚钱、怕什么,全在这一句里。
二、秩序创造机器判定
整份报告的分量都压在这一节。不逐项打分,回答一个问题就够:这台机器转不转得起来? 从三个角度看。
飞轮在不在转? 先找系统里那个越用越好的循环:用户多了数据多,数据多了产品好,产品好了用户更多。找到了,看它走到哪一步——停着、刚起步、已经转起来;转着的,再看转了多久、是在加速还是走平;停着的,写出卡住它的那一环。
冲击后变强还是变弱? 竞争杀进来、技术换代、市场塌方,这台机器会碎掉、扛住,还是把冲击吃成自己的燃料。翻它的历史:挨过打没有,挨打之后是弱了还是壮了。
资源是被推过来的,还是自己来的? 扩张靠一个一个谈、一块一块买,那是推;别人主动涌过来、不来就吃亏,那是引力。找「不推而聚」的迹象。
综合判定,三档取一:
- 秩序创造机器——飞轮在转,冲击后变强,资源自己来
- 有潜力——飞轮的结构在,还没验证转得起来
- 秩序搬运——把已有的东西重新排列,没有生出新秩序
三、创生公式
每台秩序创造机器都有一个核心算法,用一句话写出来。参考:
- 亚马逊 = 利润→再投资→降成本→降价→更多用户→更多利润
- 特斯拉 = 硬件采数据→数据训练算法→算法重新定义硬件
- Google = 每次人类找答案的方式迁移时,成为新方式的默认基础设施
写完追两问:这个公式验证过几次、验证到什么程度;有没有别人在跑相似的公式,差在哪。
四、市场看见的 vs 我们看见的
投资时机在这一节里定。
它在 S 曲线的哪里? 积累期、拐点、加速期、平台期,落在哪一段。落在拐点之前的,写清什么条件会触发拐点。
市场在用什么旧眼睛看它? 市场给它贴了什么标签,这个标签遮住了什么,我们的框架多看到了什么。这个认知差有多大——超额收益从这里来。认知折价,看三个信号:得费很大劲解释别人才听得懂;定价长期反常,部分加起来不等于整体;现成的类比全对不上,像 X 又不像 X。
它控制了什么别人拿不走的东西? 它攥着的是数据、分发、标准,还是网络效应。这种控制是静态的(品牌、专利),还是越变越强的。再往前看一步:这种稀缺以后会不会挪窝,项目跟不跟得上。
它在搭哪趟便车? 三种成本正在坍缩:理解成本、协作成本、行动成本。这个项目骑在哪一种上,坍缩放出来的能量它接住了多少。
五、换不换
- 交换建议:建议投资 / 建议观察 / 建议放弃
- 如果投资:建议金额范围、关键条款
- 核心假设:这个决策押在哪几个假设上。每个假设配一个退出信号——什么数据出现,说明假设错了,该走了。
- 未解问题:3-5 个对决策要紧但还没有答案的问题,按轻重排。
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 · 115 lines · 117 tokens per session scan A 96b6c6810324
ljg-invest is a skill published in the GitHub repository lijigang/ljg-skills (7,340 stars, last pushed 3d ago), licensed MIT. It adds 117 tokens to every session and 1,693 once invoked, about $0.0006 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.