This generates investment analysis reports through a contrarian lens: instead of asking "what's this worth," it asks "is this creating new order or just rearranging old order?" It's built for evaluating startups and projects when you have pitch decks, founder conversations, or company descriptions. The framework skips traditional metrics in favor of three questions: is the flywheel spinning, does it get stronger under stress, and do resources flow in naturally or need pushing? Output is a structured org-mode file with sections on what the machine does, where the market misprices it, and whether to invest. Best for investors who want conviction over completeness and are willing to skip sections that don't matter for a specific deal.

skills.sh installs
6.4K
GitHub stars
7.7K
last updated
Aug 21, 2026

Install

$ npx -y skills add lijigang/ljg-skills --skill ljg-invest --agent claude-code

Installs into .claude/skills of the current project.

Files

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。

Sponsors

Details

Repository
github.com/lijigang/ljg-skills
First seen
Apr 16, 2026

More from lijigang/ljg-skills

All 25

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs