tslj-idea SKILL.md skillA
tslj-idea from liuhaisi2026212-maker/taishang-laojun is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add liuhaisi2026212-maker/taishang-laojun/tslj-idea@git:20261026.e09b363Pins git:20261026.e09b363 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- liuhaisi2026212-maker/taishang-laojun
- Path
skills/tslj-idea/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261026.e09b363, committed Oct 26, 2026
- First version recorded
- Oct 22, 2026
- Size
- 6,218 bytes
- Repository stars
- 517
- License
- a license file GitHub does not identify
看火：选题判断。从用户的经历、场景、参考或热点里判断能拍什么，给出少量私人定制、带理由的方向并推荐一个；也用于判断一个已有选题值不值得拍、会招来什么人。用户不知道拍什么、手里有热点或参考想找切入点、想知道某个选题行不行时使用。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 看火：选题判断 先读[炉心](../taishang-laojun/references/core-mind.md)。 柳爷的判断：**选题决定上限**。一条视频能到十万还是五百万，主要看选题划定了多大的人群；标题、开头决定的是这群人里有多少愿意看下去。选题还决定**来的是谁**。 ## 柳爷最反感的选题 “这些选题的方式已经不是现在的选题方式了。”柳爷念过一串低水平编导式选题，比如“AI 听你看过的资料，它真的看过吗”“想用 AI 接活，先试试你能不能交付这一页”。这些选题挑不出错，毛病出在**公式化、模块化，没有为这个人私人定制**：换谁来拍都一样，所以对谁都没帮助。 每个选题给出来之前过一遍：**这个选题原样交给另一个人还成立吗？**成立就说明它没用上这个用户的东西，重做。 ## 一个选题怎么想出来：选题决策链 柳爷的爆款，选题都是一步步推出来的，没有一条是先拍脑袋定的。按下面的链条推，哪一环缺了就补哪一环： 1. **起点是什么**：一个现场（海边、机场、工厂门口、巨人展）、一个热点（世界杯、Claude 封号）、一条刷到的参考、上一条内容的评论，或者用户自己最近经历的一件事。 2. **观众最关心什么**：热点人群在这件事里最关心的那一个点是什么？（看世界杯的人最关心比分。） 3. **用户能拿什么接住**：自己的经历、能做出来的东西、能演示的操作、独有的判断。接不住的热点不追。 4. **靠哪种吸引力**：娱乐、帮助、实力展示、下危机（见炉心附表）。不同吸引力，开头和门槛完全不同。 5. **会招来谁**：这条展示的是成品、过程、生活还是忙碌？最后会来什么人，是不是用户想要的人？（展示一个预测比分的工具，会招来想拿去赌的人；展示“我忙不过来”，会招来求职者。） 6. **能不能兑现**：开头答应观众的东西，正文拿什么证据接住？ ## 五个判断角度 推的过程中，用这五个角度检查选题是否立得住。它们是观察维度，不是打分公式： - **人群广**：在用户的目标观众里，多少人会碰到这个问题或情绪？Claude 封号在 AI 圈谁都可能遇到，这就是广。细分行业也可以，“广”是相对用户自己的圈子说的。 - **认知基础**：观众已经知道什么？大家都知道 Claude、都知道它不友好，就不用铺垫。观众完全陌生的东西，要能用一个具体动作或场景讲清。 - **心理钩子**：观众心里有什么没说出口的？越不让用越想用、“肯定有坑”、一厢情愿的想象。钩子必须和内容一致。 - **事实可验证**：核心判断拿什么支撑？柳爷讲 Grok 之前查了官方文档。拿不出依据的判断不当选题的地基。 - **低门槛**：教人做事时，让观众觉得“有手就会”，钱、行动力、脑子都只要一点点。必要的门槛不藏，但不在开头堆复杂度。 …
Read the whole file at its exact version.
How to install
mdr add liuhaisi2026212-maker/taishang-laojun/tslj-idea@sha256:f1722340dc1d6457The line at the top of this page pins the label git:20261026.e09b363, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_k2mfhwjpojkpoof5)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Oct 22, 2026 and Oct 26, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261026.e09b363 latest | 2026-10-26 | e09b363 | 6,218 B | A | view · diff |
| git:20261026.69a46cd | 2026-10-26 | 69a46cd | 6,066 B | A | view · diff |
| git:20261026.8db1091 | 2026-10-26 | 8db1091 | 6,027 B | A | view · diff |
| git:20261024.0bd3156 | 2026-10-24 | 0bd3156 | 3,566 B | A | view · diff |
| git:20261022.6ba7530 | 2026-10-22 | 6ba7530 | 3,239 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6218 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
liuhaisi2026212-maker/taishang-laojun · 517 stars · license a license file GitHub does not identify · pushed 2026-10-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_k2mfhwjpojkpoof5 GET https://markdownregistry.com/api/v1/resolve?ref=liuhaisi2026212-maker/taishang-laojun/tslj-idea GET https://markdownregistry.com/api/v1/blob/f1722340dc1d6457f0d5961df27cc2d56882e3bc4854ddde1deddfede55c14ee
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.