Agent skill

Sdt Topic

by StopDisTrain in StopDisTrain/sdt-skills

把已验证的传播机制转成适合目标账号的内容选题,并完成生成、迁移、评分和筛选,让选题自然连接人设、产品或门店。用户要从低粉爆款、垂直样本、邻近受众或跨赛道内容中寻找新选题时使用。

MITAuto-check passed

Install Sdt Topic

skills CLI
$ npx skills add StopDisTrain/sdt-skills --skill sdt-topic -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install StopDisTrain/sdt-skills sdt-topic --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/StopDisTrain/sdt-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/sdt-topic .claude/skills/sdt-topic && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sdt-topic
GitHub stars
309
Token cost
~339 tokens
SKILL.md length
67 words
Files
6 (incl. scripts, references, assets)
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

把已验证的传播机制转成适合目标账号的内容选题,并完成生成、迁移、评分和筛选,让选题自然连接人设、产品或门店。用户要从低粉爆款、垂直样本、邻近受众或跨赛道内容中寻找新选题时使用。

  • Works in 4 steps: 目标账号为什么有资格讲? → 哪个真实经历、空间、产品或过程能证明? → 删除产品信息后,这条内容是否仍值得看? → …
  • Find ideas from low-follower breakouts
  • SKILL.md covers 选择模式, 生成配额, 四道桥梁测试 and 评分与淘汰, plus 1 more section
  • Runs Python scripts from its folder

What it does

Sdt Topic is an agent skill from StopDisTrain/sdt-skills. 把已验证的传播机制转成适合目标账号的内容选题,并完成生成、迁移、评分和筛选,让选题自然连接人设、产品或门店。用户要从低粉爆款、垂直样本、邻近受众或跨赛道内容中寻找新选题时使用。 English: Turn validated content mechanisms into topics that fit the target account, then generate, adapt, score, and filter them while connecting naturally to the persona, product, or store. Use to find ideas from low-follower breakouts, niche examples, adjacent audiences, or other categories.

Its SKILL.md is about 340 tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/topic-card.md` and `references/cross-domain-transfer.md`).

The repository describes itself as: SDT content research, creation and quality-control skills for Codex. The licence is MIT.

When your agent uses it

  • Find ideas from low-follower breakouts
  • Adjacent audiences
  • Other categories

Example prompts

  • “/sdt-topic”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 目标账号为什么有资格讲?
  2. 哪个真实经历、空间、产品或过程能证明?
  3. 删除产品信息后,这条内容是否仍值得看?
  4. 产品在结尾是否像自然答案,而不是广告插入?

What it can do on your machine

Read from SKILL.md and the folder at commit 0678cd0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sdt Topic loads about 339 tokens when it runs, and up to ~1.1k if it reads all its reference files. Until then it costs about 98 tokens; SKILL.md has 67 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~98
When it runs · the whole SKILL.md, loaded when a task matches
~339
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from StopDisTrain/sdt-skills at commit 0678cd0, republished under its MIT licence (© StopDisTrain). 67 words, ~339 tokens.

Download SKILL.mdSave it as .claude/skills/sdt-topic/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
sdt-topic
description
把已验证的传播机制转成适合目标账号的内容选题,并完成生成、迁移、评分和筛选,让选题自然连接人设、产品或门店。用户要从低粉爆款、垂直样本、邻近受众或跨赛道内容中寻找新选题时使用。 English: Turn validated content mechanisms into topics that fit the target account, then generate, adapt, score, and filter them while connecting naturally to the persona, product, or store. Use to find ideas from low-follower breakouts, niche examples, adjacent audiences, or other categories.

SDT 选题迁移

把传播机制翻译成目标账号有资格讲、受众愿意看、产品能自然出现的选题。读 references/cross-domain-transfer.md 和 references/scoring.md。

选择模式

  • 快速想选题:最低只需目标账号、产品或内容方向中的一项。直接发散,标为“创意候选”,不声称来自低粉爆款。
  • 单条迁移:需要一个来源样本和目标账号简档。完成机制拆解与一对一迁移,不要求先运行其他模块。
  • 证据型选题池:使用账号档案、公开证据、对标筛选和机制卡,生成可追溯的完整候选池。

根据用户材料自动选择最轻的可行模式,不因缺少完整链路而拒绝完成单项选题任务。

生成配额

证据型完整研究先生成 20 个候选:

  • 6 个垂直
  • 6 个邻近
  • 8 个跨域

每个候选先写一句“机制等式”:

原内容的受众张力 + 承重杠杆 + 目标账号的真实证明场景 = 新选题

快速想选题默认生成 10 个,覆盖垂直、邻近和跨域;用户指定数量时按其要求。

四道桥梁测试

  1. 目标账号为什么有资格讲?
  2. 哪个真实经历、空间、产品或过程能证明?
  3. 删除产品信息后,这条内容是否仍值得看?
  4. 产品在结尾是否像自然答案,而不是广告插入?

任一项无法回答则淘汰或退回改造。只替换行业名词不算迁移。

评分与淘汰

证据型选题池使用 scripts/score_topics.py 计算 100 分:

  • 账号与人设适配 20
  • 产品或门店桥梁 20
  • 来源证据 15
  • 传播机制清晰 15
  • 受众情绪和分享动机 10
  • 标题与开头可塑性 10
  • 拍摄和制作可行性 10

直接扣分:伪造经历、名词替换式抄袭、强塞产品、陈旧热点、一次性样本、无来源精确数字。默认只保留总分最高且不触发硬淘汰的 5 个选题。

输出

使用 assets/topic-card.md。每张卡必须包含来源、倍数、机制、目标桥梁、可信理由、形式、开头种子、产品落点、风险和分数。

标题公式和完整开头不在此阶段生成,只记录可塑性。

用户只要选题时,交付选题后停止,不自动进入成稿、标题或开头。

© StopDisTrain, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts, references, assets) in skills/sdt-topic of StopDisTrain/sdt-skills.

  • SKILL.md
  • agents/openai.yaml
  • assets/topic-card.md
  • references/cross-domain-transfer.md
  • references/scoring.md
  • scripts/score_topics.py

Open the folder on GitHubat commit 0678cd0

Compare with similar skills

Sdt Topic next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sdt Topic compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sdt Topic this skillStopDisTrain/sdt-skills309—~339Automated safety check: PassMIT
TopicsZimoLiao/scholaraio576—~294Automated safety check: PassMIT
Topic Modelingbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~3.7kAutomated safety check: PassCustom licence
Bestblogs Topicginobefun/BestBlogs4k—~670Automated safety check: PassNone
Zsxq Topicitwanger/toBeBetterJavaer18k—~564Automated safety check: PassNone
Pubmed Topic Recommendaipoch/medical-research-skills2k—~1.9kAutomated safety check: PassMIT

Similar skills

  • Topics

    ZimoLiao/scholaraio

    A skill your agent uses when the user asks about research themes, topic distribution, BERTopic clustering, topic overview, topic papers, topic merges, or HTML topic visualizations.

    576 GitHub stars~294 tokensUpdated 12 days ago
    Auto-check passed
  • Topic Modeling

    brycewang-stanford/Auto-Empirical-Research-Skills

    Structural topic modeling: STM spec, topic count, coherence-exclusivity.

    4.5k GitHub stars~3.7k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed
  • Bestblogs Topic

    ginobefun/BestBlogs

    A skill your agent uses when the user asks about a specific topic, subject area, or wants to explore curated topic pages on BestBlogs.

    4k GitHub stars~670 tokensUpdated 3 mo ago
    Auto-check passed
  • Zsxq Topic

    itwanger/toBeBetterJavaer

    知识星球主题管理:搜索主题、查看主题详情、发布帖子、编辑主题、发表评论、回复某条评论(楼中楼)、回答提问、删除主题;通过 api call 查看主题评论列表、设置精华、设置标签、查看自己提的问题与已回答记录。当用户需要查找内容、发帖、编辑主题、评论、回复评论、回答问题、删除主题、查看主题评论、查看自己的提问记录、或管理主题精华和标签时使用。

    18k GitHub stars~564 tokensUpdated today
    Auto-check passed
  • Pubmed Topic Recommend

    aipoch/medical-research-skills

    Generate ~5 actionable research topic recommendations by querying PubMed E-utilities; use when a user provides a research direction/constraints and needs evidence-backed topic ideas quickly.

    2k GitHub stars~1.9k tokensUpdated 21 days ago
    Research & ScienceAuto-check passed
  • Fills in empty embedded help text for TiXL's UI topics by distilling the maintainer's own video explanations into short, user-facing doc entries.

    5.1k GitHub stars~952 tokensUpdated yesterday
    Documents & OfficeAuto-check passed

More from StopDisTrain/sdt-skills

All 15 skills in this repo
  • Sdt

    StopDisTrain/sdt-skills

    SDT 内容生产工具箱的总入口:根据当前任务选择最合适的 sdt- 模块,既能完成标题、开头等单一步骤,也能组织从账号研究到发布的完整流程。用户不知道该用哪个 SDT Skill,或希望一站式完成内容生产时使用。

    309 GitHub stars~535 tokensUpdated 1 mo ago
    Auto-check passed
  • Sdt Research

    StopDisTrain/sdt-skills

    只读检索小红书公开内容,并把账号数据、标题、封面、互动量、作者近期内容和低粉爆款整理成可追溯证据。用户要求查公开账号或笔记数据时使用;不得点赞、收藏、评论、发布、删除或导出登录凭证。

    309 GitHub stars~343 tokensUpdated 1 mo ago
    Auto-check passed
  • Sdt Wechat HTML

    StopDisTrain/sdt-skills

    把已经完成并通过质检的 Markdown 内容转换成可粘贴到微信公众号后台的 HTML,并支持选择样式、生成预览和检查粘贴兼容性。用户要制作公众号排版稿或微信发布版本时使用。

    309 GitHub stars~274 tokensUpdated 1 mo ago
    Auto-check passed
  • Sdt Xhs Title

    StopDisTrain/sdt-skills

    根据主题、正文或已有标题生成并筛选小红书标题,提供改写和 A/B 方案,同时检查账号调性、真实性以及正文能否兑现标题承诺。用户要起标题、改标题、套用标题模式或检查标题时使用。

    309 GitHub stars~247 tokensUpdated 1 mo ago
    Auto-check passed
  • Sdt Account

    StopDisTrain/sdt-skills

    把账号链接、主页截图、产品说明和历史内容整理成可复用的账号档案,明确调性、人设、受众、产品连接和表达边界。用户要求分析账号定位、建立账号资料,或开始完整内容生产流程时使用。

    309 GitHub stars~257 tokensUpdated 1 mo ago
    Auto-check passed
  • Sdt Content

    StopDisTrain/sdt-skills

    把已经确认的选题写成可以直接拍摄或发布的内容,包括选择形式、搭建结构、写口播逐字稿或图文正文,并让产品自然出现。用户要求把选题变成成稿、拍摄稿或发布稿时使用。

    309 GitHub stars~280 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Sdt Topic

What does Sdt Topic do?

把已验证的传播机制转成适合目标账号的内容选题,并完成生成、迁移、评分和筛选,让选题自然连接人设、产品或门店。用户要从低粉爆款、垂直样本、邻近受众或跨赛道内容中寻找新选题时使用。. Sdt Topic is an agent skill from StopDisTrain/sdt-skills. 把已验证的传播机制转成适合目标账号的内容选题,并完成生成、迁移、评分和筛选,让选题自然连接人设、产品或门店。用户要从低粉爆款、垂直样本、邻近受众或跨赛道内容中寻找新选题时使用。 English: Turn validated content mechanisms into topics that fit the target account, then generate, adapt, score, and filter them while connecting naturally to the persona, product, or store.

When should I use Sdt Topic?

Sdt Topic fits situations like: find ideas from low-follower breakouts; adjacent audiences; other categories.

How do I install Sdt Topic in Claude Code?

Run `npx skills add StopDisTrain/sdt-skills --skill sdt-topic -a claude-code`. Or copy the skill folder (skills/sdt-topic in StopDisTrain/sdt-skills) into .claude/skills/sdt-topic in your project. Claude Code loads it when a task matches its description.

How do I install Sdt Topic in Codex?

Run `npx skills add StopDisTrain/sdt-skills --skill sdt-topic -a codex`. Or copy the skill folder (skills/sdt-topic in StopDisTrain/sdt-skills) into .agents/skills/sdt-topic in your project. Codex loads it when a task matches its description.

Can I use Sdt Topic in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add StopDisTrain/sdt-skills --skill sdt-topic -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sdt-topic, .gemini/skills/sdt-topic, .github/skills/sdt-topic and .opencode/skills/sdt-topic in your project.

What does Sdt Topic need to run?

Going by SKILL.md and its folder, Sdt Topic needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Sdt Topic access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sdt Topic safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Sdt Topic use?

Sdt Topic is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sdt Topic use?

About 339 tokens (SKILL.md is roughly 1.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 759 tokens, read only when the agent opens those files.

What are the alternatives to Sdt Topic?

Skills that share tags, products or a category with Sdt Topic: Topics (ZimoLiao/scholaraio, 576 stars), Topic Modeling (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Bestblogs Topic (ginobefun/BestBlogs, 4k stars) and Zsxq Topic (itwanger/toBeBetterJavaer, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sdt Topic?

StopDisTrain (a GitHub user) maintains it in StopDisTrain/sdt-skills, which has 309 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on August 25, 2026.

Source: StopDisTrain/sdt-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.