Ra 选题 logo

Ra 选题

CommunityPopular
Pluviobyte
ra-选题

选题全生命周期调度:记录选题、深化选题、选题推荐、立项分发(视频/图文/文章/实操长片/多形态)、发布归档。 Use when the user says 灵感xx, 想法xx, 记录选题, 这个可以做个选题, 先存着这个链接, 深化选题/深化一下xx, 给我N个选题, 帮我出选题, 选题推荐, 立项, 做成视频, 制作视频, 做成文章, 制作文章, 做成图文, 制作图文, 做成实操长片, 图文视频文章都做/都分发, 我要自己出镜讲, xx发布了, xx要改; or when the user gives a link plus a target form (链接+制作视频/文章/图文). Owns the 00-选题池 card system: one topic = one card; user never moves files — this skill does.

Overview

PublisherPluviobyte
Repositoryrnskill
Skill namera-选题
Stars
1.6K
Forks
181
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Pluviobyte on GitHub. Read the source before you install it.

Installation

Install the Ra 选题 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Use it in TypingMind

Enable Ra 选题 in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ra 选题 on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ra 选题 is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ra-选题

Goal

把用户的自然语言入口翻译成文件操作。用户只说话:记灵感、给链接、定形态、报发布。建卡、洗稿路由、建条目、挪卡、登记看板全部由本 skill 完成。

核心模型

  • 选题卡 = 户口本01-内容生产/00-选题池/YYYY-MM-DD-<主题>.md(按 _选题卡模板.md)。只记想法、来源、判断、立项去向;正文永远住对应工作台。
  • 立项 = 决定形态的那一刻:一题可多形态;每个形态在自己的工作台建实体,卡上记 - 形态 → [[链接]]
  • 卡不移动文件:立项时只改 frontmatter 状态为 已立项,卡留在 00-选题池/ 原位。
  • 户口本完整性兜底:任何立项动作发现没有卡,先自动补卡再走流程(含直接甩链接洗稿的场景)。

动词表

1. 记录选题(灵感xx / 想法xx / 记录选题xx / 这个链接先存着)

  • 00-选题池/ 建卡:用户原话 + 提炼的一句话说清 + 素材线索;有链接记入 来源:,能解析出平台作品ID的同时填 源ID:<platform>:<post_id>
  • 状态 = 想法;回复卡片路径,不追问、不展开

2. 深化选题(深化xx / xx想清楚点)

  • 找到卡(按文件名或标题匹配),检索素材库/方法论,把角度、钩子、案例写进「深化笔记」
  • 状态 = 深化中(已立项的卡不改状态)
  • 人话规则的适用边界:笔记本体(角度/论据/素材/流量判断)自由写,信息密度优先,不跑 ra-人话 全流程;但候选钩子、开头句、标题方向、金句这类会直接进成稿的种子句,必须遵守 ra-人话 硬禁令(不用「不是A而是B」、真正/其实/本质上、冒号讲义腔、命令式模板开头)。完整的人话精修与质量门在立项洗稿阶段跑,深化阶段不重复。

3. 立项(做成/制作 + 形态;可组合「视频文章图文都做」)

按形态路由,每个形态完成后在卡「已立项」追加一行,最后挪卡:

形态流程落位
视频(AI 成片)有链接走 ra-video-wash-pipeline,纯想法/文稿走 ra-洗稿交接稿 → 视频工作台/待制作/<日期-主题>/交接稿.md
视频(自录口播)洗稿产出口播逐字稿,文首标注「自录口播」视频工作台/逐字稿/
文章有链接先提源文本:抖音/小红书视频用 ra-逐字稿提取skill;B站/YouTube 等视频复用 ra-video-wash-pipeline 的提取环节;网页/推文用 Jina(https://r.jina.ai/<url>)读正文——源资料一律存 视频工作台/.internal/ → 洗成长文(ra-人话 + 方法论/公众号开头方法论),dbs-ai-check 诊断一遍修掉具体指纹 → 按 文章工作台/_文章模板.md 建条目(一篇一文件夹,主稿 + assets/,只存主稿)文章工作台/创作中/ + 发布看板登记「待修改」
图文洗成小红书文案 + dbs-xhs-title 标题候选,按 _图文交接模板.md 生成交接稿(出图归 Codex)图文工作台/待制作/

4. 发布归档(xx发布了 / xx要改)

  • 发布了:看板该行勾选并移入「已发布」日志(日期/平台);文章条目从 待发布/ 移 已发布/
  • 要改:看板移回/登记「待修改」

5. 课程灵感(这个可以进课程 / 课程灵感xx / #课程灵感)

  • 02-课程体系/课程选题库/灵感记录.md 追加一行:- YYYY-MM-DD | 一句话灵感 | 关联:[[选题卡或作品]]
  • 只做积累,不展开课程结构(业务启动前保持最细的线)

6. 选题推荐(给我N个选题 / 帮我出一批选题)

四路取材,输出 N 个候选(默认 10):

  1. 云端爆款库:运行 automation/scripts/hot_monitor_local_job.sh read booms 读取最近 90 天最多 30 条轻量候选,先按 R/M、life 和题材筛选;对入围样本再运行 automation/scripts/hot_monitor_local_job.sh read work <云端作品ID> 读取 L1/逐字稿/指标历史。时效型且超窗(发布日距今 > life_window_days)的不推选题本身,只提取题型基因(如「月度盘点」「街采」「节令营销」)转化为当下的新选题;长青型可直接跟进
  2. 近 3 天机会:运行 automation/scripts/hot_monitor_local_job.sh read recent 3 200 0,读取云端最近 3 天的全部新作(包括未判爆作品和 YouTube);响应 has_more=true 时按 next_offset 继续读取,直到 has_more=false。需要确认账号覆盖时运行 automation/scripts/hot_monitor_local_job.sh read creators。服务器已经统一扫描抖音、小红书和 YouTube 对标号,默认不再直接调用 TikHub 重复采集
  3. 自己号数据数据统计/ 台账里自己号 R 值高的题材优先放大
  4. 定位过滤:对照 个人定位.md;偏离定位但流量潜力大的泛选题不降级(流量优先原则)
  5. 已洗对比(硬门):第 1、2 路的云端输出必须先过台账再进入筛选——命令末尾接管道 | python3 automation/scripts/wash_ledger.py filter(例:bash automation/scripts/hot_monitor_local_job.sh read booms | python3 automation/scripts/wash_ledger.py filter)。标注 washed: true 的条目保留展示但必须带「已洗 <日期> → <产出>」标记,不得当成新题推荐;washed_match.status=skipped 标「曾定不做」;washed_suspect 标「疑似已洗」。汇报候选时说明本批已洗/不做/疑似各几条

每条候选格式:选题一句话 | 证据(源爆款+R/M 或 对标新作数据)| 时效窗口 | 建议形态(实操长片/AI成片/口播/图文/文章)| 角度预判

用户选定 → 建卡:云端候选直接从过滤后的 JSON 取 platform/post_id,按平台拼标准链接写入 来源:(douyin→https://www.douyin.com/video/<post_id>,xhs→https://www.xiaohongshu.com/explore/<post_id>,youtube→https://www.youtube.com/watch?v=<post_id>),同时填 源ID:<platform>:<post_id>)→ 按形态立项;实操长片路由到 ra-实操策划。洗稿端落稿登记台账时带 --work-id <云端作品id>

云端读取失败时必须明确报告,不得退回已删除的 _爆款总库.jsonl / _账号池.md,也不得把历史 深度分析/ 冒充实时数据。

硬规则

  • 全形态隐私墙:源链接、源标题、源逐字稿只允许出现在选题卡 来源: 字段和 视频工作台/.internal/;一切成稿、交接稿、工作台条目零源信息。用户明确要求标注参考来源时除外。
  • 洗稿去重台账:台账在 视频工作台/.internal/洗稿台账.jsonl(属源隐私区),工具 automation/scripts/wash_ledger.py。选题推荐的云端读取必过 filter;任何形态立项洗稿前必 check(命中「已洗」硬停等用户确认);交接稿/成稿落地后由洗稿端 add 登记。台账内容只在会话里向用户报告,不进任何成稿。
  • 用户永远不被要求移动文件;本 skill 代劳并在回复里报告每一次移动。
  • 看板登记分工:文章完成由本端登记;视频/图文交付由制作端(Codex)登记。
  • 立项视频仍遵守两段式:默认只到待制作队列,用户说「直接制作/直接出片/一条龙」才继续制作。

Frequently asked questions

What does the Ra 选题 AI skill do?

选题全生命周期调度:记录选题、深化选题、选题推荐、立项分发(视频/图文/文章/实操长片/多形态)、发布归档。 Use when the user says 灵感xx, 想法xx, 记录选题, 这个可以做个选题, 先存着这个链接, 深化选题/深化一下xx, 给我N个选题, 帮我出选题, 选题推荐, 立项, 做成视频, 制作视频, 做成文章, 制作文章, 做成图文, 制作图文, 做成实操长片, 图文视频文章都做/都分发, 我要自己出镜讲, xx发布了, xx要改; or when the user gives a link plus a target form (链接+制作视频/文章/图文). Owns the 00-选题池 card system: one topic = one card; user never moves files — this skill does.

Why use Ra 选题 on TypingMind?

Because you install it once and use it with any model. Ra 选题 is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ra 选题 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Pluviobyte/rnskill/tree/main/skills/ra-选题. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ra 选题?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ra 选题?

As many as you like. As long as a model supports skills, you can use Ra 选题 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ra 选题 AI skill free?

It is published on GitHub by Pluviobyte. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇