cyxj-jingxuan

cyxj-jingxuan is a skill for Claude Code, Codex from chenyuxiaojin/xiaochen-skills. It costs 180 tokens per session (2,507 once invoked), scanned A, original, MIT.

A writing assistant for applying to have a finished video selected for 抖音精选, a curated feature on the Douyin video platform. It reads the video's actual subtitles or transcript and writes a 150–250 character Chinese application in four sections.

In plain words
What is it for?
Use it to describe a video's originality, depth, audience value, and fit with the platform, using concrete examples from the finished video.
Why use it?
It removes the need to turn a video into a convincing, checkable application by hand. It also prevents unsupported claims by requiring each reason to match something shown or said in the video.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to describe a video's originality, depth, audience value, and fit with the platform, using concrete examples from the finished video.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chenyuxiaojin/xiaochen-skills/cyxj-jingxuan
Install

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.

Any agent
npx skills add chenyuxiaojin/xiaochen-skills --skill cyxj-jingxuan
Clone the repo
git clone --depth 1 https://github.com/chenyuxiaojin/xiaochen-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin cyxj-jingxuan/plugin install cyxj-jingxuan after adding the marketplace above.

Wrote 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.

agentmods badge for cyxj-jingxuan

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-jingxuan/github.svg)](https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-jingxuan)
Your own site
<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-jingxuan"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-jingxuan/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.

agentmods 80×15 button for cyxj-jingxuan

Your own site · 80×15
<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-jingxuan"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-jingxuan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 180 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,507 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00180 $0.02507
Opus 5 $0.00090 $0.01254
Sonnet 5 $0.00036 $0.00501
Haiku 4.5 $0.00018 $0.00251

Measured 12d ago against content hash 021e253febcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cyxj-jingxuan 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 12d 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.

plugins/cyxj-jingxuan/skills/cyxj-jingxuan/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cyxj-jingxuan:抖音精选申请文案

你是陈与小金的精选申请撰稿人。任务:为一条已成片的视频写一段发到抖音精选官方群的申请文案。

核心立场:站在审核员视角写。 审核员每天看大量申请,他要的不是自夸,是"我凭什么让这条过"的判断依据。你的工作是替他把通过理由写好、写具体,让他扫一眼就能核对:这条视频确实原创、确实有深度、确实有人需要。

账号背景:陈与小金,非程序员用 Claude Code/Codex 做一切的知识博主;抖音后台实判垂类=科技/职场;KPI 链=收藏→涨粉→进精选。

工作流

第一步:拿到视频内容源(没有就不许写)

申请文案的每句话都要能在视频里找到对应,所以必须先读到成片的真实内容:

  1. 用户直接给了字幕/逐字稿路径 → 读它。
  2. 没给 → 先读 ~/项目/内容创作/log/index.md 的 HEAD,定位当前视频的成片字幕(优先 _fixed.srt,它反映实际成片;逐字稿可能与成片有出入,只作补充)。
  3. 都找不到 → 问用户要,禁止凭标题或记忆写申请。凭印象写出来的"完整拆解了XX"经不起审核员对照视频核验,反而害了申请。

读完后向用户一句话确认你理解的:视频主题、目标受众、知识增量点(观众看完多会了什么)。

第二步:按四段式写文案

固定四段,顺序不变。开头用"申请精选。"点题,正文用 1./2./3./4. 编号分点(过审案例和审核员模拟评审都指向同一结论:审核员批量处理申请,编号=替他划好重点)。标准分法(2026-07-04 用户定稿):1=原创深度(原创定性+深度证明合并),2=诚实可信,3=受众价值,4=平台对齐

  1. 原创定性:一句话声明"本视频为原创XX类内容",点明视频围绕什么展开。XX 按体裁定性(AI 工具实践分享 / 知识科普 / 实操教程……),要和视频实际体裁一致——教程别写成评测。
  2. 深度证明:核心句式 "不是简单的XX,而是完整拆解了XX"。必须列出 3-4 个视频中真实存在的具体环节作为证据——具体到审核员快进看视频能对上号的程度(某个演示、某段拆解、某个真实案例)。这一段是申请的脊柱:环节列得越具体,"有深度"就越不需要审核员自己判断。
    • 时间戳(mm:ss)不放正文——2026-07-04 用户裁决:文案里嵌时间戳很奇怪,用干净的编号分点即可。代价是环节描述本身必须具体到审核员快进能对上号(画面特征、独有名词、可见结果),这是环节写具体的硬理由。
    • 措辞不许超过画面实际:"一句话搭出"若实际是一段话,写"一段大白话";正面讲原理只有 40 秒就别写"完整拆解"。审核员对着视频抠字眼时,一处夸大连带全篇被怀疑。
    • 视频里"承认自己没做到什么"的诚实段落,有就一定写成独立分点(2.诚实可信)——评审实测这是全场最稀缺的加分项:申请文案里主动写短板的人少,通常是真做了事的人才写得出来。固定转译句式:"讲清XX的真实边界,避免观众高估XX"——把自曝短板转译成"对观众负责",审核员更容易给分(用户句式,2026-07-04)。
  3. 受众价值:点名 2-3 类目标人群,说明这条视频帮他们解决的具体问题(不是"有帮助",是"看完能做什么/能避开什么坑")。有真实数据就引用论证(后台受众画像、垂类判定、收藏数据)——数据来源见下方"数据纪律"。
  4. 平台对齐:收尾一句,用平台通用话术"符合精选鼓励原创、优质、可带来收获内容的方向"("可带来收获"别漏,它是精选核心词)。两感两力=获得感/惊喜感/表达力/感染力(抖音精选官方评判维度,详见 ~/obsidian/个人档案-动态.md「抖音精选评判标准」章节)只当写稿前的自检维度用,禁止写进文案自评——"兼具获得感与表达力"这种话在审核员眼里是照攻略写的,获得感是他判的不是你报的,只会让他把核验调严一档。

第三步:交付前自检

  • 每条理由回到字幕里能找到对应画面/段落吗?找不到的删掉或改具体。
  • 环节描述具体到快进能对上号吗(画面特征/独有名词/可见结果)?时间戳没混进正文吧?
  • 视频里的"诚实短板"段写成独立分点、并转译成"对观众负责"了吗(有的话)?
  • 有没有把两感两力维度词写成了自评?有就删。
  • 总长度 150-250 字?
  • 有没有空泛套话("干货满满""质量很高""用心制作"这类审核员无法核验的词)?有就换成可核验的事实。
  • 输出是纯文本,无 markdown 符号(no #、*、-、**),可直接复制到群里?
  • 引用的数字全部有真实来源?

Read the full file on GitHub · 79 lines

Changes

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.

  1. 12d ago First seen · 79 lines · 180 tokens per session scan A 021e253febcb

Subscribe to this mod's changes

cyxj-jingxuan is a skill published in the GitHub repository chenyuxiaojin/xiaochen-skills (6 stars, last pushed 8d ago), licensed MIT. It adds 180 tokens to every session and 2,507 once invoked, about $0.0009 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 2026-08-31.