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.
npx skills add chenyuxiaojin/xiaochen-skills --skill cyxj-jingxuangit clone --depth 1 https://github.com/chenyuxiaojin/xiaochen-skillsWrote 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.
[](https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-jingxuan)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- 用户直接给了字幕/逐字稿路径 → 读它。
- 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)。 - 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:
- 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。
- 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)。
- 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"。
- 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?
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.
- 12d ago First seen · 79 lines · 180 tokens per session scan A 021e253febcb
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.
Other skills, from other repositories
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.
document
Generate minimal documentation through parallel agents.
grill-me
Internal requirements-interview engine for the CCF commands plan and init. Invoked only by those commands through the Skill tool with a mode argument (plan / init); it interrogates the user one question at a time, exploring the code to self-answer first, and returns a summary of the decisions. Not a standalone…
prd-gen
A guide for turning a feature idea into a product requirements document (PRD), a structured plan that explains what to build and how success will be judged.
full-pm-cycle
A product-management workflow covering the path from market and user research through product strategy, requirements, prototype design, release planning, and post-launch review. It uses defined stages and checkpoints, and can produce HTML prototypes.
market-research
A research skill for understanding markets and users. It can study market trends, market size, competitors, and opportunities, or help design interviews, surveys, and user profiles.