Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-release-kit)<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-release-kit"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-release-kit/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-release-kit"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-release-kit.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 | $0.00235 | $0.03447 |
| Opus 5 | $0.00118 | $0.01724 |
| Sonnet 5 | $0.00047 | $0.00689 |
| Haiku 4.5 | $0.00023 | $0.00345 |
Grade A, and why
cyxj-release-kit scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 自写脚本 403 `error code: 1010` | **Cloudflare 拦 `Python-urllib` 的 UA** | 请求和下图都要带浏览器 UA;`generate.py` 已内置 | How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cyxj-release-kit:视频发布物料一条龙
成片定稿 → 标题(6 平台)→ 简介(6 平台)→ 封面(4:3 首选,另含 16:9 / 3:4)→ 上传 JPG。 本 skill 把 2026-07-05 loop 视频那次全流程实战固化下来,核心教训只有一条: 中文文字永远不要交给生图模型渲染——模型不认精确比例、脚本会中心裁切,文字进画面必掉字; 文字由浏览器渲染,底图才交给生图/实拍。
前置
- 读
内容创作/log/index.mdHEAD,拿到:成片位置、最终导出字幕(SRT)位置、视频主题。 - 确认视频标题已定稿。没定稿就先出候选(规则见下),用户拍板后再走后面模块。
- 所有事实(数字、时间戳、功能点)只从最终字幕/成片里来,数据不编(同 cyxj-jingxuan 的红线)。
模块一:标题(6 平台)
先读 ${CLAUDE_PLUGIN_ROOT}/skills/cyxj-release-kit/references/platform-specs.md(各平台字数上限 + 自家高播放样本,必读)。
标题只做一件事:对观众正在用 / 正在选的东西,给一个具体判决。 形式就是"X 实测:发生了什么,数字多少"。 用户拍板的标准样本(2026-09-04):「Agent Teams 实测:3 个 AI 互相证伪排 bug,Token 贵 4 倍」—— 东西名 + 体裁词 + 一个具体事件 + 一个数字判决,平铺直叙像新闻导语,第三人称陈述句。
流程:
- 先摘利害句:从最终字幕 / 成片里摘 3-5 条——具体数字(倍数 / 刀 / 分钟 / 百分比)、判决(不如 / 贵 / 降智 / 删掉 / 别用)、 观众身上正在发生的痛。摘不出来就如实回报用户"这期没有可卖的判决",等用户定方向。
- 拼标题:主语(工具 / 功能名,观众认识的东西)+ 体裁词(实测 / 对比 / 拆解 / 翻车)+ 事件 + 数字判决。冒号 / 逗号分隔。
- 每平台 3 条候选,各卖一条不同的利害句;每条附「前 15 字截断预览」;标一条推荐并说一句为什么。 用户拍板;拿不准的上 YouTube 后台「标题测试」让数据选,不靠猜。
- 自检(逐条过):≤字数上限?有具体数字?主语是观众认识的东西?体裁词 = 真实体裁?是陈述句?
硬上限(交付前数一遍):YouTube ≤25 字 / B 站 ≤25 字 / 抖音首行 ≤20 字 / 视频号 ≤25 字 / 小红书 ≤20 字 / TikTok 英文 ≤50 字符。
写法要求(只说要怎么写):
- 主语是观众正在用的工具 / 功能名,只写一次,英文名直接用
- 一条标题一个判决,判决里带一个具体数字(倍数 / 百分比 / 刀 / 天)
- 陈述句,第三人称,冒号或逗号分隔,像新闻导语
- 体裁词 = 片子的真实体裁(实测 / 对比 / 拆解 / 教程),标题里的每个事实都能在片中找到
- 三平台卖同一个判决,各平台只调字数和关键词位置
模块二:简介(6 平台)
规格逐平台见 platform-specs.md。要点:
- YouTube 简介带章节时间戳,第一条必须
00:00,每个时间戳都要回字幕核对,禁止估。 - 标题+简介成对交付,一次给全 6 个平台,别挤牙膏。
模块三:封面(HTML 封面工作台)
3.1 底图(一期一张,无字)
底图 = 16:9 无文字场景图,来源二选一:
-
生图:调 cyxj-image-studio 的
generate.py,必须显式指定风格:S=~/.claude/plugins/.../cyxj-video-cover/scripts/generate.py # 真人底图(人在左、右半边留白): python3 $S --title "本期标识" --style plate --ratios 16:9 --n 3 \ --face ~/Pictures/封面形象/<用户指定的原图> --label "<项目>-底图" # 无人底图(不喂脸,走文生图端点): python3 $S --title "本期标识" --style plate-noface --ratios 16:9 --n 3 --label "<项目>-底图"--style不给就是 default,那会把中文标题渲进画面,出来是带字整图,不能当底图。 plate / plate-noface 的 prompt 完全不含 title,并且写死了「无任何文字/字母/数字/logo/水印」- 「右半边整片空墙留给排版」。
--title在这两个风格里只是批次标识,不进画面。
- 「右半边整片空墙留给排版」。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed · +15 lines 431ec1733635
- 8d ago Changed · +35 lines · +7 tokens per session 856e83b72854
- 12d ago First seen · 109 lines · 228 tokens per session scan A 822e7022417d
cyxj-release-kit is a skill published in the GitHub repository chenyuxiaojin/xiaochen-skills (6 stars, last pushed 8d ago), licensed MIT. It adds 235 tokens to every session and 3,447 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.