cyxj-video-cover

cyxj-video-cover is a skill for Claude Code from chenyuxiaojin/xiaochen-skills. It costs 131 tokens per session (769 once invoked), scanned A, original, MIT.

A generator for making 16:9 video-cover background scenes without text, letters, numbers, logos, or watermarks.

In plain words
What is it for?
Use it to create a person or scene background for a video cover, especially when a user-supplied face photo should guide the image.
Why use it?
It avoids relying on image generators to render accurate cover text, leaving that job to a separate HTML cover workspace.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cyxj-image-studio plugin — 2 skills shipped together

Good fit Use it to create a person or scene background for a video cover, especially when a user-supplied face photo should guide the image.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chenyuxiaojin/xiaochen-skills/cyxj-video-cover
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-video-cover
Clone the repo
git clone --depth 1 https://github.com/chenyuxiaojin/xiaochen-skills

Made for: Claude Code.

Or install cyxj-image-studio, the plugin that ships this one along with the rest of its 2 skills.

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-video-cover

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-video-cover"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-video-cover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 769 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 $0.00131 $0.00769
Opus 5 $0.00066 $0.00385
Sonnet 5 $0.00026 $0.00154
Haiku 4.5 $0.00013 $0.00077

Measured 12d ago against content hash 32a76a9b2cfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cyxj-video-cover 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-image-studio/skills/cyxj-video-cover/SKILL.md · 45 lines

What it actually says

cyxj-video-cover:无字底图生成引擎(已降级)

2026-07-26 降级定稿(裁决记录见 内容创作/log):旧「生图直接渲染中文标题」工作流作废—— 中文文字永远不要交给生图模型渲染,文字由浏览器渲染(cyxj-release-kit 的 cover-studio.html), 底图才交给生图。本 skill 只剩一件事:出无字底图

唯一入口:generate.py

python3 <本目录>/scripts/generate.py \
  --title "占位" \                  # 仍需传参但别指望它排字;场景里必须禁字(见下)
  --label "<项目名>-底图" \
  --ratios "16:9" \
  --face ~/Pictures/封面形象/<用户指定的原图> \
  --scene "<场景描述>。画面中完全不出现任何文字、字母、数字、标志、水印;右侧大面积留白给排版"

硬规矩:

  1. 人脸参考必须由用户指定原图(--face 显式传),严禁默认取目录第一张、严禁拿生成图回喂(会越来越不像)。
  2. 场景提示词必须带禁字条款(上面那句),出图后人工检查画面无任何文字残留。
  3. 底图只出 16:9 一张;分比例适配、标题渲染、JPG 转换全部在 cyxj-release-kit 里做。
  4. 输出仍落 ~/Pictures/封面出图/<日期>-<label>/

技术事实(engine 层,维护时看)

  • 引擎:gpt-image-2-vip @ GPTIMG2 中转 api.chatgpt-code.com(OpenAI 兼容,{base}/v1/images/edits, 真人照片做参考图重绘保脸;response_format=url,脚本下载落地 PNG)
  • 密钥:密钥存储/.envGPTIMG2_BASE_URL(末尾无 /v1)+ GPTIMG2_API_KEY,脚本自动读
  • 引擎实测对照与 Gemini 实验路径:references/engines.md
  • 依赖:Python 3.11+ 标准库;可选 Pillow(自动中心裁切)

历史

旧版完整工作流(整图带字、4 比例×2、风格预设、psjpg 交付)已删,如需考古看本仓 git 历史 (2026-07-26 之前的版本);网页生成模板 web-prompts.md 同日删除。

Files

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.

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 · 45 lines · 131 tokens per session scan A 32a76a9b2cfc

Subscribe to this mod's changes

cyxj-video-cover is a skill published in the GitHub repository chenyuxiaojin/xiaochen-skills (6 stars, last pushed 8d ago), licensed MIT. It adds 131 tokens to every session and 769 once invoked, about $0.0007 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.