Chinese Social Media Cover Maker

What it does

When your agent uses it

• Making a cover in the registered house style for a Chinese video or post
• Producing matching vertical and horizontal covers in one run
• Replacing the person on a reference cover with your digital-human frame

Example prompts

• “Use skill-cover for a cover whose main title is New Open Model, Fully Tested, in both 3:4 and 4:3.”
• “Take this reference cover and replace the person with a frame from my avatar master.”
• “Make only a 4:3 cover in the registered style with the open palm gesture.”

Requirements

• An image generation capability the agent can call once per ratio
• Python 3 for the prompt, validation and frame-extraction scripts
• A presenter or avatar video, only for reference-cover mode

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1读取 references/style-registry.json。
2. 2将用户说出的风格名称与 display_name、slug 和 aliases 匹配。
3. 3用户未指定风格时使用 default_style。如果参考图明显要求另一种已注册风格，则优先尊重参考图。
4. 4读取注册项的 reference_doc，只加载所选风格的详细视觉合同。
5. 5读取 assets/shared/gestures/registry.json 和对应动作的 manifest.json；风格只用 default_gesture 与 allowed_gestures 引用动作，不重复保存动作定义。
6. 6未注册的新风格或动作不得假装已存在；分别按“新增风格”和“新增动作”流程建立资产包。

What it can do on your machine

Read from SKILL.md and the folder at commit 83d1783. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/, which the agent can run.

  Shell commands in SKILL.md call:

  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Chinese Social Media Cover Maker loads about 1.2k tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 144 tokens; SKILL.md has 226 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~144

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 226 words (~1,201 tokens).

name

skill-cover

Read the full SKILL.md on GitHub

Files

SKILL.md and 23 other files (scripts, references, assets) in skills/skill-cover of Pluviobyte/rnskill.

• SKILL.md
• agents/openai.yaml
• assets/shared/avatar/black-t-identity.png
• assets/shared/gestures/registry.json
• assets/shared/gestures/tanshou/manifest.json
• assets/shared/gestures/tanshou/reference.png
• assets/shared/gestures/zhengzuo/manifest.json
• assets/shared/gestures/zhengzuo/reference-3x4.png
• assets/shared/gestures/zhengzuo/reference-4x3.png
• assets/shared/gestures/zhengzuo/reference.png
• assets/styles/shizhan/base/base-clean-3x4.png
• … and 13 more

Open the folder on GitHubat commit 83d1783