chanjing-video-compose SKILL.md skillA
chanjing-video-compose from chanjing-ai/chan-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add chanjing-ai/chan-skills/chanjing-video-compose@git:20260327.fce5536Pins git:20260327.fce5536 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- chanjing-ai/chan-skills
- Path
skills/chanjing-video-compose/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260327.fce5536, committed Mar 27, 2026
- First version recorded
- Mar 19, 2026
- Size
- 9,587 bytes
- Repository stars
- 22
- License
- none declared
Use Chanjing video synthesis APIs to create digital human videos from text or audio, with optional background upload, polling, and explicit download.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Chanjing Video Compose ## 功能说明 调用蝉镜**视频合成** Open API：列举公共/定制形象、上传素材、文本或音频驱动数字人、轮询任务；用户明确要求时用脚本下载成片。本 skill 脚本**不**依赖 ffmpeg/ffprobe（与一键成片编排不同）。凭据与权限边界见同目录 **`manifest.yaml`**。 ## 运行依赖 - **python3** 与同仓库 `scripts/*.py` - **无** ffmpeg/ffprobe 门控 ## 环境变量与机器可读声明 - 环境变量键名与说明：**`manifest.yaml`**（`environment` 段）及本文 - 变量、凭据模型、合规 **`permissions`**、**`clientPermissions`、`agentPolicy`**：**`manifest.yaml`** ## 使用命令 - **ClawHub**（slug 以注册表为准）：`clawhub run chanjing-video-compose` - **本仓库**：`python skills/chanjing-video-compose/scripts/create_task.py …`（见 **Standard Workflow**） --- ## 登记与审稿（单一事实来源） 凭据、`primaryEnv` 省略、可选 env、无 ffmpeg 门控（本 skill 独立使用场景）等：**以 `manifest.yaml` 为准**。本篇从 **When to Use** 起写流程与 API 说明。 ## When to Use This Skill 当用户要做这些事时使用本 Skill： * 创建数字人视频合成任务 * 用文本驱动数字人出镜 * 用本地音频驱动数字人视频 * 查询公共数字人或定制数字人形象 * 轮询视频合成结果 * 在用户明确要求时下载最终视频到本地 如果需求更接近“上传一段真人视频做对口型驱动”，优先使用 `chanjing-avatar`，不要混用。 ## Preconditions 执行本 Skill 前，必须先通过 `chanjing-credentials-guard` 完成 AK/SK 与 Token 校验。 本 Skill 与 guard 共用： * `~/.chanjing/credentials.json` * `https://open-api.chanjing.cc` 无凭证时，脚本会自动打开蝉镜登录页，并提示配置命令。 ### 审阅与安全（凭据与边界） …
Read the whole file at its exact version.
How to install
mdr add chanjing-ai/chan-skills/chanjing-video-compose@sha256:fabda7bb5dffcbcaThe line at the top of this page pins the label git:20260327.fce5536, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_kzkad2ia3xtmj2xf)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Mar 19, 2026 and Mar 27, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260327.fce5536 latest | 2026-03-27 | fce5536 | 9,587 B | A | view · diff |
| git:20260324.4d81838 | 2026-03-24 | 4d81838 | 7,556 B | A | view · diff |
| git:20260324.1f62de4 | 2026-03-24 | 1f62de4 | 7,547 B | A | view · diff |
| git:20260319.e2196da | 2026-03-19 | e2196da | 6,613 B | A | view · diff |
| git:20260319.e5172e8 | 2026-03-19 | e5172e8 | 4,777 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9587 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
chanjing-ai/chan-skills · 22 stars · license none declared · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_kzkad2ia3xtmj2xf GET https://markdownregistry.com/api/v1/resolve?ref=chanjing-ai/chan-skills/chanjing-video-compose GET https://markdownregistry.com/api/v1/blob/fabda7bb5dffcbca1d7641b3f6e661c04c85f0cc6ed4950440698bbbd721373f
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.