← Back to Skills Marketplace
binkes

Chanjing Ai Creation

by BinKes · GitHub ↗ · v1.0.8 · MIT-0
cross-platform ✓ Security Clean
263
Downloads
0
Stars
2
Active Installs
9
Versions
Install in OpenClaw
/install chanjing-ai-creation
Description
Chanjing AI creation Open API client: submit image/video tasks, poll task status, list and get tasks, and optionally download outputs when the user runs down...
README (SKILL.md)

Chanjing AI Creation

功能说明

调用蝉镜 AI 创作 Open API:提交任务轮询状态列表与单条查询;仅在用户明确要求时用 download_result.py 可选下载输出。需读写本地 credentials.json 并访问 Open API。跨模型文生图/视频等由 submit_task.py 参数与透传体决定。本 skill 脚本依赖 ffmpeg/ffprobe。

运行依赖

  • python3 与同仓库 scripts/*.py
  • 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.yamlenvironment 段)及本文
  • 变量、凭据、合规 permissionsclientPermissionsagentPolicymanifest.yaml

使用命令

  • ClawHub(slug 以注册表为准):clawhub run chanjing-ai-creation
  • 本仓库示例python skills/chanjing-ai-creation/scripts/submit_task.py …(见正文 Standard Workflow

登记与审稿(单一事实来源)

主凭据、可选 env、下载信任边界等:manifest.yaml 为准。本篇从 When to Use 起写业务能力。

When to Use This Skill

当用户要做这些事时使用本 Skill:

  • 提交图片或视频 AI 创作任务(submit_task.py
  • 列表 / 单条查询任务(list_tasks.pyget_task.py
  • 轮询异步结果直至完成(poll_task.py
  • 仅在用户明确要求时下载输出(download_result.py

上述流程依赖读写本地 credentials.json 并调用 open-api.chanjing.cc

如果需求更接近“文生数字人”,优先使用 chanjing-text-to-digital-person
如果需求更接近“已有数字人视频合成”,优先使用 chanjing-video-compose

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)

Purpose / Credentials / Persistencedownload_result.py 信任边界相关的逐项说明见 manifest.yaml

运行时范围:本 Skill 的说明与脚本仅服务于已声明用途——读取本地 credentials.json、调用蝉镜 Open API 端点;在轮询或查询成功时自动落盘生成物,在用户显式执行 download_result.py 时下载资源。

_auth.py 与仓库布局:鉴权辅助可能打开系统浏览器,或按相对路径调用同仓库下的 chanjing-credentials-guard 脚本(例如 open_login_page.py)。这假设当前工作区为 chan-skills 式多 Skill 目录结构,或已单独安装并具备等效路径的 guard skill;否则将回退为仅打开登录页 URL。

敏感数据与持久化:预期仅处理 credentials.json 中的 app_idsecret_keyaccess_token(及与 token 生命周期相关的字段,见 manifest.yaml)。将 access_token 写入磁盘 是有意设计且已文档化,对 API 客户端而言通常可接受;但在多人共用主机全盘备份/同步到不可信存储等场景下,磁盘上的 token 会扩大泄露面,需按环境自行评估。

Standard Workflow

AI 创作的主接口是统一提交器:

  1. 调用 submit_task.py 提交图片或视频生成任务,得到 unique_id
  2. 调用 poll_task.py 轮询直到成功,得到 output_url
  3. 如需回看任务参数或错误原因,调用 get_task.py
  4. 如需看历史记录,调用 list_tasks.py
  5. 只有在用户明确要求保存到本地时,才调用 download_result.py

这个 skill 默认做成“通用任务提交器”:

  • 对常见图片/视频模型,优先使用脚本提供的通用参数
  • 对特殊模型参数,使用 --body-file--body-json 透传完整请求体

Covered APIs

本 Skill 当前覆盖:

  • POST /open/v1/ai_creation/task/submit
  • POST /open/v1/ai_creation/task/page
  • GET /open/v1/ai_creation/task

Scripts

脚本目录:

  • skills/chanjing-ai-creation/scripts/
脚本 说明
_auth.py 读写 credentials.json、获取或刷新 access_token
submit_task.py 提交 AI 创作任务,输出 unique_id
get_task.py 获取单个任务详情
list_tasks.py 列出图片或视频任务
poll_task.py 轮询任务直到完成,默认输出第一个结果地址
download_result.py 下载图片或视频到 outputs/ai-creation/

Usage Examples

示例 1:Seedream 3.0 文生图

TASK_ID=$(python3 skills/chanjing-ai-creation/scripts/submit_task.py \
  --creation-type 3 \
  --model-code "doubao-seedream-3.0-t2i" \
  --prompt "赛博朋克城市夜景,霓虹灯,雨夜,电影镜头" \
  --aspect-ratio "16:9" \
  --clarity 2048 \
  --number-of-images 1)

python3 skills/chanjing-ai-creation/scripts/poll_task.py --unique-id "$TASK_ID"

示例 2:腾讯 Kling v2.1 Master 图生视频

TASK_ID=$(python3 skills/chanjing-ai-creation/scripts/submit_task.py \
  --creation-type 4 \
  --model-code "tx_kling-v2-1-master" \
  --ref-img-url "https://res.chanjing.cc/chanjing/res/aigc_creation/photo/start.jpg" \
  --ref-img-url "https://res.chanjing.cc/chanjing/res/aigc_creation/photo/end.jpg" \
  --prompt "角色从静止到转身,镜头平滑移动,叙事感强" \
  --aspect-ratio "9:16" \
  --clarity 1080 \
  --quality-mode pro \
  --video-duration 5)

python3 skills/chanjing-ai-creation/scripts/poll_task.py --unique-id "$TASK_ID"

示例 3:直接透传完整 JSON

python3 skills/chanjing-ai-creation/scripts/submit_task.py \
  --body-file ./payload.json

Download Rule

下载是显式动作,不是默认动作:

  • poll_task.py 成功后应先返回远端 output_url
  • 不要自动下载结果文件
  • 只有当用户明确表达“下载到本地”“保存到 outputs”“帮我落盘”时,才执行 download_result.py

Output Convention

默认本地输出目录:

  • outputs/ai-creation/

Additional Resources

更多接口细节见:

  • skills/chanjing-ai-creation/reference.md
  • skills/chanjing-ai-creation/examples.md
Usage Guidance
This skill is a normal Open API client for Chanjing. Before installing, note: (1) it will read and write ~/.chanjing/credentials.json (or the directory you set via CHANJING_OPENAPI_CREDENTIALS_DIR) and persist access_token and related fields to disk — avoid using it on shared machines or where that file is backed up to untrusted storage; (2) the auth helper may open your browser or, if present in the workspace, run a local 'chanjing-credentials-guard' script — verify any local helper you trust; (3) downloads only occur when you explicitly run download_result.py, but that script can fetch arbitrary URLs you provide (ensure you trust the URL and that agent network policies are acceptable); (4) network traffic goes to open-api.chanjing.cc (and login pages at www.chanjing.cc) per the manifest. If you need higher assurance, inspect the credentials.json content and the included scripts (they are small and readable) and keep credentials.json permissions restricted (e.g., chmod 600).
Capability Analysis
Type: OpenClaw Skill Name: chanjing-ai-creation Version: 1.0.8 The chanjing-ai-creation skill bundle is a standard API client for the Chanjing AI platform, allowing users to submit, poll, and download AI-generated images and videos. It manages authentication by reading and writing credentials (app_id, secret_key, access_token) to a local file (~/.chanjing/credentials.json) and communicates exclusively with the documented endpoint open-api.chanjing.cc. The code is well-structured, lacks obfuscation, and its behaviors—including the explicit requirement for user-initiated downloads—are transparently documented in SKILL.md and manifest.yaml.
Capability Assessment
Purpose & Capability
Name and description match the shipped scripts and manifest. The scripts submit tasks, poll, list/get tasks and optionally download outputs from open-api.chanjing.cc, which is coherent with the stated purpose. No unrelated credentials or services are requested.
Instruction Scope
SKILL.md and scripts explicitly require reading/writing a local credentials.json and calling https://open-api.chanjing.cc, which is expected. The auth helper may open the browser or attempt to invoke a local 'chanjing-credentials-guard' script (via subprocess.run) if present; this is documented in SKILL.md but means the skill can execute a local helper script if the workspace contains it. Downloading results is only performed by download_result.py and is documented as an explicit user action.
Install Mechanism
There is no install spec and the skill is instruction + small Python scripts only. Nothing is downloaded or written to disk by an installer step beyond the scripts already included in the skill bundle.
Credentials
No unrelated environment variables or external credentials are requested. The manifest documents optional CHANJING_OPENAPI_CREDENTIALS_DIR and CHANJING_OPENAPI_BASE_URL. The skill persists access_token and expire_in to credentials.json by design (manifest.persistAccessTokenOnDisk: true); this is proportionate to a CLI API client but increases token exposure risk on multi-user or backed-up hosts.
Persistence & Privilege
alwaysSkill is false and the skill does not request global agent modifications. It reads/writes only its declared credentials file and may open a browser for auth; these behaviors are declared in manifest and SKILL.md.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install chanjing-ai-creation
  3. After installation, invoke the skill by name or use /chanjing-ai-creation
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.8
- Documentation rewritten for clarity and conciseness; focus is now on essential functions and workflow. - Explicitly states that local credentials.json is both read and written. - Commands and script purposes are streamlined and grouped by typical user actions. - Removes redundant and overly detailed explanations; all details about environment variables now point to manifest.yaml. - Clarifies that outputs are only downloaded when the user requests, never automatically.
v1.0.7
Version 1.0.7 - Expanded documentation in SKILL.md about authentication helper behavior, credential/token handling, and security review boundaries. - Clarified disk persistence of access_token, potential exposure scenarios, and evaluation advice for shared environments. - Added implementation notes on expected repo structure, fallback behaviors, and assumptions about skill co-location. - No runtime/code changes—documentation only.
v1.0.6
Chanjing AI Creation 1.0.6 - Added machine-readable manifest.yaml for clearer environment and credential specification. - Standardized environment variables and permissions in SKILL.md, referencing manifest.yaml as the authoritative source. - Updated SKILL.md to clarify credential, API trust boundary, and compliance details; moved legacy environment variable info to dedicated section. - No logic change to scripts; update focuses on documentation and skill spec clarity.
v1.0.5
- Added skill metadata: author, env variables, category, and tags fields. - Improved documentation by clarifying usage, runtime dependencies, and environment variables. - No change to functionality or usage commands—documentation and metadata only. - No scripts or code changes in this version.
v1.0.4
- Added Python scripts for all major API actions: download_result.py, get_task.py, list_tasks.py, poll_task.py, submit_task.py. - Updated usage, workflow, and documentation in SKILL.md and examples.md to reference new *.py script filenames. - All API interactions (submit, list, get, poll, download) now use explicit .py scripts for clarity and consistency. - No functional changes to core API coverage—improvements are in code structure, clarity, and documentation.
v1.0.3
- Documentation updated in SKILL.md: browser warning text now correctly refers to open_login_page.py instead of open_login_page. - No changes to core logic or scripts; behavior remains unchanged.
v1.0.2
- Expanded and clarified credential handling: primary credential is credentials.json (app_id/secret_key; access_token read/written here), with CHANJING_CONFIG_DIR and CHANJING_API_BASE now documented as optional. - Added a registration summary and an explicit table evaluating purpose, credential, scope, and persistence (for easier audit and compliance checks). - Documented that ffmpeg/ffprobe are not required by this skill. - Updated usage examples to reference the scripts/chanjing-ai-creation/scripts/ directory. - Download of generated assets remains explicit and only performed on user request. - Minor corrections and improved documentation structure for clarity and user guidance.
v1.0.1
- Local authentication and config process is now fully integrated—no external skill dependencies. - New scripts added: chanjing-config (manage local app_id/secret_key) and chanjing-get-token (fetch/refresh token from local credentials). - Scripts moved to the root scripts/ directory; example commands and docs updated for new paths. - Environment variable support added for config dir and API base override. - Documentation rewritten to clarify setup, workflow, script usage, and download behavior.
v1.0.0
Chanjing AI Creation Skill 1.0.0 - Initial release supporting Chanjing AI creation APIs for image and video generation. - Supports submitting generation tasks, polling async results, checking task status, and listing tasks. - Includes explicit asset download only when requested by the user. - Standard task submission and polling workflow with support for both common and custom model parameters. - Requires prior authentication via `chanjing-credentials-guard`.
Metadata
Slug chanjing-ai-creation
Version 1.0.8
License MIT-0
All-time Installs 2
Active Installs 2
Total Versions 9
Frequently Asked Questions

What is Chanjing Ai Creation?

Chanjing AI creation Open API client: submit image/video tasks, poll task status, list and get tasks, and optionally download outputs when the user runs down... It is an AI Agent Skill for Claude Code / OpenClaw, with 263 downloads so far.

How do I install Chanjing Ai Creation?

Run "/install chanjing-ai-creation" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Chanjing Ai Creation free?

Yes, Chanjing Ai Creation is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Chanjing Ai Creation support?

Chanjing Ai Creation is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Chanjing Ai Creation?

It is built and maintained by BinKes (@binkes); the current version is v1.0.8.

💬 Comments