Chenyu Aigc

Generate AI videos and images via Chenyu Studio AIGC API. Supports text-to-video, image-to-video, video extension, style transfer, and AI image generation. T...

Security Scan

The skill's requirements and runtime instructions are consistent with a CLI-based wrapper for an external AIGC API and do not request unrelated credentials or install code on disk.

Purpose & Capability

Name/description (AI video/image generation) match the declared env vars (CHENYU_API_KEY, CHENYU_BASE_URL) and required binaries (curl, jq, uuidgen, base64). All requested items are reasonable for an instruction-only curl-based integration.

Instruction Scope

SKILL.md and auxiliary docs only instruct making HTTP requests to the declared CHENYU_BASE_URL, polling task status, and optionally encoding local image files as base64 and writing a temporary payload file. There is no instruction to read unrelated files, environment secrets, or to exfiltrate data to unexpected endpoints beyond the configured base URL.

Install Mechanism

No install spec or code is present (instruction-only), so nothing is downloaded or written by an installer. This is the lowest-risk pattern for skills.

Credentials

Only two env vars are required: CHENYU_API_KEY (primary) and CHENYU_BASE_URL. Both are necessary and proportional for an API integration. No unrelated credentials or secrets are requested.

Persistence & Privilege

always is false and the skill does not request permanent or elevated presence, nor does it modify other skills or global agent configuration.

Assessment

This skill appears to be a straightforward CLI-based integration with the Chenyu AIGC API. Before installing, verify the CHENYU_BASE_URL you intend to use (the docs default to https://chenyu.pro) and confirm you trust that service and its terms/privacy for uploading images/videos. The skill explicitly instructs encoding local image files and writing a temporary payload (e.g., /tmp/payload.json) — be careful not to point it at sensitive files. Limit the API key's permissions if possible and rotate the key if you stop using the skill. Finally, ensure the required binaries (curl, jq, uuidgen, base64) are available and that outbound network access to the CHENYU_BASE_URL is permitted by your environment.

Chenyu AIGC - AI Video & Image Generation

Generate videos and images using AI models through the Chenyu Studio AIGC orchestration API.

When to Use

• User wants to generate a video from text prompt
• User wants to generate a video from an image (first/last frame)
• User wants to extend or remix a video
• User wants to generate AI images
• User wants to check status of a generation task
• User wants to list available AI models

When NOT to Use

• User wants to analyze or understand existing videos (use video-analysis skill)
• User wants to download videos from social platforms (use video-fetch skill)
• User wants to manage digital humans or clone voices (use chenyu-core skill)

Authentication

Authorization: Bearer $CHENYU_API_KEY

Base URL: $CHENYU_BASE_URL (default: https://chenyu.pro)

Workflow

1. Discover recipes — list available AI models (see below)
2. Get recipe schema — check what inputs/parameters the recipe accepts
3. Execute — submit a generation task → see execute-recipe.md
4. Poll & manage — track status, get output, cancel → see manage-tasks.md

Step 1: List Available Recipes

curl -s "$CHENYU_BASE_URL/api/v1/aigc/recipes" \
  -H "Authorization: Bearer $CHENYU_API_KEY" | jq '.data[] | {recipe_id, name, slug, description, output_type}'

Each recipe represents an AI model capability. Key response fields:

• recipe_id — use this ID when executing
• slug — human-readable identifier (e.g. volcengine-seedance-v1-pro)
• output_type — what it produces: video, image, audio

Step 2: Get Recipe Schema

curl -s "$CHENYU_BASE_URL/api/v1/aigc/recipes/{recipe_id}/schema" \
  -H "Authorization: Bearer $CHENYU_API_KEY" | jq '.data'

The schema tells you:

• typed_inputs_schema.definitions — accepted input types and their fields
• parameters_schema — available parameters with constraints (min/max/enum)
• credit_cost / credit_cost_rules — how many credits it costs

After getting the schema, read execute-recipe.md for execution details.