$npx -y skills add calesthio/OpenMontage --skill heygen[DEPRECATED] Use create-video for prompt-based video generation or avatar-video for precise avatar/scene control. This legacy skill combines both workflows — the newer focused skills provide clearer guidance.
| 1 | # HeyGen API (Deprecated) |
| 2 | |
| 3 | > **This skill is deprecated.** Use the focused skills instead: |
| 4 | > - **`create-video`** — Generate videos from a text prompt (Video Agent API) |
| 5 | > - **`avatar-video`** — Build videos with specific avatars, voices, scripts, and scenes (v2 API) |
| 6 | |
| 7 | This skill remains for backward compatibility but will be removed in a future release. |
| 8 | |
| 9 | --- |
| 10 | |
| 11 | AI avatar video creation API for generating talking-head videos, explainers, and presentations. |
| 12 | |
| 13 | ## Tool Selection |
| 14 | |
| 15 | If HeyGen MCP tools are available (`mcp__heygen__*`), **prefer them** over direct HTTP API calls — they handle authentication and request formatting automatically. |
| 16 | |
| 17 | | Task | MCP Tool | Fallback (Direct API) | |
| 18 | |------|----------|----------------------| |
| 19 | | Generate video from prompt | `mcp__heygen__generate_video_agent` | `POST /v1/video_agent/generate` | |
| 20 | | Check video status / get URL | `mcp__heygen__get_video` | `GET /v2/videos/{video_id}` | |
| 21 | | List account videos | `mcp__heygen__list_videos` | `GET /v2/videos` | |
| 22 | | Delete a video | `mcp__heygen__delete_video` | `DELETE /v2/videos/{video_id}` | |
| 23 | |
| 24 | If no HeyGen MCP tools are available, use direct HTTP API calls with `X-Api-Key: $HEYGEN_API_KEY` header as documented in the reference files. |
| 25 | |
| 26 | ## Default Workflow |
| 27 | |
| 28 | **Prefer Video Agent** for most video requests. |
| 29 | Always use [prompt-optimizer.md](references/prompt-optimizer.md) guidelines to structure prompts with scenes, timing, and visual styles. |
| 30 | |
| 31 | **With MCP tools:** |
| 32 | 1. Write an optimized prompt using [prompt-optimizer.md](references/prompt-optimizer.md) → [visual-styles.md](references/visual-styles.md) |
| 33 | 2. Call `mcp__heygen__generate_video_agent` with prompt and config (duration_sec, orientation, avatar_id) |
| 34 | 3. Call `mcp__heygen__get_video` with the returned video_id to poll status and get the download URL |
| 35 | |
| 36 | **Without MCP tools (direct API):** |
| 37 | 1. Write an optimized prompt using [prompt-optimizer.md](references/prompt-optimizer.md) → [visual-styles.md](references/visual-styles.md) |
| 38 | 2. `POST /v1/video_agent/generate` — see [video-agent.md](references/video-agent.md) |
| 39 | 3. `GET /v2/videos/<id>` — see [video-status.md](references/video-status.md) |
| 40 | |
| 41 | Only use v2/video/generate when user explicitly needs: |
| 42 | - Exact script without AI modification |
| 43 | - Specific voice_id selection |
| 44 | - Different avatars/backgrounds per scene |
| 45 | - Precise per-scene timing control |
| 46 | - Programmatic/batch generation with exact specs |
| 47 | |
| 48 | ## Quick Reference |
| 49 | |
| 50 | | Task | MCP Tool | Read | |
| 51 | |------|----------|------| |
| 52 | | Generate video from prompt (easy) | `mcp__heygen__generate_video_agent` | [prompt-optimizer.md](references/prompt-optimizer.md) → [visual-styles.md](references/visual-styles.md) → [video-agent.md](references/video-agent.md) | |
| 53 | | Generate video with precise control | — | [video-generation.md](references/video-generation.md), [avatars.md](references/avatars.md), [voices.md](references/voices.md) | |
| 54 | | Check video status / get download URL | `mcp__heygen__get_video` | [video-status.md](references/video-status.md) | |
| 55 | | Add captions or text overlays | — | [captions.md](references/captions.md), [text-overlays.md](references/text-overlays.md) | |
| 56 | | Transparent video for compositing | — | [video-generation.md](references/video-generation.md) (WebM section) | |
| 57 | | Use with Remotion | — | [remotion-integration.md](references/remotion-integration.md) | |
| 58 | |
| 59 | ## Reference Files |
| 60 | |
| 61 | ### Foundation |
| 62 | - [references/authentication.md](references/authentication.md) - API key setup and X-Api-Key header |
| 63 | - [references/quota.md](references/quota.md) - Credit system and usage limits |
| 64 | - [references/video-status.md](references/video-status.md) - Polling patterns and download URLs |
| 65 | - [references/assets.md](references/assets.md) - Uploading images, videos, audio |
| 66 | |
| 67 | ### Core Video Creation |
| 68 | - [references/avatars.md](references/avatars.md) - Listing avatars, styles, avatar_id selection |
| 69 | - [references/voices.md](references/voices.md) - Listing voices, locales, speed/pitch |
| 70 | - [references/scripts.md](references/scripts.md) - Writing scripts, pauses, pacing |
| 71 | - [references/video-generation.md](references/video-generation.md) - POST /v2/video/generate and multi-scene videos |
| 72 | - [references/video-agent.md](references/video-agent.md) - One-shot prompt video generation |
| 73 | - [references/prompt-optimizer.md](references/prompt-optimizer.md) - Writing effective Video Agent prompts (core workflow + rules) |
| 74 | - [references/visual-styles.md](references/visual-styles.md) - 20 named visual styles with full specs |
| 75 | - [references/prompt-examples.md](references/prompt-examples.md) - Full production prompt example + ready-to-use templates |
| 76 | - |