用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/HybridAIOne/hybridclaw --skill video-from-script命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Read, send, react to, edit, pin, and thread Discord messages with HybridClaw's `message` tool.
Work with Lexware Office contacts, products, invoices, quotations, bookkeeping vouchers, receipts, payment status, and guarded invoice, quotation, or expense writes through the Public API.
Expose HybridClaw as a custom Alexa skill and prepare guarded Alexa smart-home/device control payloads without exposing Amazon credentials.
基于 SOC 职业分类
正在显示 SKILL.md
| name | video.from-script |
| description | Render approved avatar + voice + script briefs into HeyGen MP4 videos with async job polling. |
| user-invocable | true |
| requires | {"bins":["node"]} |
| credentials | [{"id":"heygen-api-key","kind":"api_key","required":true,"secret_ref":{"source":"store","id":"HEYGEN_API_KEY"},"scope":"HeyGen Direct API avatar video generation.","how_to_obtain":"Create or regenerate the API token from HeyGen account settings. Set `HEYGEN_API_KEY` through browser admin at the active `/admin/secrets` route; if browser admin is unavailable, use `/secret set HEYGEN_API_KEY \"<api-key>\"` in browser `/chat` or TUI; local console fallback: `hybridclaw secret set HEYGEN_API_KEY \"<api-key>\"`."}] |
| metadata | {"hybridclaw":{"category":"media","short_description":"Async HeyGen avatar videos from script text.","tags":["video","avatar-video","heygen","from-script","mp4"],"related_roadmap":["R55","R55.2"],"issue":875,"depends_on":["R55.1","heygen"],"stakes_tiers":{"green":"[Truncated]","amber":"[Truncated]","red":"[Truncated]"},"escalation":{"writes":"confirm-each","route":"f8"},"cost_measurement":{"system":"UsageTotals","sub_limit_contract":"R5.4","sub_limit_key":"heygen"}}} |
Use this skill when the user wants an avatar video from three concrete inputs:
an avatar or image source, a voice id, and approved script text. The backing
provider is HeyGen Direct API via the bundled heygen adapter.
completed, failed, or still rendering.generated-videosTemplate videos, free-form prompt-to-video, public publishing, social posting,
and custom avatar training are outside this skill. Use video-generation for
native Sora/Veo prompt videos and heygen for lower-level HeyGen API work.
Polling is the completion transport implemented for R55.2; webhook callbacks
belong in a provider/gateway adapter if that transport is added later.
/brand-voice before starting a credit-consuming render.plan if the request is vague or needs an explicit risk summary.start after the operator grants the exact credit-consuming render.
Return the jobId to the user because HeyGen renders asynchronously.status --job-id <id> to poll conservatively. Add --download only
after the status is complete or when the user asks you to fetch the MP4.render --wait only when the user explicitly wants the agent to wait
for the final MP4 in the same run.Do not run parallel render bursts. HeyGen quotas are tight and account/plan dependent.
Run the helper with Node:
node skills/video.from-script/video-from-script.cjs --help
In packaged agent workspaces this skill can be mounted with a hyphenated
directory name. If the command above fails with Cannot find module, run:
node skills/video-from-script/video-from-script.cjs --help
Plan without contacting HeyGen:
node skills/video.from-script/video-from-script.cjs plan "Create a product update avatar video"
Start an async render after explicit operator grant:
node skills/video.from-script/video-from-script.cjs start \
--avatar-id avatar_123 \
--voice-id voice_123 \
--script "Approved script text" \
--title "Product update" \
--resolution 1080p \
--aspect-ratio 16:9 \
--operator-grant
Poll and download the completed MP4:
node skills/video.from-script/video-from-script.cjs status \
--job-id video_123 \
--download
Wait for completion in one command only when that behavior is requested:
node skills/video.from-script/video-from-script.cjs render --wait \
--avatar-id avatar_123 \
--voice-id voice_123 \
--script "Approved script text" \
--operator-grant
--avatar-id and --voice-id. Display names
such as a presenter name or voice name are not ids.node skills/heygen/heygen.cjs request list-avatars --limit <count> and node skills/heygen/heygen.cjs request list-voices --limit <count> before choosing ids. Those summaries are cached so this
helper can reject display names and stale ids before contacting HeyGen.--skip-cache-validation only when the operator supplied a known private
HeyGen asset id that is not present in the cached list.--avatar-id, --image-url, or
--image-asset-id.--operator-grant for start and render.start + status over a long blocking render.pending, waiting, and processing as normal async states.failed as terminal and include the provider error when available..generated-videos.artifacts[] output so the gateway can render the browser preview/download
route. When asked to post or show an already completed video, run
status --job-id <id> --download again instead of writing a remembered local
path or hand-built /api/artifact link.Run:
python3 skills/skill-creator/scripts/quick_validate.py skills/video.from-script
node skills/video.from-script/video-from-script.cjs --help
node skills/video.from-script/video-from-script.cjs eval-scenarios