본문으로 건너뛰기
cccskills
무료GitHub에 공개

byted-byteplus-vod-precision-erasure

Upload video/audio media to BytePlus VOD (Video on Demand) storage, returning the Vid and playback references; supports local file upload (ApplyUploadInfo + TOS + CommitUploadInfo) and URL pull upload (UploadMediaByUrl); also submits precision erasure jobs on ingested media (StartExecution / Operation.Task.Erase): Auto OCR only — default subtitle-only erasure, optional full on-screen text, optional EraseOption ClipFilter (skip/selected); NewVid is always true; optional WithEraseInfo. Trigger keywords: precision erasure, precise erase, VOD upload, subtitle removal, OCR subtitles, remove on-screen text, erase text, StartExecution Erase.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(10)

  • SKILL.md10.2 KB
  • LICENSE9.9 KB
  • references/precise_erase.md2.5 KB
  • scripts/.env.example219 B
  • scripts/poll_execution.py1.3 KB
  • scripts/precise_erase.py11.0 KB
  • scripts/pyproject.toml259 B
  • scripts/tos_upload.py13.5 KB
  • scripts/upload.py12.3 KB
  • scripts/vod_client.py23.3 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

VOD precision erasure

Uploads video/audio to a BytePlus VOD space (from a local file or a public URL) and returns a vid://… reference. For media already in VOD, submits precision erasure tasks (StartExecution → Operation.Task.Type: Erase) using automatic OCR only. Do not tell end users they can change erasure mode between Manual and Auto — this skill always sends Auto. NewVid is always true (not surfaced as a user choice).


Product scope

AspectBehaviour
InputVid or DirectUrl (JSON field video)
Erasure coverageDefault subtitle only (Auto.Type: Subtitle, SubtitleFilter: {}). User may opt into all detected on-screen text via text: true or all_text: true → Auto.Type: Text.
TimelineDefault: whole video (no ClipFilter). Optional clip_filter with mode skip or selected — when either is used, clips is mandatory (non-empty).
Output assetNewVid is always true — not configurable and not prompted.
Erasure metadataDefault with_erase_info: true (WithEraseInfo). If false, stdout EraseMeta is {}; VideoUrls are still populated when Erase.File is returned.

Not supported: Manual mode, custom ratio Locations, tuning SubtitleFilter beyond {}, VideoOption.EncodeMode, overriding NewVid.

Precision erasure allowlist: if you see HTTP 403 or “Permission denied”, explain allowlist / work order per BytePlus VOD.


Prerequisites

  • Environment variables (required; optionally place a .env in the working directory — scripts load it automatically):
    • BYTEPLUS_ACCESSKEY — BytePlus Access Key
    • BYTEPLUS_SECRETKEY — BytePlus Secret Key
    • VOD_SPACE_NAME — VOD space name
  • Execution: examples use uv run python … (python scripts/… works if deps are installed).

Workflow overview

Upload pipeline (local file):
  [S1_APPLY]  ApplyUploadInfo → TOS upload address + SessionKey
  [S2_TOS]    PUT file to TOS (direct or chunked)
  [S3_COMMIT] CommitUploadInfo → Vid
  Output: { Vid, Source, PlayURL, FileName, SpaceName, SourceUrl }

Upload pipeline (URL):
  [S1_UPLOAD] Submit URL upload job (UploadMediaByUrl) → JobId
  [S2_POLL]   Poll QueryUploadTaskInfo → Vid
  Output: { Vid, Source, PlayURL, FileName, SpaceName, SourceUrl, JobId }

Precision erasure pipeline:
  [S3_ERASE]  Submit Erase task (StartExecution / Task.Type Erase) → RunId
  [S4_POLL]   Poll GetExecution → output Erase.File (+ optional Erase.Info)
  Output: { Status, SpaceName, VideoUrls[{ FileId, Vid, DirectUrl, Source, Url }], EraseMeta? }

Quick Self-Check (recommended)

Before running any script:

  • .env or env vars contain BYTEPLUS_ACCESSKEY, BYTEPLUS_SECRETKEY, and VOD_SPACE_NAME.

Pick the pipeline from user intent:

User intentPipelineEntry script
Upload video to VODUploadscripts/upload.py
Subtitle / on-screen text erasurePrecision erasurescripts/precise_erase.py

S1_UPLOAD & S2_POLL: Upload and Obtain Vid

Calling convention

Run from the Skill root directory (byted-byteplus-vod-precision-erasure/):

# Local file upload (returns Vid when complete)
uv run python scripts/upload.py "/path/to/video.mp4" [space_name]

# URL upload (polls until Vid is returned)
uv run python scripts/upload.py "https://example.com/video.mp4" [space_name]

uv run python scripts/upload.py "https://example.com/sample.mp4" my_space
  • First argument: local file path or public http:// / https:// URL (auto-detected).
  • Second argument (optional): space name; if omitted, VOD_SPACE_NAME is used.
  • Paths and URLs must include a file extension (e.g. .mp4, .mov, .mp3).

Upload flow

Local file (synchronous, three-step):

  1. ApplyUploadInfo (API version 2023-01-01) → TOS address, SessionKey
  2. PUT to TOS (direct < 20 MiB, else chunked)
  3. CommitUploadInfo (2023-01-01) → Vid

URL pull (async + poll):

  1. UploadMediaByUrl (2023-01-01) → JobId
  2. Poll QueryUploadTaskInfo until done (same limits as sibling skill: typically 360 × 5 s)
  3. Return Vid

Output format

On success, one JSON object on stdout, e.g.:

{
  "Vid": "v0d123abc",
  "Source": "vid://v0d123abc",
  "PlayURL": "https://example.cdn.com/xxx.m3u8",
  "PosterUri": "",
  "FileName": "uuid-filename.mp4",
  "SpaceName": "my_space",
  "SourceUrl": "https://example.com/video.mp4",
  "JobId": "job-xxx"
}
  • Preserve Source (vid://…) for downstream skills.

Timeout handling (URL upload)

If URL polling exhausts retries, stderr / JSON includes something like:

{
  "error": "Polling timed out (360 attempts × 5s); the URL pull upload is still processing",
  "resume_hint": {
    "description": "The URL upload has not finished yet; retry with the command below",
    "command": "uv run python scripts/upload.py \"<original URL>\" [space_name]"
  },
  "JobIds": "job-xxx",
  "State": "running"
}

S3_ERASE & S4_POLL: precision erasure

Calling convention

Run from the Skill root directory (byted-byteplus-vod-precision-erasure/):

# Default: subtitle-only, whole video, WithEraseInfo on
uv run python scripts/precise_erase.py '{"type":"Vid","video":"v0310abc"}'

uv run python scripts/precise_erase.py '{"type":"Vid","video":"vid://v0d225gxxx"}' production_space

# Broader OCR (subtitle + other on-screen text)
uv run python scripts/precise_erase.py '{"type":"Vid","video":"v0310abc","text":true}'

uv run python scripts/precise_erase.py @params.json

# Resume after timeout
uv run python scripts/poll_execution.py '<RunId>' [space_name]

Parameter reference

ParameterTypeRequiredDescription
typestring✅Vid or DirectUrl
videostring✅Vid or VOD FileName; vid:// / directurl:// stripped automatically
textbooleannoIf true: Auto.Type: Text (more aggressive). Default false → subtitle-only.
all_textbooleannoSynonym for text (if both are set, text is applied first).
clip_filterobjectnoOmit = whole video. If set: mode skip or selected, and clips (non-empty list of { "start", "end" } seconds; Start/End accepted).
with_erase_infobooleannoDefault true (WithEraseInfo). If false, detailed erase geometry is not requested; stdout EraseMeta is {}.

Do not prompt users for Manual mode or NewVid.

Agent prompting (plain language)

Clarify: subtitle-only vs all on-screen text; whole video vs segments (skip / selected + clips); whether they need region-level erase telemetry (with_erase_info). Use conversational labels — avoid exposing raw JSON field names unless the user asks for implementation details.

Output format

On success, one JSON object on stdout, roughly:

{
  "Status": "Success",
  "SpaceName": "my_space",
  "VideoUrls": [
    {
      "FileId": "…",
      "Vid": "v0…",
      "DirectUrl": "path/to/output.mp4",
      "Source": "vid://v0…",
      "Url": "https://example.cdn.com/…"
    }
  ],
  "AudioUrls": [],
  "Texts": [],
  "EraseMeta": {
    "Duration": 57.099,
    "Info": {}
  }
}

When with_erase_info was false, EraseMeta is {}.

  • VideoUrls[0].Url: playable / downloadable when signing succeeds for the space.
  • Source: prefer vid://… when the API returns a new Vid; else directurl://….

Timeout handling (GetExecution polling)

Same pattern as the enhancement skill:

{
  "error": "Polling timed out (360 attempts × 5s); the job is still processing",
  "resume_hint": {
    "description": "The job has not finished yet; resume polling with the command below",
    "command": "uv run python scripts/poll_execution.py '<RunId>' [space_name]"
  }
}

Environment Variables

NameDescriptionRequired
BYTEPLUS_ACCESSKEYBytePlus Access KeyYes
BYTEPLUS_SECRETKEYBytePlus Secret KeyYes
VOD_SPACE_NAMEVOD space nameYes (or via CLI argument)
VOD_POLL_INTERVALPolling interval (seconds, default 5)No
VOD_POLL_MAXMaximum polling attempts (default 360)No
VOD_URL_EXPIRE_MINUTESSigned URL expiry (minutes, default 60)No
VOD_PLAY_DOMAINForce a specific playback domain (optional, highest priority)No
VOD_HOSTOverride VOD OpenAPI hostname (optional)No

Error Output Format

All failures use:

{"error": "error description"}

References

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Deploy, update, validate, and troubleshoot the AgentKit hybrid-cloud customer-service demo in this directory. Use when a user asks an AI coding agent to follow the README, deploy or update the demo, configure OpenAPI/Runtime/Knowledge/Memory/Sandbox/MCP/Skills/A2A, run customer-view validation, or record manual platform steps and failures.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

bytedance/agentkit-samples4742026년 10월 16일 업데이트

Generate deterministic SVG algorithmic artwork. Invoke when the user asks for geometric, generative, or algorithmic visual art.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

bytedance/agentkit-samples4742026년 10월 16일 업데이트

通过本地 Python CLI 和 OpenAPI 客户端管理、排查火山云手机资源。适用于查询实例和资源、截图、执行命令、查看任务、检查应用、主机和机房容量、标签、DNS、路由,以及操作已授权的测试云手机实例。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

bytedance/agentkit-samples4742026년 10월 16일 업데이트

Launch and continue the Volcengine AI Research survey workflow for concept testing, audience design, questionnaire drafting, interview guide generation, execution confirmation, progress checks, and result queries. Use this skill when the user wants to create, revise, confirm, execute, or follow up on a real AI research survey task in ABCompass instead of doing generic brainstorming, copywriting, translation, summarization, or broad market discussion.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

bytedance/agentkit-samples4742026년 10월 16일 업데이트

Create and check long-running video material evaluation tasks. Use this skill when the user wants to submit videos for evaluation, check an existing video evaluation task list, or fetch the result of a previously created video evaluation task. This skill is not a general-purpose video upload skill because upload is allowed only as an internal step of task creation. Authentication uses an API key passed as an Authorization bearer token.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

bytedance/agentkit-samples4742026년 10월 16일 업데이트

火山引擎 AntiDDoSPro 高防域名只读巡检。用户要查域名健康、攻击、流量、CC/WAF/区域封禁、智能防护或 CCAI 状态时使用。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

bytedance/agentkit-samples4742026년 10월 16일 업데이트

bytedance의 스킬 모두 보기

이 스킬의 문제 신고