Orchestrate a configurable, debuggable local pipeline from approved narration packages to timed audio, captions, visual assets, semantic motion, rendered video, optional avatar compositing…
$ npx skills add JayceHuang/agent-video-pipeline --skill agent-video-pipeline -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install JayceHuang/agent-video-pipeline agent-video-pipeline --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agent-video-pipeline" agent skill from https://github.com/JayceHuang/agent-video-pipeline/tree/main into .claude/skills/agent-video-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-video-pipeline", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JayceHuang/agent-video-pipeline --skill agent-video-pipeline -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install JayceHuang/agent-video-pipeline agent-video-pipeline --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-video-pipeline" agent skill from https://github.com/JayceHuang/agent-video-pipeline/tree/main into .agents/skills/agent-video-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-video-pipeline", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JayceHuang/agent-video-pipeline --skill agent-video-pipeline -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install JayceHuang/agent-video-pipeline agent-video-pipeline --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-video-pipeline" agent skill from https://github.com/JayceHuang/agent-video-pipeline/tree/main into .cursor/skills/agent-video-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-video-pipeline", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JayceHuang/agent-video-pipeline --skill agent-video-pipeline -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install JayceHuang/agent-video-pipeline agent-video-pipeline --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-video-pipeline" agent skill from https://github.com/JayceHuang/agent-video-pipeline/tree/main into .gemini/skills/agent-video-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-video-pipeline", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install JayceHuang/agent-video-pipeline agent-video-pipelineInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add JayceHuang/agent-video-pipeline --skill agent-video-pipeline -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-video-pipeline" agent skill from https://github.com/JayceHuang/agent-video-pipeline/tree/main into .github/skills/agent-video-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-video-pipeline", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JayceHuang/agent-video-pipeline --skill agent-video-pipeline -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install JayceHuang/agent-video-pipeline agent-video-pipeline --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-video-pipeline" agent skill from https://github.com/JayceHuang/agent-video-pipeline/tree/main into .opencode/skills/agent-video-pipeline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-video-pipeline", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
agent-video-pipelineOrchestrate a configurable, debuggable local pipeline from approved narration packages to timed audio, captions, visual assets, semantic motion, rendered video, optional avatar compositing…
Agent Video Pipeline is an agent skill from JayceHuang/agent-video-pipeline. Orchestrate a configurable, debuggable local pipeline from approved narration packages to timed audio, captions, visual assets, semantic motion, rendered video, optional avatar compositing, publishing assets, and QC. Use for building, batch-producing, resuming, rerendering, or debugging explainer-video projects. Keep author identity, voice assets, CTA, illustration provider, canvas, avatar layout, brand, platform copy, delivery paths, and machine runtime in external profiles; use the separate…
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 64 other files, including scripts, reference files and assets (for example `README.md`, `agents/openai.yaml` and `references/debug-checklist.md`).
It sits in Media & Creative, covering Text to speech and voice and Video production. It works with Python. The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit ef0edce. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Agent Video Pipeline loads about 1.8k tokens when it runs, and up to ~20k if it reads all its reference files. Until then it costs about 153 tokens; SKILL.md has 210 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from JayceHuang/agent-video-pipeline at commit ef0edce, republished under its MIT licence (© JayceHuang). 210 words, ~1,845 tokens.
.claude/skills/agent-video-pipeline/SKILL.md (or your agent's skills folder). This skill also uses 60 other files; get the full folder from GitHub.编排可复现、可调试、可增量重建的本地讲解视频。Skill 只保存通用流程、契约、Schema、provider adapter 和 QC；任何个人风格或本机路径必须通过外部配置注入。
流水线没有合法的集中式 .agent-video/ 时禁止运行。配置根目录必须位于项目目录的某一级祖先，或通过 --config-root / AGENT_VIDEO_CONFIG_ROOT 显式指定，并且必须完整包含：
.agent-video/
├── profiles/workspace.yaml
├── runtime.local.yaml
├── projects/
├── assets/
└── resolved/外部工作区 Profile 只能来自 profiles/，项目覆盖只能来自 projects/，本机 runtime 只能使用根目录下唯一的 runtime.local.yaml。需要时，声音、人像、人物 IP、Logo、音乐等复用资产统一放进 assets/；项目目录不得再维护工作区配置副本。初始化生成的模板必须保持中性，不得预填作者姓名、人物 IP、CTA、品牌或其他个人信息。
Skill 内只保存可公开发布的脱敏模板：
references/templates/
├── workspace.example.yaml
└── runtime.local.example.yaml初始化脚本必须从这两份模板生成外部实例，不能在代码里另存一套字段。Skill 内模板只含中性默认值和占位符；真实解释器、模型、凭据引用、品牌与授权资产只能写入工作区的 .agent-video/。
第一次使用时，必须先运行纯 Python、跨平台的初始化脚本。它只创建缺失内容，重复执行不会覆盖已有 Profile 或 runtime：
# macOS / Linux
python scripts/init_config_root.py \
--workspace <workspace-dir># Windows PowerShell
python scripts\init_config_root.py `
--workspace <workspace-dir>默认生成 profiles/workspace.yaml，其中 profile_id 为 workspace。只有用户明确需要多个外部 Profile 时才传 --profile-id <custom-id>。需要指定独立的声音环境时增加 --tts-python <path>，本地模型增加 --model-path <path>；脚本默认把当前执行它的 Python 写入 pipeline_runtime.python。初始化后先审核中性工作区 Profile、runtime 和授权资产，再冻结项目配置。
Codex 接到运行请求时必须先检查 .agent-video/。如果不存在或不完整：停止生产，说明将生成的位置，使用 init_config_root.py 初始化，并引导用户只补充无法安全自动检测的选项；不得把真实配置写回 Skill。初始化完成后必须再由 resolve_profile.py 验证并冻结，验证失败时不得进入 TTS、插图、渲染或数字人阶段。
每个项目在高成本操作前必须生成唯一的 resolved profile：
"<pipeline_runtime.python>" scripts/resolve_profile.py \
--config-root <workspace>/.agent-video \
--profile-id workspace \
--project-config <workspace>/.agent-video/projects/<optional-project>.yaml \
--project <project-dir>首次运行从统一根目录的 runtime.local.yaml 读取 pipeline_runtime.python；缺少集中配置根目录、外部工作区 Profile、runtime 或规定目录时立即失败，不能回退到散落在项目里的配置或只用 Skill 默认值。后续所有通用 Python 控制脚本都使用 resolved profile 中的该解释器。下游脚本优先读取 <project>/.pipeline/resolved-profile.json，并校验其中的配置契约版本、配置根目录、来源角色与 SHA；旧式 resolved profile 必须重新生成。配置规则见 references/profile-contract.md。
.agent-video 集中配置契约无效时停止所有真实流水线阶段。长文改写调用独立的 adapt-longform-for-speech Skill。已批准稿件可直接标准化。流水线 adapter 再把通用 spoken-script.json 转换为项目的 series.json 与 scenes.json。
"<pipeline_runtime.python>" scripts/import_spoken_script.py \
--script <spoken-script.json> \
--script-qc <script-qc.json> \
--profile <resolved-profile.json> \
--series-output <series.json> \
--projects-root <episode-projects-dir>"<pipeline_runtime.python>" scripts/validate_episode_independence.py \
--series <series.json> \
--profile <resolved-profile.json>先生成并批准 audio/prosody.json，再调用 Profile 选择的声音 provider。随包的 VoxCPM2 脚本是可选 adapter，不是个人默认值；模型、对齐环境、声音原件和 prompt 由 resolved profile 或 CLI 提供。
本地声音 provider 必须使用 resolved profile 的 tts_runtime.generator_python 启动，不能沿用环境中的裸 python3。随包 adapter 的调用方式如下；解释器、模型与对齐器路径都来自同一份 frozen profile：
"<pipeline_runtime.python>" scripts/analyze_prosody.py \
--scenes <scenes.json> --profile <resolved-profile.json> \
--output <audio/prosody.json>
"<pipeline_runtime.python>" scripts/approve_if_clean.py --file <audio/prosody.json> --kind prosody
"<tts_runtime.generator_python>" scripts/generate_all_voxcpm2.py \
--mode episode-take --series <series.json> --project <project-dir> \
--profile <resolved-profile.json> --episode <episode-number>
"<pipeline_runtime.python>" scripts/run_gates.py --project <project-dir> --stage audio \
--profile <resolved-profile.json>audio/output/narration_master.wav 是字幕、动画、数字人和成片时长的唯一音频时间基准。
是否调用插图 Skill、provider、资产数量和跳过策略全部读取 Profile。所有项目先初始化明确的 visual-assets.json 决策；启用 provider 时再由 provider 填充并通过验证。
"<pipeline_runtime.python>" scripts/init_visual_assets.py \
--project <project-dir> --profile <resolved-profile.json>
"<pipeline_runtime.python>" scripts/validate_visual_assets.py \
--project <project-dir> --profile <resolved-profile.json>Profile 启用 provider 时，先让 provider 把初始化 manifest 更新为 complete / reused；
允许跳过的可选 provider 更新为 skipped。初始化器默认不覆盖已有决策。
"<pipeline_runtime.python>" scripts/plan_semantic_motion.py \
--scenes <scenes.json> --timeline <audio/timeline.json> \
--prosody <audio/prosody.json> --caption-words <audio/caption-words.json> \
--visual-assets <visual-assets.json> --resolved-profile <resolved-profile.json> \
--output <.hyperframes/semantic-motion.json>
"<pipeline_runtime.python>" scripts/init_layout_boxes.py \
--motion-plan <.hyperframes/semantic-motion.json> \
--profile <resolved-profile.json> \
--output <.hyperframes/layout-boxes.json>
"<pipeline_runtime.python>" scripts/run_gates.py --project <project-dir> --stage motion \
--profile <resolved-profile.json>布局与动效必须确定性、seek-safe，并以 Profile 的画布、protected zones、motion preset 和 provider 决策为准。
先生成基础视频。需要数字人时调用独立的 compose-avatar-video Skill，获得 composited video 后再进入最终包装；不需要数字人时直接使用基础视频。
"<pipeline_runtime.python>" scripts/finalize_video_assets.py \
--video <selected-video.mp4> \
--profile <resolved-profile.json> \
--title "..." --summary "..."
"<pipeline_runtime.python>" scripts/run_gates.py --project <project-dir> --stage final \
--profile <resolved-profile.json>外部交付目录未配置时只保留项目内交付包，不假设任何个人云盘或 NAS 路径。
先运行 scripts/run_gates.py --stage all，只修失败层。缓存、耗时、门禁顺序与产物契约见 references/workflow-contract.md 和 references/debug-checklist.md。
scripts/init_config_root.pyreferences/templates/workspace.example.yaml、references/templates/runtime.local.example.yaml© JayceHuang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 60 other files (scripts, references, assets) in the repository root of JayceHuang/agent-video-pipeline.
Open the folder on GitHubat commit ef0edce
Agent Video Pipeline next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Video Pipeline this skillJayceHuang/agent-video-pipeline | 105 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Web Demo Video SynthesisSven-LI-sankyuu/presentation-skills | 175 | — | ~3.2k | Automated safety check: Pass | None | |
| MoneyPrinterTurbo Video Generatorharry0703/MoneyPrinterTurbo | 130k | — | ~2.1k | Automated safety check: Warn | MIT | |
| JianYing Editor Automationluoluoluo22/jianying-editor-skill | 3.9k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Vox DirectorAlisa0808/vox-director | 2.2k | — | ~5.6k | Automated safety check: Pass | MIT | |
| Video Podcast Makerdtsola/xiaoyaosearch | 1k | — | ~3.4k | Automated safety check: Pass | MIT |
Sven-LI-sankyuu/presentation-skills
用于“网页 demo 分段配音 + timeline 驱动录屏 + 后期合成”的 workspace 协作流程：先搭建一个可审计工作目录（cues/timeline/segmentaudio/video/subtitles/final），再由人类 + Codex 迭代维护这些文件，按需只重跑局部步骤，最终合成高质量 MP4。适用于强调可复盘、可编辑、清晰度与字幕安全区可控的场景。
harry0703/MoneyPrinterTurbo
Installs and runs MoneyPrinterTurbo to turn a topic or script into a finished short video with voice-over, subtitles, stock footage and music.
luoluoluo22/jianying-editor-skill
Automates JianYing Pro video editing through a Python wrapper, JyWrapper, covering drafts, media import, subtitles, screen recording, voiceover and export.
Alisa0808/vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all…
dtsola/xiaoyaosearch
Turns a topic into a 4K horizontal video podcast through research, scripting, text-to-speech, Remotion rendering and background music, and can learn styles from references.
gnipbao/codex-whiteboard-video-skill
Generate smooth hand-drawn whiteboard and story videos directly inside Codex from text scripts, GPT Image 2 color storyboards, scene plans, SVGs, line art, or local images.
Works with
Categories
Orchestrate a configurable, debuggable local pipeline from approved narration packages to timed audio, captions, visual assets, semantic motion, rendered video, optional avatar compositing…. Agent Video Pipeline is an agent skill from JayceHuang/agent-video-pipeline. Orchestrate a configurable, debuggable local pipeline from approved narration packages to timed audio, captions, visual assets, semantic motion, rendered video, optional avatar compositing, publishing assets, and QC.
Agent Video Pipeline fits situations like: batch-producing; debugging explainer-video projects.
Run `npx skills add JayceHuang/agent-video-pipeline --skill agent-video-pipeline -a claude-code`. Or copy the skill folder (the JayceHuang/agent-video-pipeline repository) into .claude/skills/agent-video-pipeline in your project. Claude Code loads it when a task matches its description.
Run `npx skills add JayceHuang/agent-video-pipeline --skill agent-video-pipeline -a codex`. Or copy the skill folder (the JayceHuang/agent-video-pipeline repository) into .agents/skills/agent-video-pipeline in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JayceHuang/agent-video-pipeline --skill agent-video-pipeline -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-video-pipeline, .gemini/skills/agent-video-pipeline, .github/skills/agent-video-pipeline and .opencode/skills/agent-video-pipeline in your project.
Going by SKILL.md and its folder, Agent Video Pipeline needs the command-line tools its instructions call (python). Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Agent Video Pipeline is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.8k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 18k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Agent Video Pipeline: Web Demo Video Synthesis (Sven-LI-sankyuu/presentation-skills, 175 stars), MoneyPrinterTurbo Video Generator (harry0703/MoneyPrinterTurbo, 130k stars), JianYing Editor Automation (luoluoluo22/jianying-editor-skill, 3.9k stars) and Vox Director (Alisa0808/vox-director, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
JayceHuang (a GitHub user) maintains it in JayceHuang/agent-video-pipeline, which has 105 GitHub stars. The repository was last updated on August 28, 2026.
Source: JayceHuang/agent-video-pipeline on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
