Yichen Asr
mcncarl/yichen-skills
逸尘自用的统一音视频转写入口，在 StepFun Step ASR 与火山引擎豆包 ASR 之间按输出需求、安全边界和可用状态路由。用于本地音频或视频的纯文本转写、时间戳、SRT 字幕、口播粗剪，以及转写前体检；用户明确指定服务商时不得静默切换。Use when a local audio or video file needs transcription and the correct…
AI 视频导演与自动化剪辑专家。能够理解视频素材内容、视频创作指令，自主规划脚本结构，并通过调用 VectCut API 实现创建剪映草稿、编排素材（B-roll/转场/特效）、生成 AI 配音与字幕，实现端到端的视频创作流程。
Install Vectcut Skill
$ npx skills add LeoYeAI/openclaw-master-skills --skill vectcut-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills vectcut-skill --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/vectcut .claude/skills/vectcut-skill && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "vectcut-skill" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/vectcut into .claude/skills/vectcut-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vectcut-skill", 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.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/vectcutType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill vectcut-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills vectcut-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/vectcut .agents/skills/vectcut-skill && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "vectcut-skill" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/vectcut into .agents/skills/vectcut-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vectcut-skill", 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 LeoYeAI/openclaw-master-skills --skill vectcut-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills vectcut-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/vectcut .cursor/skills/vectcut-skill && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "vectcut-skill" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/vectcut into .cursor/skills/vectcut-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vectcut-skill", 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.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/vectcut--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill vectcut-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills vectcut-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/vectcut .gemini/skills/vectcut-skill && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "vectcut-skill" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/vectcut into .gemini/skills/vectcut-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vectcut-skill", 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 LeoYeAI/openclaw-master-skills vectcut-skillInstalls 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 LeoYeAI/openclaw-master-skills --skill vectcut-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/vectcut .github/skills/vectcut-skill && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "vectcut-skill" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/vectcut into .github/skills/vectcut-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vectcut-skill", 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 LeoYeAI/openclaw-master-skills --skill vectcut-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills vectcut-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/vectcut .opencode/skills/vectcut-skill && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "vectcut-skill" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/vectcut into .opencode/skills/vectcut-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vectcut-skill", 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.
Facts
- Skill name
vectcut-skill- GitHub stars
- 2.2k
- Token cost
- ~3k tokens
- SKILL.md length
- 472 words
- Files
- 177 (incl. scripts, references, assets)
- Skills in repo
- 1,235
- Repo updated
- First seen
- Licence
- MIT
At a glance
AI 视频导演与自动化剪辑专家。能够理解视频素材内容、视频创作指令，自主规划脚本结构，并通过调用 VectCut API 实现创建剪映草稿、编排素材（B-roll/转场/特效）、生成 AI 配音与字幕，实现端到端的视频创作流程。
- Works in 6 steps: 创建草稿 → 添加素材与时间线编排 → 高级能力（AI 与搜索） → …
- Tasks that involve Speech recognition and synthesis
- SKILL.md covers 核心智能行为, 环境变量配置, 执行路由 and 交互约定（输出格式）, plus 2 more sections
- Calls curl; reaches open.vectcut.com; needs VECTCUT_API_KEY
What it does
Vectcut Skill is an agent skill from LeoYeAI/openclaw-master-skills. AI 视频导演与自动化剪辑专家。能够理解视频素材内容、视频创作指令，自主规划脚本结构，并通过调用 VectCut API 实现创建剪映草稿、编排素材（B-roll/转场/特效）、生成 AI 配音与字幕，实现端到端的视频创作流程。
Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 179 other files, including scripts, reference files and assets (for example `CONTRIBUTE.md`, `README.md` and `_meta.json`).
It sits in AI & LLM Engineering, covering Speech recognition and synthesis. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
When your agent uses it
- Tasks that involve Speech recognition and synthesis
Example prompts
- “/vectcut-skill”
Requirements
- A credential in VECTCUT_API_KEY
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
open.vectcut.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
VECTCUT_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Vectcut Skill loads about 3k tokens when it runs, and up to ~110k if it reads all its reference files. Until then it costs about 32 tokens; SKILL.md has 472 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.
Safety
Auto-check passed
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.
SKILL.md
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 472 words, ~2,981 tokens.
Download SKILL.mdSave it as
.claude/skills/vectcut-skill/SKILL.md (or your agent's skills folder). This skill also uses 176 other files; get the full folder from GitHub.- name
- vectcut-skill
- description
- AI 视频导演与自动化剪辑专家。能够理解视频素材内容、视频创作指令，自主规划脚本结构，并通过调用 VectCut API 实现创建剪映草稿、编排素材（B-roll/转场/特效）、生成 AI 配音与字幕，实现端到端的视频创作流程。
- homepage
- https://www.vectcut.com/
VectCut Skill（自主规划型 AI 视频架构师）
本技能赋予 AI 像专业剪辑师一样**“思考与执行”**的能力。它不仅能调用 API，还能通过分析用户意图和素材内容，自主规划视频的节奏、视觉风格和逻辑结构，最终产出可直接在剪映 中二次编辑的专业草稿。
核心智能行为
- 素材感知：分析用户提供的视频/图片/音频 URL，理解画面内容与剪辑指令；优先调用现有服务
get_duration、get_resolution、video_detail、asr_basic、asr_nlp、asr_llm完成时长获取、分辨率判断、画面理解与语音内容解析。video_detail可提取细粒度语义（画面主体关系、人物朝向、物体位置、声音音调与风格等）。 - ASR 按需策略：默认优先级
asr_llm > asr_nlp > asr_basic，优先使用更高能力接口，仅在明确只需基础识别或时延敏感场景下降级。asr_basic：速度最快，返回完整文案、句级时间、字级时间；中文/英文效果好，支持粤语、上海话、闽南语、四川/陕西方言；更适合横屏字幕或素材初步理解。asr_nlp：速度中等，在 basic 基础上增加语义分句（每句不超过 12 字），更适合竖屏字幕。asr_llm：速度最慢，在 nlp 基础上增加 AI 关键词提取，优先用于竖屏与短视频字幕。- 三个 ASR 接口均支持传入
content（正确文案）以显著提升匹配准确率与处理速度。 - 三种回包结构不同，必须按端点解析：
asr_basic -> result.raw.result.utterances；asr_nlp -> segments；asr_llm -> segments(含 keywords/en)。
- 脚本规划：根据主题（如“成语故事”、“产品评测”）自动拆解分镜，确定各片段时长。
- 草稿生命周期管理：先创建并维护草稿，再进入编排流程；优先调用
create_draft初始化草稿，按需使用modify_draft修改草稿名/封面，任务异常或清理阶段使用remove_draft删除草稿。 - 反思自查：在关键步骤后调用
query_script回看当前草稿结构，核对轨道、素材与时间段是否符合预期；若不一致，先定位问题再执行修正操作。 - 视觉编排：基于已创建草稿自主选择并添加转场（Transitions）、特效（Effects）、滤镜（Filters）和文本（Text）。
- AI 资源补全：当素材不足时，主动调用
generate_image、generate_speech或generate_ai_video生成 B-roll 填充；其中generate_image支持nano_banana_2、nano_banana_pro、jimeng-4.5等聚合模型，generate_speech通过text + provider + model + voice_id合成配音，可配合volume、target_start、effect_type/effect_params控制入轨位置与音色效果。 - 文本编排生命周期：通过
add_text创建文本素材，使用modify_text调整文案与样式，使用remove_text清理无效文本；文本动画、字体与局部样式优先从枚举中选取，保证可用性与一致性。 - 图片编排生命周期：通过
add_image添加图片素材，使用modify_image调整图片源、时间段、位置与动画，使用remove_image清理无效图片；动画与蒙版类型优先从枚举中选取，保证编排稳定性。 - 视频编排生命周期：通过
add_video添加视频素材，使用modify_video调整素材源、裁切区间、位置与速度，使用remove_video清理无效视频；转场在片段首尾紧邻时生效，且需加在前一个元素上。 - AI 视频生成能力：通过
generate_ai_video调用聚合视频模型生成异步任务，再通过aivideo/task_status查询进度与视频结果；支持文生视频、图生视频与部分模型的首尾帧模式。 - 数字人能力：通过
digital_human/create发起音频驱动数字人任务，再通过digital_human/task_status查询生成状态与结果。 - 关键帧编排能力：通过
add_video_keyframe为文字、图片、视频设置位置、大小、透明度、旋转等关键帧，支持单点与批量关键帧写入。 - 云渲染与结果核验：通过
generate_video发起云渲染，再用task_status轮询任务状态。云渲染用于两类目标：创作中渲染中间结果核对预期；流程结束渲染最终成片并输出可直接播放的视频链接。 - 音画同步：如果需要，可以利用
get_duration计算素材时长，精确对齐视频轨道与音频轨道。 - 音视频预处理工具：在编排前可优先使用基础处理端点清洗素材。
extract_audio可从视频中提取音频（POST /process/extract_audio，入参video_url）；split_video可按时间段切分视频或音频（POST /process/split_video，入参video_url、start、end）。适用于替换现有视频 B-roll、素材混剪、先切段再入草稿等场景。
环境变量配置
所有调用均依赖于远程服务，需在环境中配置：
export VECTCUT_API_KEY="<your_token>"快捷规则与请求模板见：
rules/：决策规则与调用顺序scripts/：curl 请求模板与执行脚本examples/：curl 端到端示例prompts/：请求路由与命令生成提示词references/：端点参数与字段契约references/references.md：References 总索引（端点文档、回包解读、样例入口）
执行路由
按“能力域”路由。每个能力域复用同一条五层调用链：
- 规则层（rules）
- 全局：
rules/rules.md - 领域：
rules/<domain>_rules.md
- 全局：
- 参数层（references）
- 总索引：
references/references.md - 端点总览：
references/endpoint_params.md - 端点：
references/endpoints/<domain>.md - 枚举：
references/enums/*.json
- 总索引：
- 提示层（prompts）
- 路由与请求体生成：
prompts/<domain>_ops.md
- 路由与请求体生成：
- 执行层（scripts）
- 通过 curl 发起 API 请求：
scripts/<domain>_ops.sh
- 通过 curl 发起 API 请求：
- 验证层（examples）
- 基于 curl 的最小闭环验证：
examples/<domain>_ops_demo.sh
- 基于 curl 的最小闭环验证：
当前已落地能力域：filter
- 规则：
rules/filter_rules.md - 参数：
references/endpoints/filter.md - 提示：
prompts/filter_ops.md
当前已落地能力域：effect
- 规则：
rules/effect_rules.md - 参数：
references/endpoints/effect.md - 提示：
prompts/effect_ops.md
当前已落地能力域：material
- 规则：
rules/material_rules.md - 参数：
references/endpoints/material.md - 提示：
prompts/material_ops.md
当前已落地能力域：draft
- 规则：
rules/draft_rules.md - 参数：
references/endpoints/draft.md - 提示：
prompts/draft_ops.md
当前已落地能力域：asr
- 规则：
rules/asr_rules.md - 参数：
references/endpoints/asr.md - 提示：
prompts/asr_ops.md
当前已落地能力域：process
- 规则：
rules/process_rules.md - 参数：
references/endpoints/process.md - 提示：
prompts/process_ops.md
当前已落地能力域：generate_video
- 规则：
rules/generate_video_rules.md - 参数：
references/endpoints/generate_video.md - 提示：
prompts/generate_video_ops.md
当前已落地能力域：generate_speech
- 规则：
rules/generate_speech_rules.md - 参数：
references/endpoints/generate_speech.md - 提示：
prompts/generate_speech_ops.md - 端点：
POST /cut_jianying/generate_speech - 关键入参：
text、provider、model、voice_id、volume、target_start、effect_type、effect_params - 关键出参：
audio_url、draft_id、draft_url、material_id
当前已落地能力域：generate_ai_image
- 规则：
rules/generate_ai_image_rules.md - 参数：
references/endpoints/generate_ai_image.md - 提示：
prompts/generate_ai_image_ops.md - 端点：
POST /cut_jianying/generate_image - 关键入参：
prompt、model、reference_image、size、draft_id - 关键出参：
output.image_url、output.draft_id、output.draft_url
当前已落地能力域：generate_ai_video
- 规则：
rules/generate_ai_video_rules.md - 参数：
references/endpoints/generate_ai_video.md - 提示：
prompts/generate_ai_video_ops.md - 端点：
POST /cut_jianying/generate_ai_video、GET /cut_jianying/aivideo/task_status - 关键入参：
- generate：
prompt、model、resolution - status：
task_id
- generate：
- 关键出参：
- generate：
task_id - status：
status、progress、video_url、draft_id、draft_url
- generate：
当前已落地能力域：digital_human
- 规则：
rules/digital_human_rules.md - 参数：
references/endpoints/digital_human.md - 提示：
prompts/digital_human_ops.md - 端点：
POST /cut_jianying/digital_human/create、GET /cut_jianying/digital_human/task_status - 关键入参：
- create：
audio_url、video_url - status：
task_id
- create：
- 关键出参：
- create：
task_id或id - status：
status、progress、video_url
- create：
当前已落地能力域：video
- 规则：
rules/video_rules.md - 参数：
references/endpoints/video.md - 提示：
prompts/video_ops.md - 端点：
POST /cut_jianying/add_video、POST /cut_jianying/modify_video、POST /cut_jianying/remove_video - 关键入参：
- add：
video_url - modify/remove：
draft_id、material_id
- add：
- 关键出参：
output.draft_id、output.draft_url、output.material_id（add/modify）
当前已落地能力域：image
- 规则：
rules/image_rules.md - 参数：
references/endpoints/image.md - 提示：
prompts/image_ops.md - 端点：
POST /cut_jianying/add_image、POST /cut_jianying/modify_image、POST /cut_jianying/remove_image - 关键入参：
- add：
image_url - modify/remove：
draft_id、material_id
- add：
- 关键出参：
output.draft_id、output.draft_url、output.material_id（add/modify）
当前已落地能力域：text
- 规则：
rules/text_rules.md - 参数：
references/endpoints/text.md - 提示：
prompts/text_ops.md - 端点：
POST /cut_jianying/add_text、POST /cut_jianying/modify_text、POST /cut_jianying/remove_text - 关键入参：
- add：
text、start、end - modify：
draft_id、material_id、text、start、end - remove：
draft_id、material_id
- add：
- 关键出参：
- add：
output.material_id - modify/remove：
output.draft_id、output.draft_url
- add：
当前已落地能力域：keyframe
- 规则：
rules/keyframe_rules.md - 参数：
references/endpoints/keyframe.md - 提示：
prompts/keyframe_ops.md - 端点：
POST /cut_jianying/add_video_keyframe - 关键入参：
draft_id、track_name、property_types、times、values - 关键出参：
output.added_keyframes_count、output.draft_id、output.draft_url
Show full SKILL.md (191 more words)Show less
新增能力域时的约定
- 域命名统一使用小写下划线：
text/audio/subtitle/effect/keyframe/digital_human。 - 根文件只维护“能力域索引”，端点细节只写在对应
<domain>.md。 - 任意域新增端点时，只改该域文件，不改其他域。
交互约定（输出格式）
当你使用本技能完成“创建/编辑/渲染”类任务时，输出优先包含这些字段，便于后续继续编辑或查询：
draft_id：草稿 IDdraft_url：可打开的剪映/CapCut 草稿 URL，应封装为 markdown 超链接格式：[草稿名称](draft_url)material_id: 添加进草稿后的素材（图片、视频、音频、字幕、滤镜、贴纸、特效）的ID，方便后面继续操作
常用能力（可组合）
1) 创建草稿
调用：POST /create_draft
示例（1080x1920 竖屏）：
curl -X POST http://open.vectcut.com/cut_jianying/create_draft \
-H "Authorization: Bearer $VECTCUT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"width":1080,"height":1920,"name":"demo"}'2) 添加素材与时间线编排
你可以按需组合以下操作（都为 POST JSON）：
/add_video：添加视频（支持裁切、速度、变换、蒙版、混合、转场等）/modify_video：修改视频（基于material_id更新视频源、裁切区间、位置与速度）/remove_video：删除视频（基于material_id删除视频素材）/add_image：添加图片（支持入/出场动画、转场、蒙版、混合等）/modify_image：修改图片（基于material_id更新图片源、时长、位置、动画与样式）/remove_image：删除图片（基于material_id删除图片素材）/add_audio：添加音频（支持音量、变速、淡入淡出、音效等）/add_text：添加文字（支持字体、描边、阴影、背景、动画、多样式范围等）/modify_text：修改文字（基于material_id更新文案、时间段与样式）/remove_text：删除文字（基于material_id删除文本素材）/add_sticker：添加贴纸/add_effect：添加特效（scene/character）/add_filter：添加滤镜/add_video_keyframe：添加关键帧（支持位置、大小、透明度、旋转等属性）/get_video_scene_effect_types：获取场景特效（用于 effect_category=scene）/get_video_character_effect_types：获取人物特效（用于 effect_category=character）/get_filter_types：添加滤镜
3) 高级能力（AI 与搜索）
/generate_image：AI 图片生成并添加到草稿（支持文生图/图生图，聚合模型：nano_banana_2、nano_banana_pro、jimeng-4.5）/generate_ai_video：AI 视频生成（支持文生视频/图生视频/部分模型首尾帧，异步任务）/aivideo/task_status：查询 AI 视频生成任务状态与视频结果/digital_human/create：创建数字人口播任务（音频 + 视频输入）/digital_human/task_status：查询数字人任务状态与结果/generate_speech：TTS 语音合成并添加到草稿/llm/tts/fish/clone_voice：克隆音色并返回voice_id（可用于后续generate_speech）/llm/tts/voice_assets：查询已克隆音色资产（支持provider=minimax|fish|NULL）/remove_bg：智能抠像（移除背景）并生成合成预设/search_sticker：搜索在线贴纸素材
4) 获取可用枚举（动画/转场/特效/滤镜/字体）
用于让 AI 在可用范围内选型：
GET /get_transition_typesGET /get_mask_typesGET /get_intro_animation_types、/get_outro_animation_types、/get_combo_animation_typesGET /get_text_intro_types、/get_text_outro_types、/get_text_loop_anim_typesGET /get_video_scene_effect_types、/get_video_character_effect_typesGET /get_filter_typesGET /get_font_typesGET /get_audio_effect_types
示例（以转场枚举为例）：
curl -X GET "http://open.vectcut.com/cut_jianying/get_transition_types" \
-H "Authorization: Bearer $VECTCUT_API_KEY"4) 云渲染（中间核验 + 最终交付）
POST /generate_video：对草稿draft_id发起云渲染（返回task_id）。POST /task_status：轮询task_id获取渲染进度与结果。- 创作过程中：可按关键里程碑发起渲染，核对当前画面、节奏、字幕与预期是否一致。
- 任务结束时：必须轮询到完成态，并把结果中的可播放视频链接作为最终输出返回。
5. 典型场景示例
场景 A：成语故事/绘本视频制作（文生图 + 配音 + 自动对齐）
当用户需要制作“亡羊补牢”这样的故事视频时，建议按以下逻辑编排：
- 分镜拆解：将故事拆分为 N 个片段（图片 Prompt + 旁白文本）。
- 生成循环（对每个片段）：
- 调用
generate_image生成插图，获得image_url。 - 调用
generate_speech生成配音，获得audio_url。 - 关键点：调用
get_duration(url=audio_url)获取配音时长duration。 - 调用
add_image，将image_url加入草稿，并设置duration等于配音时长，确保音画同步。 - （如果
generate_speech未自动添加）调用add_audio添加配音。
- 调用
参考 Prompt 模板：assets/prompts/story_creation_zh.md
场景 B：素材混剪
- 创建草稿 → 2) add_video/add_audio/add_text → 3) generate_video 发起云渲染 → 4) task_status 轮询直到可取播放链接
curl -X POST http://open.vectcut.com/cut_jianying/create_draft \
-H "Authorization: Bearer $VECTCUT_API_KEY" \
-d '{"name":"my short"}'假设返回 draft_id=xxx 后：
curl -X POST http://open.vectcut.com/cut_jianying/add_video \
-H "Authorization: Bearer $VECTCUT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"draft_id":"xxx","video_url":"https://example.com/a.mp4","start":0,"end":10,"target_start":0}'发起渲染：
curl -X POST http://open.vectcut.com/cut_jianying/generate_video \
-H "Authorization: Bearer $VECTCUT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"draft_id":"xxx","resolution":"1080P","framerate":"30"}'轮询：
curl -X POST http://open.vectcut.com/cut_jianying/task_status \
-H "Authorization: Bearer $VECTCUT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"task_id":"TASK_ID"}'使用提示（让 AI 更“会剪”）
- 让用户提供素材 URL、期望时长、画面比例（9:16/16:9/1:1）、字幕风格、BGM 风格
- 需要更细粒度理解时，调用
video_detail理解（关系/朝向/位置/声音风格），再据此做镜头衔接、特效与字幕排版决策 - 需要严格可控的效果时，先拉取枚举（转场/特效/滤镜/字体），再进行选择与组装
- 复杂需求可以在上层自己组织调用顺序，这里只负责暴露基础视频编辑与渲染接口
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 176 other files (scripts, references, assets) in skills/vectcut of LeoYeAI/openclaw-master-skills.
- SKILL.md
- CONTRIBUTE.md
- README.md
- _meta.json
- assets/prompts/story_creation_zh.md
- assets/prompts/video_idea_zh.md
- assets/requests/add_audio_examples.json5
- assets/requests/add_effect_examples.json5
- assets/requests/add_filter_examples.json5
- assets/requests/add_sticker_examples.json5
- assets/requests/add_subtitle_examples.json5
- assets/requests/add_text_and_image_examples.json5
- assets/requests/add_text_template_examples.json5
- assets/requests/add_video_examples.json5
- assets/requests/add_video_keyframe_examples.json5
- assets/requests/create_draft_examples.json5
- assets/requests/generate_ai_video_examples.json5
- assets/requests/generate_image_examples.json5
- … and 159 more
Open the folder on GitHubat commit e5199b5
Compare with similar skills
Vectcut Skill 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 |
|---|---|---|---|---|---|---|
| Vectcut Skill this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~3k | Automated safety check: Pass | MIT | |
| Yichen Asrmcncarl/yichen-skills | 4.4k | — | ~780 | Automated safety check: Pass | Custom licence | |
| Youtube FetcherJimmySadek/youtube-fetcher-to-markdown | 485 | — | ~3.1k | Automated safety check: Pass | MIT | |
| End Of Speech Integrationrapidaai/voice-ai | 745 | — | ~877 | Automated safety check: Pass | Custom licence | |
| Video Understandingzenstory-ai/video-recap-skills | 559 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Hriterrense/ros2-multimodal-robot-collab | 111 | — | ~268 | Automated safety check: Pass | MIT |
Similar skills
Youtube Fetcher
JimmySadek/youtube-fetcher-to-markdown
Retrieve transcripts from YouTube, Instagram, TikTok, X, Vimeo and other video sites, summarize or analyze what was said (and shown on screen), or save an Obsidian-ready Markdown knowledge-base note…
End Of Speech Integration
rapidaai/voice-ai
Add or modify end-of-speech integrations in assistant-api with strict separation from VAD internals.
Video Understanding
zenstory-ai/video-recap-skills
把视频分析为结构化理解索引：场景检测、ASR 转写、逐场景 VLM 观察、静音窗口、融合时间线和写作 brief. An agent skill from zenstory-ai/video-recap-skills.
Hri
terrense/ros2-multimodal-robot-collab
A skill your agent uses when an Agent needs to speak to the operator through TTS, interpret ASR text, request clarification, or confirm a robot delivery action.
Ax Audio
dosco/aithy
This skill helps an LLM generate correct audio code with @ax-llm/ax.
More from LeoYeAI/openclaw-master-skills
All 1,235 skills in this repoDevOps Pipeline Management
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
Feishu Document Collaboration
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
Files Memory System
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
GEO-Claw AI Visibility Agent
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
Google Workspace CLI
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
HealthFit Health Advisors
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Related
Categories
Questions about Vectcut Skill
What does Vectcut Skill do?
AI 视频导演与自动化剪辑专家。能够理解视频素材内容、视频创作指令，自主规划脚本结构，并通过调用 VectCut API 实现创建剪映草稿、编排素材（B-roll/转场/特效）、生成 AI 配音与字幕，实现端到端的视频创作流程。. Vectcut Skill is an agent skill from LeoYeAI/openclaw-master-skills.
When should I use Vectcut Skill?
Vectcut Skill fits situations like: tasks that involve Speech recognition and synthesis.
How do I install Vectcut Skill in Claude Code?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill vectcut-skill -a claude-code`. Or copy the skill folder (skills/vectcut in LeoYeAI/openclaw-master-skills) into .claude/skills/vectcut-skill in your project. Claude Code loads it when a task matches its description.
How do I install Vectcut Skill in Codex?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill vectcut-skill -a codex`. Or copy the skill folder (skills/vectcut in LeoYeAI/openclaw-master-skills) into .agents/skills/vectcut-skill in your project. Codex loads it when a task matches its description.
Can I use Vectcut Skill in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill vectcut-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vectcut-skill, .gemini/skills/vectcut-skill, .github/skills/vectcut-skill and .opencode/skills/vectcut-skill in your project.
What does Vectcut Skill need to run?
Going by SKILL.md and its folder, Vectcut Skill needs the command-line tools its instructions call (curl) and credentials named VECTCUT_API_KEY. Our summary lists: A credential in VECTCUT_API_KEY.
Does Vectcut Skill access the network?
SKILL.md names 1 domain. In commands or code: open.vectcut.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Vectcut Skill safe to install?
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.
What licence does Vectcut Skill use?
Vectcut Skill is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Vectcut Skill use?
About 3k tokens (SKILL.md is roughly 12k 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 107k tokens, read only when the agent opens those files.
What are the alternatives to Vectcut Skill?
Skills that share tags, products or a category with Vectcut Skill: Yichen Asr (mcncarl/yichen-skills, 4.4k stars), Youtube Fetcher (JimmySadek/youtube-fetcher-to-markdown, 485 stars), End Of Speech Integration (rapidaai/voice-ai, 745 stars) and Video Understanding (zenstory-ai/video-recap-skills, 559 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Vectcut Skill?
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,160 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.