Agent skill

Carocut Media Audio

by bilibili in bilibili/carocut

音频素材生成与获取。批量 Edge TTS 旁白生成(支持 storyboard pacing 字段驱动语速)、BGM/SFX 检索(BGM 节奏匹配 BPM 规则)、音频时长提取。包含 Edge voice 配置、速度调整规则、durations.json 格式规范(含 audiovisualrelation 说明)和关键的音频时序规则。

Custom licenceAuto-check passedMedia & Creative

Install Carocut Media Audio

skills CLI
$ npx skills add bilibili/carocut --skill carocut-media-audio -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install bilibili/carocut carocut-media-audio --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/bilibili/carocut.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/carocut-media-audio .claude/skills/carocut-media-audio && rm -rf skills-src

Use ~/.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/

Facts

Skill name
carocut-media-audio
GitHub stars
130
Token cost
~2.5k tokens
SKILL.md length
1,054 words
Files
2 (incl. references)
Skills in repo
11
Repo updated
First seen
Licence
Custom licence

At a glance

音频素材生成与获取。批量 Edge TTS 旁白生成(支持 storyboard pacing 字段驱动语速)、BGM/SFX 检索(BGM 节奏匹配 BPM 规则)、音频时长提取。包含 Edge voice 配置、速度调整规则、durations.json 格式规范(含 audiovisualrelation 说明)和关键的音频时序规则。

  • Works in 4 steps: Parse {project_dir}/manifests/script.md… → For each VO segment, invoke Edge TTS… → Save each result as VO_XXX.wav in… → …
  • Tasks that involve Text to speech and voice
  • SKILL.md covers Audio Types, Voiceover Generation, Duration Extraction and BGM and SFX Retrieval, plus 7 more sections
  • Needs FREESOUND_API_KEY

What it does

Carocut Media Audio is an agent skill from bilibili/carocut. 音频素材生成与获取。批量 Edge TTS 旁白生成(支持 storyboard pacing 字段驱动语速)、BGM/SFX 检索(BGM 节奏匹配 BPM 规则)、音频时长提取。包含 Edge voice 配置、速度调整规则、durations.json 格式规范(含 audiovisualrelation 说明)和关键的音频时序规则。

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/edge-tts.md`).

It sits in Media & Creative, covering Text to speech and voice and Comics and storyboards. The repository describes itself as: Multi-Agent 的视频制作助手,基于 OpenCode AI SDK 和 Remotion 构建。

When your agent uses it

  • Tasks that involve Text to speech and voice
  • Tasks that involve Comics and storyboards

Example prompts

  • “/carocut-media-audio”

Requirements

  • Python 3
  • A credential in FREESOUND_API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Parse {project_dir}/manifests/script.md for all [VO_XXX] markers and their text content
  2. For each VO segment, invoke Edge TTS with the configured voice and speed
  3. Save each result as VO_XXX.wav in {project_dir}/raws/audio/vo/
  4. After all segments complete, extract durations to create {project_dir}/manifests/durations.json

What it can do on your machine

Read from SKILL.md and the folder at commit 2f8dc10. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • FREESOUND_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Carocut Media Audio loads about 2.5k tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 48 tokens; SKILL.md has 1,054 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.7k

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); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,054 words (~2,456 tokens).

“Generates voiceovers via TTS, retrieves background music and sound effects. Creates durations.json for timing synchronization in Remotion.”

— opening of SKILL.md by bilibili, Custom licence
name
carocut-media-audio

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (references) in .opencode/skills/carocut-media-audio of bilibili/carocut.

  • SKILL.md
  • references/edge-tts.md

Open the folder on GitHubat commit 2f8dc10

Compare with similar skills

Carocut Media Audio 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.

Carocut Media Audio compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Carocut Media Audio this skillbilibili/carocut130—~2.5kAutomated safety check: PassCustom licence
Hbg Life SimulationMr-funny/hbg-life-simulation141—~5.8kAutomated safety check: PassMIT
Paper Collage Explainer Generatortl2012tl/comfyUI-llama-TE2414 repos~5.2kAutomated safety check: PassNone
Vibe Scenevericontext/vibeframe175—~1.8kAutomated safety check: PassMIT
Paper Collage Explainer Generatorvllm-project/vllm-omni7.1k—~976Automated safety check: PassApache-2.0
Video DirectorJamailar/Beav1.8k—~9.6kAutomated safety check: PassCustom licence

Similar skills

  • Hbg Life Simulation

    Mr-funny/hbg-life-simulation

    Create Chinese HBG “模拟人生 / 人生副本” narrative videos with a consistent comic IP, a rapid multi-life opening, continuous natural-speed narration, synchronized short captions, dense static manga…

    141 GitHub stars~5.8k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Paper Collage Explainer Generator

    tl2012tl/comfyUI-llama-TE

    For creators, educators, and social-video editors who need a tactile paper-collage language for narration, knowledge points, opinions, or abstract topics.

    241 GitHub starsUsed in 4 repos~5.2k tokens
    Media & CreativeAuto-check passed
  • Vibe Scene

    vericontext/vibeframe

    Author, repair, render, and inspect VibeFrame scene projects built from STORYBOARD.md and DESIGN.md.

    175 GitHub stars~1.8k tokensUpdated 6 days ago
    Media & CreativeAuto-check passed
  • Paper Collage Explainer Generator

    vllm-project/vllm-omni

    Translate narration, ideas, or knowledge points into editorial halftone paper-collage metaphors, still prompts, storyboards, or stop-motion clips.

    7.1k GitHub stars~976 tokensUpdated today
    Media & CreativeAuto-check passed
  • Video Director

    Jamailar/Beav

    Canonical entrypoint for every AI chat request that asks to make, generate, plan, or edit a video, including promotional films, ads, short videos, product videos, reference-image videos…

    1.8k GitHub stars~9.6k tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • Ipollowork Video Studio

    Devin-AXIS/iPolloWork

    Route the active iPolloWork video request to its current storyboard, compose, voiceover or soundtrack work, using the engine's native workflow and existing media tools.

    6.8k GitHub stars~382 tokensUpdated yesterday
    Media & CreativeAuto-check passed

More from bilibili/carocut

All 11 skills in this repo
  • Remotion API 参考索引。包含 50+ 条 Remotion API 规则的目录索引、关键规则速查表、常用模式代码示例。加载此 skill 获取索引,然后按需 read 具体规则文件。是 carocut-builder-compositor 的伴侣参考。

    130 GitHub stars~2.5k tokensUpdated 5 mo ago
    Auto-check passed
  • Carocut Builder Pipeline

    bilibili/carocut

    Remotion 资产管道。调用 projectmigrate tool 将 raws/ 素材迁移到 template-project/public/ 并生成 resourceMap.ts、constants.ts、timing.ts。Agent 只需 edit constants.ts 中的 COLORS 和 FONTS。

    130 GitHub stars~730 tokensUpdated 5 mo ago
    Auto-check passed
  • Carocut Builder Setup

    bilibili/carocut

    额外包检测与安装。根据 storyboard 检测并安装额外依赖(lottie/3D/charts/gif 等)。模板和基础依赖已在 bootstrap 阶段完成。

    130 GitHub stars~436 tokensUpdated 5 mo ago
    Auto-check passed
  • Carocut Media Visual

    bilibili/carocut

    视觉素材获取与生成。根据 resources.yaml 定义,通过库存图片/视频搜索(Pexels/Pixabay)或 AI 生图(Caro LLM)获取视觉素材。包含搜索策略、视觉隐喻搜索(counterpoint 声画关系)、构图感知搜索(framing 字段)、prompt 工程指南、素材质量评估标准。

    130 GitHub stars~4.1k tokensUpdated 5 mo ago
    Auto-check passed
  • Carocut Planner Analysis

    bilibili/carocut

    视频素材分析与清点。解析 PDF 文档提取文本/图片/表格,组织原始素材目录,生成结构化的 inventory.yaml 素材清单。

    130 GitHub stars~1.8k tokensUpdated 5 mo ago
    Auto-check passed
  • Carocut Reviewer

    bilibili/carocut

    视频预览审查与最终渲染。Remotion Studio 预览启动、常见渲染错误排查、调试模式配置、渲染参数优化、用户反馈迭代流程、问题严重度分级(minor 自行修复 vs major 回退 builder)。

    130 GitHub stars~2.7k tokensUpdated 5 mo ago
    Auto-check passed

Questions about Carocut Media Audio

What does Carocut Media Audio do?

音频素材生成与获取。批量 Edge TTS 旁白生成(支持 storyboard pacing 字段驱动语速)、BGM/SFX 检索(BGM 节奏匹配 BPM 规则)、音频时长提取。包含 Edge voice 配置、速度调整规则、durations.json 格式规范(含 audiovisualrelation 说明)和关键的音频时序规则。. Carocut Media Audio is an agent skill from bilibili/carocut.

When should I use Carocut Media Audio?

Carocut Media Audio fits situations like: tasks that involve Text to speech and voice; tasks that involve Comics and storyboards.

How do I install Carocut Media Audio in Claude Code?

Run `npx skills add bilibili/carocut --skill carocut-media-audio -a claude-code`. Or copy the skill folder (.opencode/skills/carocut-media-audio in bilibili/carocut) into .claude/skills/carocut-media-audio in your project. Claude Code loads it when a task matches its description.

How do I install Carocut Media Audio in Codex?

Run `npx skills add bilibili/carocut --skill carocut-media-audio -a codex`. Or copy the skill folder (.opencode/skills/carocut-media-audio in bilibili/carocut) into .agents/skills/carocut-media-audio in your project. Codex loads it when a task matches its description.

Can I use Carocut Media Audio 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 bilibili/carocut --skill carocut-media-audio -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/carocut-media-audio, .gemini/skills/carocut-media-audio, .github/skills/carocut-media-audio and .opencode/skills/carocut-media-audio in your project.

What does Carocut Media Audio need to run?

Going by SKILL.md and its folder, Carocut Media Audio needs credentials named FREESOUND_API_KEY. Our summary lists: Python 3; A credential in FREESOUND_API_KEY.

Does Carocut Media Audio access the network?

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.

Is Carocut Media Audio 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. Review the folder before installing.

What licence does Carocut Media Audio use?

Carocut Media Audio has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Carocut Media Audio use?

About 2.5k tokens (SKILL.md is roughly 9.8k 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 210 tokens, read only when the agent opens those files.

What are the alternatives to Carocut Media Audio?

Skills that share tags, products or a category with Carocut Media Audio: Hbg Life Simulation (Mr-funny/hbg-life-simulation, 141 stars), Paper Collage Explainer Generator (tl2012tl/comfyUI-llama-TE, 241 stars), Vibe Scene (vericontext/vibeframe, 175 stars) and Paper Collage Explainer Generator (vllm-project/vllm-omni, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Carocut Media Audio?

bilibili (a GitHub organization) maintains it in bilibili/carocut, which has 130 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on April 20, 2026.

Source: bilibili/carocut on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.