#885 by GitHub stars
ChatCut-Inc/agent-plugin
AI video editor for agents. ChatCut plugin and MCP server for Codex, ChatGPT, Claude Code, Cursor, Grok, Gemini CLI, WorkBuddy, Doubao Work and Qwen Work: edit your own footage by chatting, add captions and subtitles, remove silences and filler words, create motion graphics, and export an editable timeline.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
chatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/asset-import/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/chatcut-plugin-basics-claude/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/create-motion-graphics/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/digital-human/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/export/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/image-gen/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/known-errors/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/multicam-sync/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/music/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/product-help/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/shader-gen/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/talking-head-guide/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/transcription/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/verification/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/video-gen/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/video-translation/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/visual-analysis/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/voice/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
claude/skills/widget-forms/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/asset-import/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/chatcut-plugin-basics/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/create-motion-graphics/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/digital-human/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/export/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/known-errors/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/multicam-sync/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/music/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/product-help/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/shader-gen/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/talking-head-guide/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/transcription/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/verification/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/video-gen/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/video-translation/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/visual-analysis/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/voice/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
codex/skills/widget-forms/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/asset-import/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/chatcut-plugin-basics/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/create-motion-graphics/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/digital-human/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/export/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/known-errors/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/lipsync/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/multicam-sync/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/music/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/product-help/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/shader-gen/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/talking-head-guide/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/transcription/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/verification/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/video-gen/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/video-translation/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/voice/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
grok/skills/widget-forms/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/chatcut-captions-guide/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/chatcut-connect/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/chatcut-editing-guide/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/chatcut-editor-handoff/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/chatcut-export-guide/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/chatcut-media-guide/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/chatcut-plugin-basics-kimi-work/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/chatcut-verification-guide/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/create-motion-graphics/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/digital-human/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/known-errors/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/multicam-sync/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/music/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/product-help/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/shader-gen/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/video-gen/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/video-translation/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
kimi/skills/voice/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
06e83c224aec → e8ebd99b5ca9
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Verified commit e8ebd99b5ca936498cfd3562ffa995c4e5a23849
git clone --filter=blob:none --no-checkout https://github.com/ChatCut-Inc/agent-plugin.git .hotskills/chatcut-inc-agent-plugin && git -C .hotskills/chatcut-inc-agent-plugin checkout --detach e8ebd99b5ca936498cfd3562ffa995c4e5a23849
# Copy each selected skill directory from .hotskills/chatcut-inc-agent-plugin into .claude/skills/<skill-name>/Heat
6.7- Star growth, last 7 daysAhead of 90% of tracked repositories
- Star growth, last 24 hoursAhead of 96% of tracked repositories
- Rank movement, last 7 daysAhead of 19% of tracked repositories
- Commits, last 30 daysAhead of 94% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- connect-chatcut-desktop
chatcut-desktop-codex-plugin/skills/connect-chatcut-desktop - asset-import
claude/skills/asset-import - chatcut-plugin-basics-claude
claude/skills/chatcut-plugin-basics-claude - create-motion-graphics
claude/skills/create-motion-graphics - digital-human
claude/skills/digital-human - export
claude/skills/export - image-gen
claude/skills/image-gen - known-errors
claude/skills/known-errors - multicam-sync
claude/skills/multicam-sync - music
claude/skills/music - product-help
claude/skills/product-help - shader-gen
claude/skills/shader-gen - talking-head-guide
claude/skills/talking-head-guide - transcription
claude/skills/transcription - verification
claude/skills/verification - video-gen
claude/skills/video-gen - video-translation
claude/skills/video-translation - visual-analysis
claude/skills/visual-analysis - voice
claude/skills/voice - widget-forms
claude/skills/widget-forms - asset-import
codex/skills/asset-import - chatcut-plugin-basics
codex/skills/chatcut-plugin-basics - create-motion-graphics
codex/skills/create-motion-graphics - digital-human
codex/skills/digital-human - export
codex/skills/export - known-errors
codex/skills/known-errors - multicam-sync
codex/skills/multicam-sync - music
codex/skills/music - product-help
codex/skills/product-help - shader-gen
codex/skills/shader-gen - talking-head-guide
codex/skills/talking-head-guide - transcription
codex/skills/transcription - verification
codex/skills/verification - video-gen
codex/skills/video-gen - video-translation
codex/skills/video-translation - visual-analysis
codex/skills/visual-analysis - voice
codex/skills/voice - widget-forms
codex/skills/widget-forms - asset-import
grok/skills/asset-import - chatcut-plugin-basics
grok/skills/chatcut-plugin-basics - create-motion-graphics
grok/skills/create-motion-graphics - digital-human
grok/skills/digital-human - export
grok/skills/export - known-errors
grok/skills/known-errors - lipsync
grok/skills/lipsync - multicam-sync
grok/skills/multicam-sync - music
grok/skills/music - product-help
grok/skills/product-help - shader-gen
grok/skills/shader-gen - talking-head-guide
grok/skills/talking-head-guide - transcription
grok/skills/transcription - verification
grok/skills/verification - video-gen
grok/skills/video-gen - video-translation
grok/skills/video-translation - voice
grok/skills/voice - widget-forms
grok/skills/widget-forms - chatcut-captions-guide
kimi/skills/chatcut-captions-guide - chatcut-connect
kimi/skills/chatcut-connect - chatcut-editing-guide
kimi/skills/chatcut-editing-guide - chatcut-editor-handoff
kimi/skills/chatcut-editor-handoff - chatcut-export-guide
kimi/skills/chatcut-export-guide - chatcut-media-guide
kimi/skills/chatcut-media-guide - chatcut-plugin-basics-kimi-work
kimi/skills/chatcut-plugin-basics-kimi-work - chatcut-verification-guide
kimi/skills/chatcut-verification-guide - create-motion-graphics
kimi/skills/create-motion-graphics - digital-human
kimi/skills/digital-human - known-errors
kimi/skills/known-errors - multicam-sync
kimi/skills/multicam-sync - music
kimi/skills/music - product-help
kimi/skills/product-help - shader-gen
kimi/skills/shader-gen - video-gen
kimi/skills/video-gen - video-translation
kimi/skills/video-translation - voice
kimi/skills/voice
How it works
connect-chatcut-desktop
When your agent uses it
Install, open, connect, or repair ChatCut Desktop when the chatcut_desktop MCP tools are missing or unavailable. Do not use from a managed agent already running inside ChatCut Desktop, or when chatcut_desktop tools are already available.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
1,456 tokensWhen the skill is activated
Reference documents
103,975 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Download
- Install or repair
- User handoff
Scripts executed separately
../../../claude/skills/asset-import/scripts/serve-local-media.mjs../../../claude/skills/asset-import/scripts/upload-media.mjs../../../claude/skills/chatcut-plugin-basics-claude/scripts/mcp-doctor.mjs../../../claude/skills/chatcut-plugin-basics-claude/scripts/mcp-evidence.mjs../../../claude/skills/chatcut-plugin-basics-claude/scripts/mcp-failure.mjs../../../claude/skills/chatcut-plugin-basics-claude/scripts/mcp-wire.mjs../../../claude/skills/multicam-sync/scripts/transcript-offset.mjs../../../claude/skills/visual-analysis/scripts/concat-images.mjs
Files
../../../.claude-plugin/marketplace.jsonasset865 bytesSKILL.mdcore6,563 bytesSKILL.mdcore6,563 bytesSKILL.mdcore6,563 bytesSKILL.mdcore6,563 bytesSKILL.mdcore6,563 bytesSKILL.mdcore6,563 bytesSKILL.mdcore6,563 bytesSKILL.mdcore6,563 bytesagents/openai.yamlasset201 bytes../../../claude/.claude-plugin/plugin.jsonasset1,252 bytes../../../claude/assets/logo-light.pngasset57,172 bytes../../../claude/skills/asset-import/SKILL.mddoc5,862 bytes../../../claude/skills/asset-import/scripts/serve-local-media.mjsruns6,962 bytes../../../claude/skills/asset-import/scripts/upload-media.mjsruns68,448 bytes../../../claude/skills/chatcut-plugin-basics-claude/SKILL.mddoc37,847 bytes../../../claude/skills/chatcut-plugin-basics-claude/references/connection-diagnostics.mddoc25,318 bytes../../../claude/skills/chatcut-plugin-basics-claude/scripts/mcp-doctor.mjsruns65,567 bytes../../../claude/skills/chatcut-plugin-basics-claude/scripts/mcp-evidence.mjsruns23,646 bytes../../../claude/skills/chatcut-plugin-basics-claude/scripts/mcp-failure.mjsruns7,535 bytes../../../claude/skills/chatcut-plugin-basics-claude/scripts/mcp-wire.mjsruns11,027 bytes../../../claude/skills/create-motion-graphics/SKILL.mddoc39,931 bytes../../../claude/skills/create-motion-graphics/references/font-matching.mddoc1,515 bytes../../../claude/skills/create-motion-graphics/references/overlay-composition.mddoc3,520 bytes../../../claude/skills/digital-human/SKILL.mddoc31,050 bytes../../../claude/skills/export/SKILL.mddoc5,942 bytes../../../claude/skills/image-gen/SKILL.mddoc5,719 bytes../../../claude/skills/image-gen/references/gpt-image-2.5.mddoc1,772 bytes../../../claude/skills/image-gen/references/gpt-image-2.mddoc2,252 bytes../../../claude/skills/image-gen/references/nano-banana.mddoc1,724 bytes../../../claude/skills/known-errors/SKILL.mddoc2,571 bytes../../../claude/skills/multicam-sync/SKILL.mddoc16,832 bytes../../../claude/skills/multicam-sync/scripts/transcript-offset.mjsruns8,623 bytes../../../claude/skills/music/SKILL.mddoc4,378 bytes../../../claude/skills/music/references/song.mddoc3,327 bytes../../../claude/skills/product-help/SKILL.mddoc9,803 bytes../../../claude/skills/shader-gen/SKILL.mddoc13,569 bytes../../../claude/skills/shader-gen/examples/cube-rotate.mddoc2,205 bytes../../../claude/skills/shader-gen/examples/door-open.mddoc4,222 bytes../../../claude/skills/shader-gen/examples/page-curl.mddoc4,158 bytes../../../claude/skills/shader-gen/references/design-principles.mddoc12,553 bytes../../../claude/skills/shader-gen/references/property-changes.mddoc4,544 bytes../../../claude/skills/talking-head-guide/SKILL.mddoc25,528 bytes../../../claude/skills/talking-head-guide/references/audio-and-music.mddoc5,679 bytes../../../claude/skills/talking-head-guide/references/b-roll.mddoc6,605 bytes../../../claude/skills/talking-head-guide/references/captions.mddoc5,487 bytes../../../claude/skills/talking-head-guide/references/motion-graphics.mddoc15,959 bytes../../../claude/skills/talking-head-guide/references/multicam.mddoc1,455 bytes../../../claude/skills/talking-head-guide/references/other-a-roll-editing-scenarios.mddoc5,259 bytes../../../claude/skills/transcription/SKILL.mddoc2,729 bytes../../../claude/skills/verification/SKILL.mddoc2,020 bytes../../../claude/skills/video-gen/SKILL.mddoc22,984 bytes../../../claude/skills/video-gen/references/kling.mddoc11,912 bytes../../../claude/skills/video-gen/references/minimax-h3-max.mddoc1,388 bytes../../../claude/skills/video-gen/references/minimax-h3.mddoc1,748 bytes../../../claude/skills/video-gen/references/omni.mddoc6,900 bytes../../../claude/skills/video-gen/references/seedance2.mddoc19,522 bytes../../../claude/skills/video-gen/references/seedance25.mddoc21,272 bytes../../../claude/skills/video-translation/SKILL.mddoc13,393 bytes../../../claude/skills/visual-analysis/SKILL.mddoc6,013 bytes../../../claude/skills/visual-analysis/scripts/concat-images.mjsruns9,231 bytes../../../claude/skills/voice/SKILL.mddoc46,169 bytes../../../claude/skills/voice/references/fix-spoken-mistakes.mddoc5,560 bytes../../../claude/skills/voice/references/video-sync.mddoc8,034 bytes../../../claude/skills/widget-forms/SKILL.mddoc6,734 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubasset-import
When your agent uses it
Import local or downloaded media, or relink missing media to an existing ChatCut asset, through the hosted Claude plugin. Use the editor loopback bridge when the editor and files are on the same machine; use the upload helper for imports otherwise. Desktop MCP sessions use their own built-in import tools.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
1,228 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Same-machine editor import (preferred)
- Relink an existing asset
- Upload-helper fallback
Scripts executed separately
scripts/serve-local-media.mjsscripts/upload-media.mjs
Files
SKILL.mdcore5,862 bytesSKILL.mdcore5,862 bytesSKILL.mdcore5,862 bytesSKILL.mdcore5,862 bytesSKILL.mdcore5,862 bytesscripts/serve-local-media.mjsruns6,962 bytesscripts/upload-media.mjsruns68,448 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubchatcut-plugin-basics-claude
When your agent uses it
Hosted ChatCut plugin only (`chatcut` or `plugin:chatcut:chatcut`). MANDATORY Claude Code prerequisite: invoke this Skill before the first hosted ChatCut MCP tool call and wait for loading. Also invoke when video editing or creation should remain editable in ChatCut, even if the user does not mention ChatCut. Covers project/editor access, local media import, timeline editing, captions, transcription, talking-head cleanup, B-roll, overlays, motion graphics, generation, audio, translation, export, and verification. Use when hosted tools are missing, unavailable, unauthenticated, or fail to connect; includes connection evidence diagnostics. For `chatcut_desktop*`, follow Desktop instructions unless the user explicitly selects the hosted plugin/web surface.
What it loads into context
Frontmatter
165 tokensAlways available to the agent
SKILL.md
7,630 tokensWhen the skill is activated
Reference documents
5,296 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Role
- Your Environment
- Data Model
- Alignment & Execution
- Verify Before Modifying
- Do Only What Was Asked
- How You Think About Editing
- Design Style Consistency
- Project Onboarding And Editor Handoff
- Connector Boundaries
Scripts executed separately
scripts/mcp-doctor.mjsscripts/mcp-evidence.mjsscripts/mcp-failure.mjsscripts/mcp-wire.mjs
Files
../../assets/widget-media/manifest.jsonasset8,056 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesSKILL.mdcore37,847 bytesreferences/connection-diagnostics.mddoc25,318 bytesscripts/mcp-doctor.mjsruns65,567 bytesscripts/mcp-evidence.mjsruns23,646 bytesscripts/mcp-failure.mjsruns7,535 bytesscripts/mcp-wire.mjsruns11,027 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-motion-graphics
When your agent uses it
Use when Codex uses the ChatCut plugin (chatcut MCP server) to add, create, hand-author, patch, or place Motion Graphic JSX assets. Covers reference browsing, direct inline JSX authoring, editable properties, asset binding, timeline placement, and composed verification.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
8,604 tokensWhen the skill is activated
Reference documents
986 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Plugin host and project
- Find MG references before designing
- Core Principles
- Before You Code
- Visual system and placement
- Editable Properties
- Fonts
- Assets and composition
- Design Principles
- Motion Graphic Code Contract
- Renderer CSS Support
- Placement And Review
- Asset And Timeline Flow
- Verification
Files
SKILL.mdcore39,931 bytesSKILL.mdcore39,931 bytesSKILL.mdcore39,931 bytesSKILL.mdcore39,931 bytesSKILL.mdcore39,931 bytesSKILL.mdcore39,931 bytesSKILL.mdcore39,931 bytesreferences/font-matching.mddoc1,515 bytesreferences/overlay-composition.mddoc3,520 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdigital-human
When your agent uses it
Create and manage script- or audio-driven AI avatar videos from an official or saved presenter, an imported portrait, or a representative still prepared from video. Use for 数字人、数字分身、虚拟人、照片开口说话、人像口播、改稿不重拍, AI avatar, AI avatar video, avatar video, talking avatar, talking photo, photo avatar, video avatar, AI presenter, virtual presenter, virtual spokesperson, digital human, or a person's digital twin, including choosing or creating the avatar and deciding its voice, script, aspect ratio, and output quality. Do not use for a static profile-picture avatar, game or 3D character creation, an industrial digital twin, ordinary B-roll, generic image-to-video, video translation, talking-head editing, lip-sync dubbing alone, or TTS-only requests.
What it loads into context
Frontmatter
184 tokensAlways available to the agent
SKILL.md
6,467 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Required Inputs
- Workflow
- Provider Selection
- Consent and Safety
- Verification
- Hard Rules
Files
SKILL.mdcore31,050 bytesSKILL.mdcore31,050 bytesSKILL.mdcore31,050 bytesSKILL.mdcore31,050 bytesSKILL.mdcore31,050 bytesSKILL.mdcore31,050 bytesSKILL.mdcore31,050 bytesSKILL.mdcore31,050 bytesSKILL.mdcore31,050 bytesSKILL.mdcore31,050 bytesSKILL.mdcore31,050 bytesSKILL.mdcore31,050 bytesSKILL.mdcore31,050 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubexport
When your agent uses it
Hosted ChatCut plugin sessions only (the `chatcut` MCP server). If the conversation is driving ChatCut Desktop (a `chatcut_desktop*` MCP server), load this skill only when the user explicitly chooses the plugin/web surface — desktop sessions otherwise ship their own instructions and tools. Export or deliver a ChatCut project through the hosted connector, including video, audio, subtitles, XML, and render-status checks.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,245 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Delivery
- Other Formats
- Cloud Rendering
Files
SKILL.mdcore5,942 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubimage-gen
When your agent uses it
AI image generation and reference-image editing via GPT Image 2.5 Flare/Sunburst, GPT Image 2, and Nano Banana. Use when the user wants to generate or create an image / picture / still through the backend image-generation jobs.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
1,391 tokensWhen the skill is activated
Reference documents
1,346 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Model Selection
- Tool Params
- Defaults
- Ask Before Submit
- Reference Images
- Run
- Rules
Files
SKILL.mdcore5,719 bytesSKILL.mdcore5,719 bytesreferences/gpt-image-2.5.mddoc1,772 bytesreferences/gpt-image-2.mddoc2,252 bytesreferences/nano-banana.mddoc1,724 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubknown-errors
When your agent uses it
Diagnose ChatCut plugin tool failures, rejected mutations, unexpected response shapes, and blocked import, generation, or render operations.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
488 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Mutation Rejections
- Import And Media
- Generation And Motion Graphics
- Verification And Export
Files
SKILL.mdcore2,571 bytesSKILL.mdcore2,571 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmulticam-sync
When your agent uses it
Synchronize footage from a multi-camera / multi-recorder shoot — several cameras plus separate audio recorders covering one session, imported as loose clips — and make a speaker-follow draft by default unless the user explicitly asks for sync only. Use when a user drops in multiple clips from the same recording and wants them aligned, asks for multicam / 多机位 / multi-angle sync, wants a "cut to whoever is talking" edit, or refers to camera A/B, angles, or separate lav or field recordings that need to line up with picture.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
3,731 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Part 1 — Discover the structure
- Part 2 — Align and place
- Part 3 — Identify and label
- Part 4 — Cut to the speaker (default unless sync-only)
Scripts executed separately
scripts/transcript-offset.mjs
Files
SKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesscripts/transcript-offset.mjsruns8,623 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmusic
When your agent uses it
Shared ChatCut entry point for newly generated music, soundtrack, theme music, 配乐, background music, an intro theme, a music bed, BGM, or vocal songs. If vocals are unspecified, ask whether the user wants a vocal song or instrumental music before choosing a generator. Use `submit_music` for either branch, with `generationType` selecting instrumental or song mode.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
985 tokensWhen the skill is activated
Reference documents
745 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Capability Boundary
- Workflow
- Tool Input Shape
- Prompt Shape
- Rules
Files
SKILL.mdcore4,378 bytesreferences/song.mddoc3,327 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubproduct-help
When your agent uses it
Answer current ChatCut product questions using the latest official Docs, Releases, and Changelog. Use for how ChatCut works; UI layout, buttons, and feature instructions; troubleshooting; feature or fix availability on Web, Desktop, or Agent Plugin and minimum version requirements; credits including costs, balance, usage history, validity, or recent charges; plans, subscriptions, renewals, ChatCut Pro, pricing, card or Alipay (支付宝) payments, and billing; Desktop downloads; Agent Plugin installation or updates for Codex and Claude Code; and manual GUI guidance when an action cannot be completed directly. NOT for live project, asset, timeline, or item state; use the matching read tool instead.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
2,091 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Route the question
- Establish the relevant product surface
- Find the smallest useful source
- Decide whether the user must update
- Export location, progress, and stuck exports
- Answering and fallback rules
Files
SKILL.mdcore9,803 bytesSKILL.mdcore9,803 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubshader-gen
When your agent uses it
AI shader generator for WebGL video effects, transitions, masks, and color grading (LUT / 调色 / 电影感 / film look). Use when the user wants a video effect (滤镜 / 特效), a transition (转场 / crossfade / wipe / cube / 3d), a mask (蒙版 / 遮罩 / reveal), a zoom / push-in (推近 / 推镜头), or a color grade — try the built-in effects (zoom, builtin LUTs) before generating a new shader.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
3,010 tokensWhen the skill is activated
Reference documents
6,929 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Catalog-first rule — try existing assets before generation
- Supported Targets
- Type Routing
- Applying an Existing LUT Asset
- Usage
- Strategy
- Editing Existing Properties
- Parameters
- Output
- Applying to Timeline
- Validation & Verification
Files
SKILL.mdcore13,569 bytesSKILL.mdcore13,569 bytesSKILL.mdcore13,569 bytesSKILL.mdcore13,569 bytesSKILL.mdcore13,569 bytesSKILL.mdcore13,569 bytesexamples/cube-rotate.mddoc2,205 bytesexamples/door-open.mddoc4,222 bytesexamples/page-curl.mddoc4,158 bytesreferences/design-principles.mddoc12,553 bytesreferences/property-changes.mddoc4,544 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtalking-head-guide
When your agent uses it
Guide for editing speech-led videos where spoken delivery or conversation drives the cut — single-speaker talking-head / 口播, two- or multi-speaker interview / 访谈, video podcast, lecture, tutorial, course, and similar formats. Load before analyzing, planning, or performing non-trivial edits of those formats, including speech cleanup (剪口播 / 口播剪辑 / 去口癖 / clean up fillers / smooth speech), pause or repeated-take removal, motion graphics layered onto the footage (口播加 MG / 加动画), B-roll (加 B-roll / add B-roll), music, or captions. For motion graphics specifically, use this together with the active Motion Graphics skill/workflow available in the current ChatCut environment — this skill adds speech-specific guidance (rhythm-aware timing, frame-aware placement, subject/caption protection, placement verification).
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
5,410 tokensWhen the skill is activated
Reference documents
8,392 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- What shapes the edit
- Order of execution
- A-roll editing
- MG Overlay
- B-roll
- Multicam (multiple camera angles of the same take)
- Track roles (turn on auto-ducking)
- Background Music
- Captions
Files
SKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesreferences/audio-and-music.mddoc5,679 bytesreferences/b-roll.mddoc6,605 bytesreferences/captions.mddoc5,487 bytesreferences/motion-graphics.mddoc15,959 bytesreferences/multicam.mddoc1,455 bytesreferences/other-a-roll-editing-scenarios.mddoc5,259 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtranscription
When your agent uses it
Hosted ChatCut plugin sessions only (the `chatcut` MCP server). If the conversation is driving ChatCut Desktop (a `chatcut_desktop*` MCP server), load this skill only when the user explicitly chooses the plugin/web surface — desktop sessions otherwise ship their own instructions and tools. Use for ChatCut transcription, transcript readiness, captions, subtitles, transcript repair, filler removal, and speech-led editing setup.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
542 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore2,729 bytesSKILL.mdcore2,729 bytesSKILL.mdcore2,729 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubverification
When your agent uses it
Hosted ChatCut plugin sessions only (the `chatcut` MCP server). If the conversation is driving ChatCut Desktop (a `chatcut_desktop*` MCP server), load this skill only when the user explicitly chooses the plugin/web surface — desktop sessions otherwise ship their own instructions and tools. Verify that ChatCut plugin edits are reflected in project structure and visible timeline output before reporting success.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
385 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore2,020 bytesSKILL.mdcore2,020 bytesSKILL.mdcore2,020 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvideo-gen
When your agent uses it
AI video generation via Seedance, Kling, Gemini Omni, MiniMax H3, and MiniMax H3 Max. Use when the user wants to generate a video clip — text-to-video, image-to-video, first/last-frame transitions, reference-guided generation — or wants to modify / edit / extend an existing generated clip.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
4,880 tokensWhen the skill is activated
Reference documents
13,631 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Models
- Model Selection
- Tool Params
- Input Resolution
- Workflow
- Visual consistency across shots
- Run
- Config Mode
- Rules
Files
SKILL.mdcore22,984 bytesSKILL.mdcore22,984 bytesSKILL.mdcore22,984 bytesSKILL.mdcore22,984 bytesSKILL.mdcore22,984 bytesSKILL.mdcore22,984 bytesSKILL.mdcore22,984 bytesreferences/kling.mddoc11,912 bytesreferences/minimax-h3-max.mddoc1,388 bytesreferences/minimax-h3.mddoc1,748 bytesreferences/omni.mddoc6,900 bytesreferences/seedance2.mddoc19,522 bytesreferences/seedance25.mddoc21,272 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvideo-translation
When your agent uses it
Translate, dub, and localize speech in an existing video while optionally preserving speaker voices, generating translated captions, or synchronizing the speaker's lip movements. Use when the user asks for 视频译制、多语言配音、 把视频里的中文变成英文、让视频里的人说另一种语言、保留原音色、翻译声音、 口型同步、translated video, video dubbing, voice translation, or lip-synced localization, as well as traducción de video, doblaje de video, traducir un video, or sincronización labial. This Skill MUST be loaded before composing treatment choices for an ambiguous video-translation request in any language, including a turn that only asks the user to choose a treatment. Do not use when the user only wants subtitles translated, wants an SRT/VTT file, wants text or a script translated before generating a new avatar video, or wants ordinary TTS with a newly selected voice.
What it loads into context
Frontmatter
209 tokensAlways available to the agent
SKILL.md
2,826 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Authentication and inputs
- When to Use
- Workflow
- Constraints and cost
Files
SKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytesSKILL.mdcore13,393 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvisual-analysis
When your agent uses it
Verify composed ChatCut edits, compare source frames, locate visual changes, and build labeled contact sheets using the hosted plugin's actual frame delivery.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
1,139 tokensWhen the skill is activated
Reference documents
1,228 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Keep coordinates and subjects explicit
- Read the actual delivery
- Narrow a change
- Straightening across shots
- Contact sheets from host-local images
Scripts executed separately
scripts/concat-images.mjs
Files
../asset-import/SKILL.mddoc5,862 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesscripts/concat-images.mjsruns9,231 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvoice
When your agent uses it
Text-to-Speech (TTS), voice cloning, voiceover, narration placement/sync, and custom sound effects (SFX) generator. Use when the user wants generated speech from text, wants to clone a consented voice from uploaded reference audio, wants to correct a misspoken word or short phrase in recorded speech, wants to add/replace/align narration or voiceover for an existing video/timeline, wants to keep existing voiceover synced after visual retiming edits, needs voice audition/selection, or explicitly wants a newly generated/custom sound effect that is not available in the Sound Effects library.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
10,230 tokensWhen the skill is activated
Reference documents
2,885 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- TTS (Text-to-Speech)
- Voice Audition Before Generation
- Custom Voice Cloning
- Sound Effects
- Parameters
- Voices
- Hard rules — what you must NOT do
Files
SKILL.mdcore46,169 bytesSKILL.mdcore46,169 bytesSKILL.mdcore46,169 bytesSKILL.mdcore46,169 bytesSKILL.mdcore46,169 bytesSKILL.mdcore46,169 bytesSKILL.mdcore46,169 bytesSKILL.mdcore46,169 bytesSKILL.mdcore46,169 bytesSKILL.mdcore46,169 bytesSKILL.mdcore46,169 bytesSKILL.mdcore46,169 bytesSKILL.mdcore46,169 bytesreferences/fix-spoken-mistakes.mddoc5,560 bytesreferences/video-sync.mddoc8,034 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwidget-forms
When your agent uses it
Ask for structured ChatCut input using the current plugin host's supported form surface.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
1,483 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Semantic contract mapping
- Codex
- Claude Code
Files
../../assets/widget-media/manifest.jsonasset8,056 bytesSKILL.mdcore6,734 bytesSKILL.mdcore6,734 bytesSKILL.mdcore6,734 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubasset-import
When your agent uses it
Import local or downloaded media, or relink missing media to an existing ChatCut asset, through the hosted Codex plugin. Use the editor loopback bridge when the editor and files are on the same machine; use the upload helper for imports otherwise. Desktop MCP sessions use their own built-in import tools.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
1,251 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Same-machine editor import (preferred)
- Relink an existing asset
- Upload-helper fallback
Scripts executed separately
scripts/serve-local-media.mjsscripts/upload-media.mjs
Files
SKILL.mdcore5,947 bytesSKILL.mdcore5,947 bytesSKILL.mdcore5,947 bytesSKILL.mdcore5,947 bytesSKILL.mdcore5,947 bytesscripts/serve-local-media.mjsruns6,962 bytesscripts/upload-media.mjsruns68,448 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubchatcut-plugin-basics
When your agent uses it
Must read before using the hosted ChatCut plugin in Codex, including creating projects, opening the editor, or editing/creating videos. Also use when ChatCut tools are missing or need authentication. For ChatCut Desktop, follow its own instructions unless the user explicitly chooses the hosted plugin/web surface.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
6,853 tokensWhen the skill is activated
Reference documents
5,296 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Role
- Your Environment
- Data Model
- Alignment & Execution
- Verify Before Modifying
- Do Only What Was Asked
- How You Think About Editing
- Design Style Consistency
- Project Onboarding And Editor Handoff
- Codex Connector Boundaries
Scripts executed separately
scripts/mcp-doctor.mjsscripts/mcp-evidence.mjsscripts/mcp-failure.mjsscripts/mcp-wire.mjs
Files
SKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesSKILL.mdcore34,362 bytesreferences/connection-diagnostics.mddoc25,318 bytesscripts/mcp-doctor.mjsruns65,567 bytesscripts/mcp-evidence.mjsruns23,646 bytesscripts/mcp-failure.mjsruns7,535 bytesscripts/mcp-wire.mjsruns11,027 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-motion-graphics
When your agent uses it
Use when Codex uses the ChatCut plugin (chatcut MCP server) to add, create, hand-author, patch, or place Motion Graphic JSX assets. Covers reference browsing, direct inline JSX authoring, editable properties, asset binding, timeline placement, and composed verification.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
8,604 tokensWhen the skill is activated
Reference documents
986 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Plugin host and project
- Find MG references before designing
- Core Principles
- Before You Code
- Visual system and placement
- Editable Properties
- Fonts
- Assets and composition
- Design Principles
- Motion Graphic Code Contract
- Renderer CSS Support
- Placement And Review
- Asset And Timeline Flow
- Verification
Files
SKILL.mdcore39,931 bytesSKILL.mdcore39,931 bytesSKILL.mdcore39,931 bytesSKILL.mdcore39,931 bytesSKILL.mdcore39,931 bytesSKILL.mdcore39,931 bytesSKILL.mdcore39,931 bytesreferences/font-matching.mddoc1,515 bytesreferences/overlay-composition.mddoc3,520 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdigital-human
When your agent uses it
Create and manage script- or audio-driven AI avatar videos from an official or saved presenter, an imported portrait, or a representative still prepared from video. Use for 数字人、数字分身、虚拟人、照片开口说话、人像口播、改稿不重拍, AI avatar, AI avatar video, avatar video, talking avatar, talking photo, photo avatar, video avatar, AI presenter, virtual presenter, virtual spokesperson, digital human, or a person's digital twin, including choosing or creating the avatar and deciding its voice, script, aspect ratio, and output quality. Do not use for a static profile-picture avatar, game or 3D character creation, an industrial digital twin, ordinary B-roll, generic image-to-video, video translation, talking-head editing, lip-sync dubbing alone, or TTS-only requests.
What it loads into context
Frontmatter
184 tokensAlways available to the agent
SKILL.md
6,467 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Required Inputs
- Workflow
- Provider Selection
- Consent and Safety
- Verification
- Hard Rules
Files
SKILL.mdcore31,051 bytesSKILL.mdcore31,051 bytesSKILL.mdcore31,051 bytesSKILL.mdcore31,051 bytesSKILL.mdcore31,051 bytesSKILL.mdcore31,051 bytesSKILL.mdcore31,051 bytesSKILL.mdcore31,051 bytesSKILL.mdcore31,051 bytesSKILL.mdcore31,051 bytesSKILL.mdcore31,051 bytesSKILL.mdcore31,051 bytesSKILL.mdcore31,051 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubexport
When your agent uses it
Hosted ChatCut plugin sessions only (the `chatcut` MCP server). If the conversation is driving ChatCut Desktop (a `chatcut_desktop*` MCP server), load this skill only when the user explicitly chooses the plugin/web surface — desktop sessions otherwise ship their own instructions and tools. Export or deliver a ChatCut project through the hosted connector, including video, audio, subtitles, XML, and render-status checks.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,245 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Delivery
- Other Formats
- Cloud Rendering
Files
SKILL.mdcore5,942 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubknown-errors
When your agent uses it
Diagnose ChatCut plugin tool failures, rejected mutations, unexpected response shapes, and blocked import, generation, or render operations.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
488 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Mutation Rejections
- Import And Media
- Generation And Motion Graphics
- Verification And Export
Files
SKILL.mdcore2,571 bytesSKILL.mdcore2,571 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmulticam-sync
When your agent uses it
Synchronize footage from a multi-camera / multi-recorder shoot — several cameras plus separate audio recorders covering one session, imported as loose clips — and make a speaker-follow draft by default unless the user explicitly asks for sync only. Use when a user drops in multiple clips from the same recording and wants them aligned, asks for multicam / 多机位 / multi-angle sync, wants a "cut to whoever is talking" edit, or refers to camera A/B, angles, or separate lav or field recordings that need to line up with picture.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
3,731 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Part 1 — Discover the structure
- Part 2 — Align and place
- Part 3 — Identify and label
- Part 4 — Cut to the speaker (default unless sync-only)
Scripts executed separately
scripts/transcript-offset.mjs
Files
SKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesSKILL.mdcore16,832 bytesscripts/transcript-offset.mjsruns8,623 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmusic
When your agent uses it
Shared ChatCut entry point for newly generated music, soundtrack, theme music, 配乐, background music, an intro theme, a music bed, BGM, or vocal songs. If vocals are unspecified, ask whether the user wants a vocal song or instrumental music before choosing a generator. Use `submit_music` for either branch, with `generationType` selecting instrumental or song mode.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
985 tokensWhen the skill is activated
Reference documents
745 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Capability Boundary
- Workflow
- Tool Input Shape
- Prompt Shape
- Rules
Files
SKILL.mdcore4,378 bytesreferences/song.mddoc3,327 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubproduct-help
When your agent uses it
Answer current ChatCut product questions using the latest official Docs, Releases, and Changelog. Use for how ChatCut works; UI layout, buttons, and feature instructions; troubleshooting; feature or fix availability on Web, Desktop, or Agent Plugin and minimum version requirements; credits including costs, balance, usage history, validity, or recent charges; plans, subscriptions, renewals, ChatCut Pro, pricing, card or Alipay (支付宝) payments, and billing; Desktop downloads; Agent Plugin installation or updates for Codex and Claude Code; and manual GUI guidance when an action cannot be completed directly. NOT for live project, asset, timeline, or item state; use the matching read tool instead.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
2,091 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Route the question
- Establish the relevant product surface
- Find the smallest useful source
- Decide whether the user must update
- Export location, progress, and stuck exports
- Answering and fallback rules
Files
SKILL.mdcore9,803 bytesSKILL.mdcore9,803 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubshader-gen
When your agent uses it
AI shader generator for WebGL video effects, transitions, masks, and color grading (LUT / 调色 / 电影感 / film look). Use when the user wants a video effect (滤镜 / 特效), a transition (转场 / crossfade / wipe / cube / 3d), a mask (蒙版 / 遮罩 / reveal), a zoom / push-in (推近 / 推镜头), or a color grade — try the built-in effects (zoom, builtin LUTs) before generating a new shader.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
3,010 tokensWhen the skill is activated
Reference documents
6,929 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Catalog-first rule — try existing assets before generation
- Supported Targets
- Type Routing
- Applying an Existing LUT Asset
- Usage
- Strategy
- Editing Existing Properties
- Parameters
- Output
- Applying to Timeline
- Validation & Verification
Files
SKILL.mdcore13,561 bytesSKILL.mdcore13,561 bytesSKILL.mdcore13,561 bytesSKILL.mdcore13,561 bytesSKILL.mdcore13,561 bytesSKILL.mdcore13,561 bytesexamples/cube-rotate.mddoc2,205 bytesexamples/door-open.mddoc4,222 bytesexamples/page-curl.mddoc4,158 bytesreferences/design-principles.mddoc12,553 bytesreferences/property-changes.mddoc4,544 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtalking-head-guide
When your agent uses it
Guide for editing speech-led videos where spoken delivery or conversation drives the cut — single-speaker talking-head / 口播, two- or multi-speaker interview / 访谈, video podcast, lecture, tutorial, course, and similar formats. Load before analyzing, planning, or performing non-trivial edits of those formats, including speech cleanup (剪口播 / 口播剪辑 / 去口癖 / clean up fillers / smooth speech), pause or repeated-take removal, motion graphics layered onto the footage (口播加 MG / 加动画), B-roll (加 B-roll / add B-roll), music, or captions. For motion graphics specifically, use this together with the active Motion Graphics skill/workflow available in the current ChatCut environment — this skill adds speech-specific guidance (rhythm-aware timing, frame-aware placement, subject/caption protection, placement verification).
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
5,410 tokensWhen the skill is activated
Reference documents
8,392 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- What shapes the edit
- Order of execution
- A-roll editing
- MG Overlay
- B-roll
- Multicam (multiple camera angles of the same take)
- Track roles (turn on auto-ducking)
- Background Music
- Captions
Files
SKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesSKILL.mdcore25,528 bytesreferences/audio-and-music.mddoc5,680 bytesreferences/b-roll.mddoc6,605 bytesreferences/captions.mddoc5,487 bytesreferences/motion-graphics.mddoc15,960 bytesreferences/multicam.mddoc1,455 bytesreferences/other-a-roll-editing-scenarios.mddoc5,259 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtranscription
When your agent uses it
Hosted ChatCut plugin sessions only (the `chatcut` MCP server). If the conversation is driving ChatCut Desktop (a `chatcut_desktop*` MCP server), load this skill only when the user explicitly chooses the plugin/web surface — desktop sessions otherwise ship their own instructions and tools. Use for ChatCut transcription, transcript readiness, captions, subtitles, transcript repair, filler removal, and speech-led editing setup.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
542 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore2,729 bytesSKILL.mdcore2,729 bytesSKILL.mdcore2,729 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubverification
When your agent uses it
Hosted ChatCut plugin sessions only (the `chatcut` MCP server). If the conversation is driving ChatCut Desktop (a `chatcut_desktop*` MCP server), load this skill only when the user explicitly chooses the plugin/web surface — desktop sessions otherwise ship their own instructions and tools. Verify that ChatCut plugin edits are reflected in project structure and visible timeline output before reporting success.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
385 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore2,020 bytesSKILL.mdcore2,020 bytesSKILL.mdcore2,020 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvideo-gen
When your agent uses it
AI video generation via Seedance, Kling, Gemini Omni, MiniMax H3, and MiniMax H3 Max. Use when the user wants to generate a video clip — text-to-video, image-to-video, first/last-frame transitions, reference-guided generation — or wants to modify / edit / extend an existing generated clip.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
4,880 tokensWhen the skill is activated
Reference documents
13,631 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Models
- Model Selection
- Tool Params
- Input Resolution
- Workflow
- Visual consistency across shots
- Run
- Config Mode
- Rules
Files
SKILL.mdcore22,985 bytesSKILL.mdcore22,985 bytesSKILL.mdcore22,985 bytesSKILL.mdcore22,985 bytesSKILL.mdcore22,985 bytesSKILL.mdcore22,985 bytesSKILL.mdcore22,985 bytesreferences/kling.mddoc11,910 bytesreferences/minimax-h3-max.mddoc1,388 bytesreferences/minimax-h3.mddoc1,748 bytesreferences/omni.mddoc6,900 bytesreferences/seedance2.mddoc19,522 bytesreferences/seedance25.mddoc21,272 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvideo-translation
When your agent uses it
Translate, dub, and localize speech in an existing video while optionally preserving speaker voices, generating translated captions, or synchronizing the speaker's lip movements. Use when the user asks for 视频译制、多语言配音、 把视频里的中文变成英文、让视频里的人说另一种语言、保留原音色、翻译声音、 口型同步、translated video, video dubbing, voice translation, or lip-synced localization, as well as traducción de video, doblaje de video, traducir un video, or sincronización labial. This Skill MUST be loaded before composing treatment choices for an ambiguous video-translation request in any language, including a turn that only asks the user to choose a treatment. Do not use when the user only wants subtitles translated, wants an SRT/VTT file, wants text or a script translated before generating a new avatar video, or wants ordinary TTS with a newly selected voice.
What it loads into context
Frontmatter
209 tokensAlways available to the agent
SKILL.md
2,754 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Workflow
- Constraints and cost
Files
SKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytesSKILL.mdcore13,008 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvisual-analysis
When your agent uses it
Verify composed ChatCut edits, compare source frames, locate visual changes, and build labeled contact sheets using the hosted plugin's actual frame delivery.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
1,139 tokensWhen the skill is activated
Reference documents
1,251 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Keep coordinates and subjects explicit
- Read the actual delivery
- Narrow a change
- Straightening across shots
- Contact sheets from host-local images
Scripts executed separately
scripts/concat-images.mjs
Files
../asset-import/SKILL.mddoc5,947 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesSKILL.mdcore6,013 bytesscripts/concat-images.mjsruns9,231 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvoice
When your agent uses it
Text-to-Speech (TTS), voice cloning, voiceover, narration placement/sync, and custom sound effects (SFX) generator. Use when the user wants generated speech from text, wants to clone a consented voice from uploaded reference audio, wants to correct a misspoken word or short phrase in recorded speech, wants to add/replace/align narration or voiceover for an existing video/timeline, wants to keep existing voiceover synced after visual retiming edits, needs voice audition/selection, or explicitly wants a newly generated/custom sound effect that is not available in the Sound Effects library.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
10,230 tokensWhen the skill is activated
Reference documents
2,885 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- TTS (Text-to-Speech)
- Voice Audition Before Generation
- Custom Voice Cloning
- Sound Effects
- Parameters
- Voices
- Hard rules — what you must NOT do
Files
SKILL.mdcore46,167 bytesSKILL.mdcore46,167 bytesSKILL.mdcore46,167 bytesSKILL.mdcore46,167 bytesSKILL.mdcore46,167 bytesSKILL.mdcore46,167 bytesSKILL.mdcore46,167 bytesSKILL.mdcore46,167 bytesSKILL.mdcore46,167 bytesSKILL.mdcore46,167 bytesSKILL.mdcore46,167 bytesSKILL.mdcore46,167 bytesSKILL.mdcore46,167 bytesreferences/fix-spoken-mistakes.mddoc5,560 bytesreferences/video-sync.mddoc8,034 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwidget-forms
When your agent uses it
Ask for structured ChatCut input using the current plugin host's supported form surface.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
1,483 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Semantic contract mapping
- Codex
- Claude Code
Files
SKILL.mdcore6,734 bytesSKILL.mdcore6,734 bytesSKILL.mdcore6,734 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubasset-import
When your agent uses it
Hosted ChatCut plugin sessions only (the `chatcut` MCP server). Import local or downloaded media, or relink missing media to an existing ChatCut asset. Use the editor loopback bridge when the editor and files are on the same machine; use the upload helper otherwise. Desktop sessions use their own built-in import tools.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
1,699 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Same-machine editor import (preferred)
- Relink an existing asset
- Upload-helper fallback
- Download an existing source
Scripts executed separately
scripts/serve-local-media.mjsscripts/upload-media.mjs
Files
SKILL.mdcore8,057 bytesSKILL.mdcore8,057 bytesSKILL.mdcore8,057 bytesSKILL.mdcore8,057 bytesSKILL.mdcore8,057 bytesSKILL.mdcore8,057 bytesSKILL.mdcore8,057 bytesscripts/serve-local-media.mjsruns6,110 bytesscripts/upload-media.mjsruns68,458 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubchatcut-plugin-basics
When your agent uses it
Must read before using the hosted ChatCut plugin in Grok Bot, including creating projects, opening the editor, or editing/creating videos. Also use when ChatCut tools are missing or need authentication. For ChatCut Desktop, follow its own instructions unless the user explicitly chooses the hosted plugin/web surface.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
5,439 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Role
- Your Environment
- Data Model
- Alignment & Execution
- Verify Before Modifying
- Do Only What Was Asked
- How You Think About Editing
- Design Style Consistency
- Project Onboarding And Editor Handoff
- Connector Boundaries
Files
SKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytesSKILL.mdcore27,540 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-motion-graphics
When your agent uses it
Use whenever Grok Bot needs to add, create, hand-author, patch, or place Motion Graphic JSX assets in a ChatCut project. Covers direct inline JSX authoring, visual language, editable properties, asset binding, timeline placement, and verification.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
8,923 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Principles
- Before You Code
- Align With The User
- Project Visual Language
- Visual System And Placement
- Editable Properties
- Fonts
- Assets
- Design Principles
- Motion Graphic Code Contract
- Renderer CSS Support
- Placement And Review
- Asset And Timeline Flow
- Verification
Files
SKILL.mdcore41,631 bytesSKILL.mdcore41,631 bytesSKILL.mdcore41,631 bytesSKILL.mdcore41,631 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdigital-human
When your agent uses it
Create and manage script- or audio-driven AI avatar videos from an official or saved presenter, an imported portrait, or a representative still prepared from video. Use for 数字人、数字分身、虚拟人、照片开口说话、人像口播、改稿不重拍, AI avatar, AI avatar video, avatar video, talking avatar, talking photo, photo avatar, video avatar, AI presenter, virtual presenter, virtual spokesperson, digital human, or a person's digital twin, including choosing or creating the avatar and deciding its voice, script, aspect ratio, and output quality. Do not use for a static profile-picture avatar, game or 3D character creation, an industrial digital twin, ordinary B-roll, generic image-to-video, video translation, talking-head editing, lip-sync dubbing alone, or TTS-only requests.
What it loads into context
Frontmatter
178 tokensAlways available to the agent
SKILL.md
5,603 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Required Inputs
- Workflow
- Provider Selection
- Consent and Safety
- Verification
- Hard Rules
Files
SKILL.mdcore27,483 bytesSKILL.mdcore27,483 bytesSKILL.mdcore27,483 bytesSKILL.mdcore27,483 bytesSKILL.mdcore27,483 bytesSKILL.mdcore27,483 bytesSKILL.mdcore27,483 bytesSKILL.mdcore27,483 bytesSKILL.mdcore27,483 bytesSKILL.mdcore27,483 bytesSKILL.mdcore27,483 bytesSKILL.mdcore27,483 bytesSKILL.mdcore27,483 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubexport
When your agent uses it
Hosted ChatCut plugin sessions only (the `chatcut` MCP server). If the conversation is driving ChatCut Desktop (a `chatcut_desktop*` MCP server), load this skill only when the user explicitly chooses the plugin/web surface — desktop sessions otherwise ship their own instructions and tools. Export or deliver a ChatCut project through the hosted connector, including video, audio, subtitles, XML, and render-status checks.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
868 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore4,165 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubknown-errors
When your agent uses it
Diagnose ChatCut plugin tool failures, rejected mutations, unexpected response shapes, and blocked import, generation, or render operations.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
458 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Mutation Rejections
- Import And Media
- Generation And Motion Graphics
- Verification And Export
Files
SKILL.mdcore2,431 bytesSKILL.mdcore2,431 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHublipsync
When your agent uses it
Synchronize mouths in an existing video to supplied final speech audio, only when the user explicitly wants mouth movements changed to match that audio. Replacing dialogue alone does not imply lip sync; use voice for new dialogue with unchanged picture. Does not translate, clone voices, generate speech, or create a new avatar performance. Integrated lip-synced translation uses video-translation; independently generated audio uses this skill only when mouth synchronization is requested.
What it loads into context
Frontmatter
107 tokensAlways available to the agent
SKILL.md
1,181 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope and input roles
- Prepare, submit and inspect
- Recover the affected stage
Files
SKILL.mdcore6,012 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmulticam-sync
When your agent uses it
Synchronize footage from a multi-camera / multi-recorder shoot — several cameras plus separate audio recorders covering one session, imported as loose clips — and make a speaker-follow draft by default unless the user explicitly asks for sync only. Use when a user drops in multiple clips from the same recording and wants them aligned, asks for multicam / 多机位 / multi-angle sync, wants a "cut to whoever is talking" edit, or refers to camera A/B, angles, or separate lav or field recordings that need to line up with picture.
What it loads into context
Frontmatter
118 tokensAlways available to the agent
SKILL.md
3,691 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Part 1 — Discover the structure
- Part 2 — Align and place
- Part 3 — Identify and label
- Part 4 — Cut to the speaker (default unless sync-only)
Scripts executed separately
scripts/transcript-offset.mjs
Files
SKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesSKILL.mdcore16,668 bytesscripts/transcript-offset.mjsruns8,623 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmusic
When your agent uses it
Shared ChatCut entry point for newly generated music, soundtrack, theme music, 配乐, background music, an intro theme, a music bed, BGM, or vocal songs. If vocals are unspecified, ask whether the user wants a vocal song or instrumental music before choosing a generator. Use `submit_music` for either branch, with `generationType` selecting instrumental or song mode.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
947 tokensWhen the skill is activated
Reference documents
714 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Capability Boundary
- Workflow
- Tool Input Shape
- Prompt Shape
- Rules
Files
SKILL.mdcore4,222 bytesreferences/song.mddoc3,192 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubproduct-help
When your agent uses it
Answer current ChatCut product questions using the latest official Docs, Releases, and Changelog. Use for how ChatCut works; UI layout, buttons, and feature instructions; troubleshooting; feature or fix availability on Web, Desktop, or Agent Plugin and minimum version requirements; credits including costs, balance, usage history, validity, or recent charges; plans, subscriptions, renewals, ChatCut Pro, pricing, card or Alipay (支付宝) payments, and billing; Desktop downloads; Agent Plugin installation or updates for supported hosts, including Grok Bot and Cursor; and manual GUI guidance when an action cannot be completed directly. NOT for live project, asset, timeline, or item state; use the matching read tool instead.
What it loads into context
Frontmatter
151 tokensAlways available to the agent
SKILL.md
1,517 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Route the question
- Establish the relevant product surface
- Find the smallest useful source
- Decide whether the user must update
- Answering and fallback rules
Files
SKILL.mdcore7,360 bytesSKILL.mdcore7,360 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubshader-gen
When your agent uses it
AI shader generator for WebGL video effects, transitions, masks, and color grading (LUT / 调色 / 电影感 / film look). Use when the user wants a video effect (滤镜 / 特效), a transition (转场 / crossfade / wipe / cube / 3d), a mask (蒙版 / 遮罩 / reveal), a zoom / push-in (推近 / 推镜头), or a color grade — try the built-in effects (zoom, builtin LUTs) before generating a new shader.
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
2,988 tokensWhen the skill is activated
Reference documents
6,929 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Catalog-first rule — try existing assets before generation
- Supported Targets
- Type Routing
- Applying an Existing LUT Asset
- Usage
- Strategy
- Editing Existing Properties
- Parameters
- Output
- Applying to Timeline
- Validation & Verification
Files
SKILL.mdcore13,489 bytesSKILL.mdcore13,489 bytesSKILL.mdcore13,489 bytesSKILL.mdcore13,489 bytesSKILL.mdcore13,489 bytesSKILL.mdcore13,489 bytesexamples/cube-rotate.mddoc2,205 bytesexamples/door-open.mddoc4,222 bytesexamples/page-curl.mddoc4,158 bytesreferences/design-principles.mddoc12,553 bytesreferences/property-changes.mddoc4,544 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtalking-head-guide
When your agent uses it
Guide for editing speech-led videos where spoken delivery or conversation drives the cut — single-speaker talking-head / 口播, two- or multi-speaker interview / 访谈, video podcast, lecture, tutorial, course, and similar formats. Use for any non-trivial edit of those formats, including speech cleanup (剪口播 / 口播剪辑 / 去口癖 / clean up fillers / smooth speech), pause or repeated-take removal, motion graphics layered onto the footage (口播加 MG / 加动画), B-roll (加 B-roll / add B-roll), music, or captions. For motion graphics specifically, use this together with the active Motion Graphics skill/workflow available in the current ChatCut environment — this skill adds speech-specific guidance (rhythm-aware timing, frame-aware placement, subject/caption protection, placement verification).
What it loads into context
Frontmatter
181 tokensAlways available to the agent
SKILL.md
5,153 tokensWhen the skill is activated
Reference documents
8,300 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this skill covers
- What shapes the edit
- Order of execution
- A-roll editing
- MG Overlay
- B-roll
- Multicam (multiple camera angles of the same take)
- Track roles (turn on auto-ducking)
- Background Music
- Captions
Files
SKILL.mdcore24,274 bytesSKILL.mdcore24,274 bytesSKILL.mdcore24,274 bytesSKILL.mdcore24,274 bytesSKILL.mdcore24,274 bytesSKILL.mdcore24,274 bytesSKILL.mdcore24,274 bytesSKILL.mdcore24,274 bytesSKILL.mdcore24,274 bytesreferences/audio-and-music.mddoc5,680 bytesreferences/b-roll.mddoc6,520 bytesreferences/captions.mddoc5,303 bytesreferences/motion-graphics.mddoc15,968 bytesreferences/multicam.mddoc1,356 bytesreferences/other-a-roll-editing-scenarios.mddoc5,259 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtranscription
When your agent uses it
Hosted ChatCut plugin sessions only (the `chatcut` MCP server). If the conversation is driving ChatCut Desktop (a `chatcut_desktop*` MCP server), load this skill only when the user explicitly chooses the plugin/web surface — desktop sessions otherwise ship their own instructions and tools. Use for ChatCut transcription, transcript readiness, captions, subtitles, transcript repair, filler removal, and speech-led editing setup.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
542 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore2,729 bytesSKILL.mdcore2,729 bytesSKILL.mdcore2,729 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubverification
When your agent uses it
Hosted ChatCut plugin sessions only (the `chatcut` MCP server). If the conversation is driving ChatCut Desktop (a `chatcut_desktop*` MCP server), load this skill only when the user explicitly chooses the plugin/web surface — desktop sessions otherwise ship their own instructions and tools. Verify that ChatCut plugin edits are reflected in project structure and visible timeline output before reporting success.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
387 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore2,045 bytesSKILL.mdcore2,045 bytesSKILL.mdcore2,045 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvideo-gen
When your agent uses it
AI video generation via Seedance, Kling, Gemini Omni, MiniMax H3, and MiniMax H3 Max. Use when the user wants to generate a video clip — text-to-video, image-to-video, first/last-frame transitions, reference-guided generation — or wants to modify / edit / extend an existing generated clip.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
4,854 tokensWhen the skill is activated
Reference documents
15,208 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Models
- Model Selection
- Tool Params
- Input Resolution
- Workflow
- Visual consistency across shots
- Run
- Config Mode
- Rules
Files
../asset-import/SKILL.mddoc8,057 bytesSKILL.mdcore22,856 bytesSKILL.mdcore22,856 bytesSKILL.mdcore22,856 bytesSKILL.mdcore22,856 bytesSKILL.mdcore22,856 bytesSKILL.mdcore22,856 bytesSKILL.mdcore22,856 bytesreferences/kling.mddoc11,775 bytesreferences/minimax-h3-max.mddoc1,388 bytesreferences/minimax-h3.mddoc1,748 bytesreferences/omni.mddoc6,765 bytesreferences/seedance2.mddoc19,370 bytesreferences/seedance25.mddoc21,137 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvideo-translation
When your agent uses it
Translate, dub, and localize speech in an existing video while optionally preserving speaker voices, generating translated captions, or synchronizing the speaker's lip movements. Use when the user asks for 视频译制、多语言配音、 把视频里的中文变成英文、让视频里的人说另一种语言、保留原音色、翻译声音、 口型同步、translated video, video dubbing, voice translation, or lip-synced localization, as well as traducción de video, doblaje de video, traducir un video, or sincronización labial. This Skill MUST be loaded before composing treatment choices for an ambiguous video-translation request in any language, including a turn that only asks the user to choose a treatment. Do not use when the user only wants subtitles translated, wants an SRT/VTT file, wants text or a script translated before generating a new avatar video, or wants ordinary TTS with a newly selected voice.
What it loads into context
Frontmatter
203 tokensAlways available to the agent
SKILL.md
2,691 tokensWhen the skill is activated
Reference documents
2,567 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Workflow
- Constraints and cost
- Prepare the processing source
Files
../asset-import/SKILL.mddoc8,057 bytes../export/SKILL.mddoc4,165 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytesSKILL.mdcore12,915 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvoice
When your agent uses it
Text-to-Speech (TTS), voice cloning, voiceover, narration placement/sync, and custom sound effects (SFX) generator. Use when the user wants generated speech from text, wants to clone a consented voice from uploaded reference audio, wants to correct a misspoken word or short phrase in recorded speech, wants to add/replace/align narration or voiceover for an existing video/timeline, wants to keep existing voiceover synced after visual retiming edits, needs voice audition/selection, or explicitly wants a newly generated/custom sound effect that is not available in the Sound Effects library.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
8,566 tokensWhen the skill is activated
Reference documents
4,608 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- TTS (Text-to-Speech)
- Voice Audition Before Generation
- Custom Voice Cloning
- Sound Effects
- Parameters
- Voices
- Hard rules — what you must NOT do
Files
../asset-import/SKILL.mddoc8,057 bytesSKILL.mdcore38,886 bytesSKILL.mdcore38,886 bytesSKILL.mdcore38,886 bytesSKILL.mdcore38,886 bytesSKILL.mdcore38,886 bytesSKILL.mdcore38,886 bytesSKILL.mdcore38,886 bytesSKILL.mdcore38,886 bytesSKILL.mdcore38,886 bytesSKILL.mdcore38,886 bytesSKILL.mdcore38,886 bytesSKILL.mdcore38,886 bytesreferences/fix-spoken-mistakes.mddoc5,670 bytesreferences/video-sync.mddoc8,034 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwidget-forms
When your agent uses it
Adapt ChatCut questions and previews to the media and interaction surfaces that Grok Bot reliably supports.
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
616 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Stable visual-preview path
- Text questions and choices
- Audio and video restrictions
Files
SKILL.mdcore3,139 bytesSKILL.mdcore3,139 bytesSKILL.mdcore3,139 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubchatcut-captions-guide
When your agent uses it
Use when the user asks for transcription, captions, subtitles, bilingual subtitles, filler-word removal, or pause cleanup in ChatCut.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
203 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
Files
SKILL.mdcore970 bytesSKILL.mdcore970 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubchatcut-connect
When your agent uses it
Connect to ChatCut via MCP, ensure authentication, list projects, and report them with clean editor links. Use when the user asks to connect ChatCut, list ChatCut projects, authenticate ChatCut MCP, or any combination like "连接 ChatCut 并列出我的项目". Delegates editor opening to the chatcut-editor-handoff skill.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
582 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Never
Files
SKILL.mdcore2,577 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubchatcut-editing-guide
When your agent uses it
Use when the user wants to edit an existing video or build a simple editable timeline in ChatCut. Teaches the standard project, timeline, edit, and review workflow.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
282 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Standard workflow
- Common requests
Files
SKILL.mdcore1,326 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubchatcut-editor-handoff
When your agent uses it
Open a ChatCut project editor in the Kimi Work in-app browser with automatic login, keep one editor tab per session, and show only clean links to the user. Use whenever a ChatCut tool result carries browserHandoff, when the user says "用内置浏览器打开" a ChatCut project, or before long-running visible editing work.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
757 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to open
- How to open
- After opening
- Link hygiene (always)
Files
SKILL.mdcore3,307 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubchatcut-export-guide
When your agent uses it
Use when the user asks to render, export, download, share, or deliver a ChatCut project.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
153 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
Files
SKILL.mdcore724 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubchatcut-media-guide
When your agent uses it
Use when the user needs to import local or downloaded media, or relink missing media to an existing ChatCut asset. Prefer the editor loopback bridge when the editor and files are on the same machine.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
911 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Same-machine editor import
- Relink an existing asset
- Fallback
Scripts executed separately
scripts/serve-local-media.mjs
Files
SKILL.mdcore4,180 bytesSKILL.mdcore4,180 bytesSKILL.mdcore4,180 bytesscripts/serve-local-media.mjsruns6,110 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubchatcut-plugin-basics-kimi-work
When your agent uses it
MANDATORY Kimi Work prerequisite for any conversation that may use the ChatCut MCP server: invoke this Skill before the first ChatCut MCP tool call and wait for it to finish loading. Also invoke it whenever video editing or creation should remain editable in ChatCut, even if the user does not mention ChatCut. Covers project creation and targeting, timeline editing, captions, subtitles, transcription, editor opening, verification, and identifying the active ChatCut project or editor URL.
What it loads into context
Frontmatter
107 tokensAlways available to the agent
SKILL.md
1,515 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- MCP surface
- Your environment
- Editor handoff (Kimi Work mechanics)
- Role and alignment
- Talking to the user
- Boundaries
Files
SKILL.mdcore7,120 bytesSKILL.mdcore7,120 bytesSKILL.mdcore7,120 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubchatcut-verification-guide
When your agent uses it
Use after ChatCut edits, imports, captions, generation, or exports when the user needs confidence that the result is correct.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
173 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Checks
Files
SKILL.mdcore877 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcreate-motion-graphics
When your agent uses it
Use when Kimi Work uses the ChatCut plugin (chatcut MCP server) to add, create, hand-author, patch, or place Motion Graphic JSX assets. Covers reference browsing, direct inline JSX authoring, editable properties, asset binding, timeline placement, and composed verification.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
8,475 tokensWhen the skill is activated
Reference documents
986 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Plugin host and project
- Find MG references before designing
- Core Principles
- Before You Code
- Visual system and placement
- Editable Properties
- Fonts
- Assets and composition
- Design Principles
- Motion Graphic Code Contract
- Renderer CSS Support
- Placement And Review
- Asset And Timeline Flow
- Verification
Files
SKILL.mdcore39,358 bytesSKILL.mdcore39,358 bytesSKILL.mdcore39,358 bytesSKILL.mdcore39,358 bytesSKILL.mdcore39,358 bytesSKILL.mdcore39,358 bytesSKILL.mdcore39,358 bytesreferences/font-matching.mddoc1,515 bytesreferences/overlay-composition.mddoc3,520 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdigital-human
When your agent uses it
Create and manage script- or audio-driven AI avatar videos from an official or saved presenter, an imported portrait, or a representative still prepared from video. Use for 数字人、数字分身、虚拟人、照片开口说话、人像口播、改稿不重拍, AI avatar, AI avatar video, avatar video, talking avatar, talking photo, photo avatar, video avatar, AI presenter, virtual presenter, virtual spokesperson, digital human, or a person's digital twin, including choosing or creating the avatar and deciding its voice, script, aspect ratio, and output quality. Do not use for a static profile-picture avatar, game or 3D character creation, an industrial digital twin, ordinary B-roll, generic image-to-video, video translation, talking-head editing, lip-sync dubbing alone, or TTS-only requests.
What it loads into context
Frontmatter
178 tokensAlways available to the agent
SKILL.md
6,249 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Required Inputs
- Workflow
- Provider Selection
- Consent and Safety
- Verification
- Hard Rules
Files
SKILL.mdcore30,156 bytesSKILL.mdcore30,156 bytesSKILL.mdcore30,156 bytesSKILL.mdcore30,156 bytesSKILL.mdcore30,156 bytesSKILL.mdcore30,156 bytesSKILL.mdcore30,156 bytesSKILL.mdcore30,156 bytesSKILL.mdcore30,156 bytesSKILL.mdcore30,156 bytesSKILL.mdcore30,156 bytesSKILL.mdcore30,156 bytesSKILL.mdcore30,156 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubknown-errors
When your agent uses it
Diagnose ChatCut plugin tool failures, rejected mutations, unexpected response shapes, and blocked import, generation, or render operations.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
463 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Mutation Rejections
- Import And Media
- Generation And Motion Graphics
- Verification And Export
Files
SKILL.mdcore2,424 bytesSKILL.mdcore2,424 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmulticam-sync
When your agent uses it
Synchronize footage from a multi-camera / multi-recorder shoot — several cameras plus separate audio recorders covering one session, imported as loose clips — and make a speaker-follow draft by default unless the user explicitly asks for sync only. Use when a user drops in multiple clips from the same recording and wants them aligned, asks for multicam / 多机位 / multi-angle sync, wants a "cut to whoever is talking" edit, or refers to camera A/B, angles, or separate lav or field recordings that need to line up with picture.
What it loads into context
Frontmatter
118 tokensAlways available to the agent
SKILL.md
3,692 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Part 1 — Discover the structure
- Part 2 — Align and place
- Part 3 — Identify and label
- Part 4 — Cut to the speaker (default unless sync-only)
Scripts executed separately
scripts/transcript-offset.mjs
Files
SKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesSKILL.mdcore16,675 bytesscripts/transcript-offset.mjsruns8,623 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmusic
When your agent uses it
Shared ChatCut entry point for newly generated music, soundtrack, theme music, 配乐, background music, an intro theme, a music bed, BGM, or vocal songs. If vocals are unspecified, ask whether the user wants a vocal song or instrumental music before choosing a generator. Use `submit_music` for either branch, with `generationType` selecting instrumental or song mode.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
947 tokensWhen the skill is activated
Reference documents
714 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Capability Boundary
- Workflow
- Tool Input Shape
- Prompt Shape
- Rules
Files
SKILL.mdcore4,222 bytesreferences/song.mddoc3,192 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubproduct-help
When your agent uses it
Answer current ChatCut product questions using the latest official Docs, Releases, and Changelog. Use for how ChatCut works; UI layout, buttons, and feature instructions; troubleshooting; feature or fix availability on Web, Desktop, or Agent Plugin and minimum version requirements; credits including costs, balance, usage history, validity, or recent charges; plans, subscriptions, renewals, ChatCut Pro, pricing, card or Alipay (支付宝) payments, and billing; Desktop downloads; Agent Plugin installation or updates, including Kimi Work; and manual GUI guidance when an action cannot be completed directly. NOT for live project, asset, timeline, or item state; use the matching read tool instead.
What it loads into context
Frontmatter
146 tokensAlways available to the agent
SKILL.md
1,512 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Route the question
- Establish the relevant product surface
- Find the smallest useful source
- Decide whether the user must update
- Answering and fallback rules
Files
SKILL.mdcore7,330 bytesSKILL.mdcore7,330 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubshader-gen
When your agent uses it
AI shader generator for WebGL video effects, transitions, masks, and color grading (LUT / 调色 / 电影感 / film look). Use when the user wants a video effect (滤镜 / 特效), a transition (转场 / crossfade / wipe / cube / 3d), a mask (蒙版 / 遮罩 / reveal), a zoom / push-in (推近 / 推镜头), or a color grade — try the built-in effects (zoom, builtin LUTs) before generating a new shader.
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
2,971 tokensWhen the skill is activated
Reference documents
6,929 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Catalog-first rule — try existing assets before generation
- Supported Targets
- Type Routing
- Applying an Existing LUT Asset
- Usage
- Strategy
- Editing Existing Properties
- Parameters
- Output
- Applying to Timeline
- Validation & Verification
Files
SKILL.mdcore13,394 bytesSKILL.mdcore13,394 bytesSKILL.mdcore13,394 bytesSKILL.mdcore13,394 bytesSKILL.mdcore13,394 bytesSKILL.mdcore13,394 bytesexamples/cube-rotate.mddoc2,205 bytesexamples/door-open.mddoc4,222 bytesexamples/page-curl.mddoc4,158 bytesreferences/design-principles.mddoc12,553 bytesreferences/property-changes.mddoc4,544 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvideo-gen
When your agent uses it
AI video generation via Seedance, Kling, Gemini Omni, MiniMax H3, and MiniMax H3 Max. Use when the user wants to generate a video clip — text-to-video, image-to-video, first/last-frame transitions, reference-guided generation — or wants to modify / edit / extend an existing generated clip.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
4,852 tokensWhen the skill is activated
Reference documents
13,493 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Models
- Model Selection
- Tool Params
- Input Resolution
- Workflow
- Visual consistency across shots
- Run
- Config Mode
- Rules
Files
SKILL.mdcore22,873 bytesSKILL.mdcore22,873 bytesSKILL.mdcore22,873 bytesSKILL.mdcore22,873 bytesSKILL.mdcore22,873 bytesSKILL.mdcore22,873 bytesSKILL.mdcore22,873 bytesreferences/kling.mddoc11,775 bytesreferences/minimax-h3-max.mddoc1,388 bytesreferences/minimax-h3.mddoc1,748 bytesreferences/omni.mddoc6,765 bytesreferences/seedance2.mddoc19,315 bytesreferences/seedance25.mddoc21,137 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvideo-translation
When your agent uses it
Translate, dub, and localize speech in an existing video while optionally preserving speaker voices, generating translated captions, or synchronizing the speaker's lip movements. Use when the user asks for 视频译制、多语言配音、 把视频里的中文变成英文、让视频里的人说另一种语言、保留原音色、翻译声音、 口型同步、translated video, video dubbing, voice translation, or lip-synced localization, as well as traducción de video, doblaje de video, traducir un video, or sincronización labial. This Skill MUST be loaded before composing treatment choices for an ambiguous video-translation request in any language, including a turn that only asks the user to choose a treatment. Do not use when the user only wants subtitles translated, wants an SRT/VTT file, wants text or a script translated before generating a new avatar video, or wants ordinary TTS with a newly selected voice.
What it loads into context
Frontmatter
203 tokensAlways available to the agent
SKILL.md
2,699 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Workflow
- Constraints and cost
Files
SKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytesSKILL.mdcore12,828 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvoice
When your agent uses it
Text-to-Speech (TTS), voice cloning, voiceover, narration placement/sync, and custom sound effects (SFX) generator. Use when the user wants generated speech from text, wants to clone a consented voice from uploaded reference audio, wants to correct a misspoken word or short phrase in recorded speech, wants to add/replace/align narration or voiceover for an existing video/timeline, wants to keep existing voiceover synced after visual retiming edits, needs voice audition/selection, or explicitly wants a newly generated/custom sound effect that is not available in the Sound Effects library.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
9,820 tokensWhen the skill is activated
Reference documents
2,885 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- TTS (Text-to-Speech)
- Voice Audition Before Generation
- Custom Voice Cloning
- Sound Effects
- Parameters
- Voices
- Hard rules — what you must NOT do
Files
SKILL.mdcore44,546 bytesSKILL.mdcore44,546 bytesSKILL.mdcore44,546 bytesSKILL.mdcore44,546 bytesSKILL.mdcore44,546 bytesSKILL.mdcore44,546 bytesSKILL.mdcore44,546 bytesSKILL.mdcore44,546 bytesSKILL.mdcore44,546 bytesSKILL.mdcore44,546 bytesSKILL.mdcore44,546 bytesSKILL.mdcore44,546 bytesreferences/fix-spoken-mistakes.mddoc5,560 bytesreferences/video-sync.mddoc8,034 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- connect-chatcut-desktop
- asset-import
- chatcut-plugin-basics-claude
- create-motion-graphics
- digital-human
- export
- image-gen
- known-errors
- multicam-sync
- music
- product-help
- shader-gen
- talking-head-guide
- transcription
- verification
- video-gen
- video-translation
- visual-analysis
- voice
- widget-forms
- asset-import
- chatcut-plugin-basics
- create-motion-graphics
- digital-human
- export
- known-errors
- multicam-sync
- music
- product-help
- shader-gen
- talking-head-guide
- transcription
- verification
- video-gen
- video-translation
- visual-analysis
- voice
- widget-forms
- asset-import
- chatcut-plugin-basics
- create-motion-graphics
- digital-human
- export
- known-errors
- lipsync
- multicam-sync
- music
- product-help
- shader-gen
- talking-head-guide
- transcription
- verification
- video-gen
- video-translation
- voice
- widget-forms
- chatcut-captions-guide
- chatcut-connect
- chatcut-editing-guide
- chatcut-editor-handoff
- chatcut-export-guide
- chatcut-media-guide
- chatcut-plugin-basics-kimi-work
- chatcut-verification-guide
- create-motion-graphics
- digital-human
- known-errors
- multicam-sync
- music
- product-help
- shader-gen
- video-gen
- video-translation
- voice
Repository facts
- License
- Apache-2.0
- Created
- Jun 25, 2026
- Last pushed
- Nov 5, 2026
- Forks
- 84
- Open issues
- 4
- Project activity
- Active
Rank over the last 12 weeks
Now #885 · best #640 · down 161 in 30 days
- #870 on Oct 30
- #873 on Oct 31
- #869 on Nov 1
- #876 on Nov 2
- #884 on Nov 3
- #885 since Nov 4
73 earlier periods
- #665 on Aug 2
- #654 on Aug 7
- #651 on Aug 8
- #658 on Aug 9
- #679 on Aug 10
- #686 on Aug 11
- #681 on Aug 12
- #675 on Aug 13
- #673 on Aug 14
- #648 on Aug 15
- #665 on Aug 16
- #673 on Aug 17
- #690 on Aug 18
- #668 on Aug 19
- #670 from Aug 20 to Aug 21
- #640 on Aug 22
- #670 on Aug 23
- #686 on Aug 24
- #685 on Aug 25
- #669 on Aug 26
- #679 on Aug 27
- #652 from Aug 29 to Aug 30
- #684 on Aug 31
- #695 on Sep 1
- #686 on Sep 2
- #689 on Sep 3
- #667 on Sep 4
- #658 on Sep 5
- #676 on Sep 6
- #691 on Sep 7
- #714 on Sep 8
- #697 on Sep 9
- #699 on Sep 10
- #682 on Sep 11
- #684 from Sep 12 to Sep 13
- #705 on Sep 14
- #691 on Sep 15
- #704 on Sep 16
- #708 on Sep 17
- #696 on Sep 18
- #669 on Sep 19
- #685 on Sep 20
- #701 on Sep 21
- #720 on Sep 22
- #686 on Sep 24
- #671 on Sep 25
- #669 on Sep 26
- #701 on Sep 27
- #707 on Sep 28
- #744 on Sep 29
- #722 on Sep 30
- #681 on Oct 1
- #692 on Oct 2
- #673 on Oct 3
- #706 on Oct 4
- #724 on Oct 6
- #773 on Oct 8
- #740 on Oct 9
- #723 on Oct 10
- #739 on Oct 12
- #743 on Oct 13
- #754 on Oct 14
- #748 on Oct 15
- #752 on Oct 16
- #731 on Oct 17
- #761 on Oct 19
- #764 on Oct 20
- #774 on Oct 21
- #755 on Oct 22
- #758 on Oct 23
- #723 on Oct 24
- #866 on Oct 25
- #867 from Oct 28 to Oct 29
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 488 notes
chatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedchatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedchatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedchatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedchatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedchatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedchatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude/skills/asset-import/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude/skills/asset-import/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude/skills/asset-import/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude/skills/asset-import/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude/skills/chatcut-plugin-basics-claude/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude/skills/chatcut-plugin-basics-claude/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude/skills/chatcut-plugin-basics-claude/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude/skills/chatcut-plugin-basics-claude/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude/skills/chatcut-plugin-basics-claude/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude/skills/chatcut-plugin-basics-claude/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude/skills/chatcut-plugin-basics-claude/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude/skills/chatcut-plugin-basics-claude/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedclaude/skills/chatcut-plugin-basics-claude/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 195 network referencesin 32 files: claude/skills/shader-gen/examples/page-curl.md:1 claude/skills/product-help/SKILL.md:11 claude/.claude-plugin/plugin.json:7 and 29 more
- No hidden or obfuscated text
- No instruction overrides
- 29 executable scriptsin 21 files: claude/skills/asset-import/scripts/serve-local-media.mjs:1 claude/skills/asset-import/scripts/upload-media.mjs:1 claude/skills/chatcut-plugin-basics-claude/scripts/mcp-doctor.mjs:1 and 18 more
- 3 references to secretsin 2 files: claude/skills/chatcut-plugin-basics-claude/scripts/mcp-doctor.mjs:92 chatcut-plugin-basics/scripts/mcp-doctor.mjs:92
- No requests to vote in Hot
Show all 227 signals by file
.claude-plugin/marketplace.json
- Network accessline 4
"name": "ChatCut", "email": "dev@chatcut.io", "url": "https://chatcut.io" - Network accessline 5
"email": "dev@chatcut.io", "url": "https://chatcut.io" }, - Network accessline 6
"url": "https://chatcut.io" - Network accessline 15
"description": "Edit and create videos in ChatCut from Claude Code: import media, edit timelines, captions, motion graphics, generation, export.", "category": "productivity", "homepage": "https://chatcut.io", - Network accessline 16
"category": "productivity", "homepage": "https://chatcut.io", "author": { - Network accessline 17
"homepage": "https://chatcut.io", - Network accessline 19
"name": "ChatCut", "email": "dev@chatcut.io", "url": "https://chatcut.io" - Network accessline 20
"email": "dev@chatcut.io", "url": "https://chatcut.io" }, - Network accessline 21
"url": "https://chatcut.io"
chatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md
claude/.claude-plugin/plugin.json
- Network accessline 7
"name": "ChatCut", "email": "dev@chatcut.io", "url": "https://chatcut.io" - Network accessline 8
"email": "dev@chatcut.io", "url": "https://chatcut.io" }, - Network accessline 9
"url": "https://chatcut.io" - Network accessline 10
}, "homepage": "https://chatcut.io", "icon": "./assets/logo-light.png", - Network accessline 11
"homepage": "https://chatcut.io", - Network accessline 12
"icon": "./assets/logo-light.png", "documentationUrl": "https://chatcut.io/claude", "supportUrl": "https://chatcut.io/contact", - Network accessline 13
"documentationUrl": "https://chatcut.io/claude", - Network accessline 14
"supportUrl": "https://chatcut.io/contact", - Network accessline 15
"privacyPolicyUrl": "https://chatcut.io/privacy", - Network accessline 16
"termsOfServiceUrl": "https://chatcut.io/terms", - Network accessline 17
"repository": "https://github.com/ChatCut-Inc/agent-plugin.git", - Network accessline 33
"chatcut": { "type": "http", "url": "https://api.chatcut.io/api/external-mcp/mcp", - Network accessline 34
"type": "http", "url": "https://api.chatcut.io/api/external-mcp/mcp", "oauth_resource": "https://api.chatcut.io/api/external-mcp/mcp", - Network accessline 35
"url": "https://api.chatcut.io/api/external-mcp/mcp", - Network accessline 36
"oauth_resource": "https://api.chatcut.io/api/external-mcp/mcp",
claude/assets/widget-media/manifest.json
- Network accessline 1
{ "baseUrl": "https://cdn.jsdelivr.net/gh/ChatCut-Inc/chatcut-widget-media@bb7529532b2f97922f980d38251772370ac9d68f/widget-media/", - Network accessline 1
{ "baseUrl": "https://cdn.jsdelivr.net/gh/ChatCut-Inc/chatcut-widget-media@bb7529532b2f97922f980d38251772370ac9d68f/widget-media/", - Network accessline 2
"baseUrl": "https://cdn.jsdelivr.net/gh/ChatCut-Inc/chatcut-widget-media@bb7529532b2f97922f980d38251772370ac9d68f/widget-media/", - Network accessline 2
"baseUrl": "https://cdn.jsdelivr.net/gh/ChatCut-Inc/chatcut-widget-media@bb7529532b2f97922f980d38251772370ac9d68f/widget-media/",
claude/skills/asset-import/scripts/serve-local-media.mjs
- Executable scriptline 1
#!/usr/bin/env node - Executable scriptline 1
#!/usr/bin/env node - Network accessline 43
let port = 0; // 0 = ephemeral let ttlSeconds = 900; let origin = "https://app.chatcut.io"; - Network accessline 43
let port = 0; // 0 = ephemeral let ttlSeconds = 900; let origin = "https://app.chatcut.io"; - Network accessline 44
let ttlSeconds = 900; let origin = "https://app.chatcut.io"; const paths = []; - Network accessline 44
let ttlSeconds = 900; let origin = "https://app.chatcut.io"; const paths = []; - Network accessline 45
let origin = "https://app.chatcut.io"; - Network accessline 45
let origin = "https://app.chatcut.io"; - Network accessline 179
server.listen(port, "127.0.0.1", () => { const addr = server.address(); const base = `http://127.0.0.1:${addr.port}/${routePrefix}`; - Network accessline 179
server.listen(port, "127.0.0.1", () => { const addr = server.address(); const base = `http://127.0.0.1:${addr.port}/${routePrefix}`; - Network accessline 180
const addr = server.address(); const base = `http://127.0.0.1:${addr.port}/${routePrefix}`; const out = { - Network accessline 180
const addr = server.address(); const base = `http://127.0.0.1:${addr.port}/${routePrefix}`; const out = { - Network accessline 181
const base = `http://127.0.0.1:${addr.port}/${routePrefix}`; - Network accessline 181
const base = `http://127.0.0.1:${addr.port}/${routePrefix}`;
claude/skills/asset-import/scripts/upload-media.mjs
- Executable scriptline 1
#!/usr/bin/env node - Executable scriptline 1
#!/usr/bin/env node - Network accessline 120
); try { return await fetch(url, { ...init, signal: controller.signal }); - Network accessline 120
); try { return await fetch(url, { ...init, signal: controller.signal }); - Network accessline 121
try { return await fetch(url, { ...init, signal: controller.signal }); } catch (error) { - Network accessline 121
try { return await fetch(url, { ...init, signal: controller.signal }); } catch (error) { - Network accessline 122
return await fetch(url, { ...init, signal: controller.signal }); - Network accessline 122
return await fetch(url, { ...init, signal: controller.signal });
claude/skills/chatcut-plugin-basics-claude/SKILL.md
- Network accessline 40
claude mcp add-json --scope user chatcut '{"type":"http","url":"https://api.chatcut.io/api/external-mcp/mcp","oauth_resource":"https://api.chatcut.io/api/external-mcp/mcp","headers":{"x-chatcut-mcp-client":"claude_code","x-chatcut-mcp-surfa - Network accessline 40
claude mcp add-json --scope user chatcut '{"type":"http","url":"https://api.chatcut.io/api/external-mcp/mcp","oauth_resource":"https://api.chatcut.io/api/external-mcp/mcp","headers":{"x-chatcut-mcp-client":"claude_code","x-chatcut-mcp-surfa - Network accessline 279
For raw source-frame inspection, use the local source file directly with host-native tools such as `ffmpeg` when the file is available. If the agent has the original path, including an import-helper `sourcePath`, do not call remote ChatCut - Network accessline 279
For raw source-frame inspection, use the local source file directly with host-native tools such as `ffmpeg` when the file is available. If the agent has the original path, including an import-helper `sourcePath`, do not call remote ChatCut
claude/skills/chatcut-plugin-basics-claude/references/connection-diagnostics.md
- Network accessline 60
"source": "host_settings", "serverName": "chatcut", "url": "https://api.chatcut.io/api/external-mcp/mcp", - Network accessline 60
"source": "host_settings", "serverName": "chatcut", "url": "https://api.chatcut.io/api/external-mcp/mcp", - Network accessline 61
"serverName": "chatcut", "url": "https://api.chatcut.io/api/external-mcp/mcp", "enabled": true - Network accessline 61
"serverName": "chatcut", "url": "https://api.chatcut.io/api/external-mcp/mcp", "enabled": true - Network accessline 62
"url": "https://api.chatcut.io/api/external-mcp/mcp", - Network accessline 62
"url": "https://api.chatcut.io/api/external-mcp/mcp",
claude/skills/chatcut-plugin-basics-claude/scripts/mcp-doctor.mjs
claude/skills/chatcut-plugin-basics-claude/scripts/mcp-evidence.mjs
claude/skills/chatcut-plugin-basics-claude/scripts/mcp-failure.mjs
claude/skills/chatcut-plugin-basics-claude/scripts/mcp-wire.mjs
claude/skills/image-gen/references/gpt-image-2.5.md
claude/skills/multicam-sync/scripts/transcript-offset.mjs
claude/skills/product-help/SKILL.md
- Network accessline 11
For a ChatCut product question, the first substantive action is to search the exact topic within `https://chatcut.io/docs` and open the most relevant official - Network accessline 11
For a ChatCut product question, the first substantive action is to search the exact topic within `https://chatcut.io/docs` and open the most relevant official - Network accessline 12
exact topic within `https://chatcut.io/docs` and open the most relevant official - Network accessline 12
exact topic within `https://chatcut.io/docs` and open the most relevant official - Network accessline 64
3. For ordinary usage questions, start with the owning feature or troubleshooting page. For availability, regression, update, or version questions, directly open `https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelo - Network accessline 64
3. For ordinary usage questions, start with the owning feature or troubleshooting page. For availability, regression, update, or version questions, directly open `https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelo - Network accessline 65
page. For availability, regression, update, or version questions, directly open `https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelog`, then open the matching Changelog entry. - Network accessline 65
page. For availability, regression, update, or version questions, directly open `https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelog`, then open the matching Changelog entry. - Network accessline 66
`https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelog`, then - Network accessline 66
`https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelog`, then - Network accessline 68
4. For one user question, issue at most two search queries total: the exact topic, then one narrower query if needed. After that, stop searching and use `https://chatcut.io/docs/llms.txt` only as an index, then open the target page. - Network accessline 68
4. For one user question, issue at most two search queries total: the exact topic, then one narrower query if needed. After that, stop searching and use `https://chatcut.io/docs/llms.txt` only as an index, then open the target page. - Network accessline 69
then one narrower query if needed. After that, stop searching and use `https://chatcut.io/docs/llms.txt` only as an index, then open the target page. If the canonical pages and index are unavailable or still do not identify a - Network accessline 69
then one narrower query if needed. After that, stop searching and use `https://chatcut.io/docs/llms.txt` only as an index, then open the target page. If the canonical pages and index are unavailable or still do not identify a - Network accessline 70
`https://chatcut.io/docs/llms.txt` only as an index, then open the target page. - Network accessline 70
`https://chatcut.io/docs/llms.txt` only as an index, then open the target page.
claude/skills/shader-gen/examples/page-curl.md
- Network accessline 1
--- tags: 3d, page, curl, flip, turn, book, peel description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. - Network accessline 1
--- tags: 3d, page, curl, flip, turn, book, peel description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. - Network accessline 2
tags: 3d, page, curl, flip, turn, book, peel description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. complexity: high - Network accessline 2
tags: 3d, page, curl, flip, turn, book, peel description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. complexity: high - Network accessline 3
description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. - Network accessline 3
description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. - Network accessline 7
# Page Curl Transition - Network accessline 7
# Page Curl Transition - Network accessline 13
- **Camera distance from FOV**: `dist = 1 / Math.tan(fovRad / 2)` ensures the plane (height=2) exactly fills the viewport vertically. No hardcoded camera z. - **Radius proportional to page width**: `radius = W * 0.08` scales with aspect rat - Network accessline 13
- **Camera distance from FOV**: `dist = 1 / Math.tan(fovRad / 2)` ensures the plane (height=2) exactly fills the viewport vertically. No hardcoded camera z. - **Radius proportional to page width**: `radius = W * 0.08` scales with aspect rat - Network accessline 14
- **Radius proportional to page width**: `radius = W * 0.08` scales with aspect ratio, preventing the curl from being too tight on wide videos or too loose on tall ones. - Network accessline 14
- **Radius proportional to page width**: `radius = W * 0.08` scales with aspect ratio, preventing the curl from being too tight on wide videos or too loose on tall ones. - Network accessline 15
- **Fold sweeps left→right**: `foldX = -W/2 + eased * (W + radius * PI)`. At progress=0 fold is at left edge (nothing curled), at progress=1 it's past the right edge (fully curled away). - **UV-based position reconstruction**: Original posi - Network accessline 15
- **Fold sweeps left→right**: `foldX = -W/2 + eased * (W + radius * PI)`. At progress=0 fold is at left edge (nothing curled), at progress=1 it's past the right edge (fully curled away). - **UV-based position reconstruction**: Original posi - Network accessline 16
- **UV-based position reconstruction**: Original positions are derived from UVs each frame (`ox = uv.getX(i) * W - W/2`), since the position buffer gets overwritten. UVs are immutable. - **Three curl zones**: (1) `ox <= foldX` → flat, not y - Network accessline 16
- **UV-based position reconstruction**: Original positions are derived from UVs each frame (`ox = uv.getX(i) * W - W/2`), since the position buffer gets overwritten. UVs are immutable. - **Three curl zones**: (1) `ox <= foldX` → flat, not y - Network accessline 17
- **Three curl zones**: (1) `ox <= foldX` → flat, not yet reached. (2) `ox > foldX, angle <= PI` → wrapping around cylinder. (3) `angle > PI` → past 180°, extends flat at z=2\*radius back toward -x (folded-back page visible on top). - Network accessline 17
- **Three curl zones**: (1) `ox <= foldX` → flat, not yet reached. (2) `ox > foldX, angle <= PI` → wrapping around cylinder. (3) `angle > PI` → past 180°, extends flat at z=2\*radius back toward -x (folded-back page visible on top).
claude/skills/video-gen/references/kling.md
- Network accessline 175
| Emotion | Combine 3+ of | | ------- | ------------------------------------------------------------------------------------ | | Sad | eyes glisten, lower lip trembl - Network accessline 175
| Emotion | Combine 3+ of | | ------- | ------------------------------------------------------------------------------------ | | Sad | eyes glisten, lower lip trembl - Network accessline 176
| ------- | ------------------------------------------------------------------------------------ | | Sad | eyes glisten, lower lip trembles, breath becomes shallow, fingers curl loosely | | Scared | pupils contract, breath catche - Network accessline 176
| ------- | ------------------------------------------------------------------------------------ | | Sad | eyes glisten, lower lip trembles, breath becomes shallow, fingers curl loosely | | Scared | pupils contract, breath catche - Network accessline 177
| Sad | eyes glisten, lower lip trembles, breath becomes shallow, fingers curl loosely | - Network accessline 177
| Sad | eyes glisten, lower lip trembles, breath becomes shallow, fingers curl loosely |
claude/skills/video-gen/references/omni.md
- Network accessline 95
Sources checked 2026-08-30: [Google announcement](https://blog.google/innovation-and-ai/technology/developers-tools/build-with-gemini-omni-1-1-flash/), [Vertex model](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gem - Network accessline 95
Sources checked 2026-08-30: [Google announcement](https://blog.google/innovation-and-ai/technology/developers-tools/build-with-gemini-omni-1-1-flash/), [Vertex model](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gem
claude/skills/visual-analysis/scripts/concat-images.mjs
codex/skills/asset-import/scripts/serve-local-media.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 43
let port = 0; // 0 = ephemeral let ttlSeconds = 900; let origin = "https://app.chatcut.io"; - Network accessline 44
let ttlSeconds = 900; let origin = "https://app.chatcut.io"; const paths = []; - Network accessline 45
let origin = "https://app.chatcut.io"; - Network accessline 179
server.listen(port, "127.0.0.1", () => { const addr = server.address(); const base = `http://127.0.0.1:${addr.port}/${routePrefix}`; - Network accessline 180
const addr = server.address(); const base = `http://127.0.0.1:${addr.port}/${routePrefix}`; const out = { - Network accessline 181
const base = `http://127.0.0.1:${addr.port}/${routePrefix}`;
codex/skills/asset-import/scripts/upload-media.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 120
); try { return await fetch(url, { ...init, signal: controller.signal }); - Network accessline 121
try { return await fetch(url, { ...init, signal: controller.signal }); } catch (error) { - Network accessline 122
return await fetch(url, { ...init, signal: controller.signal });
codex/skills/chatcut-plugin-basics/SKILL.md
- Network accessline 40
codex mcp add chatcut --url https://api.chatcut.io/api/external-mcp/mcp --oauth-resource https://api.chatcut.io/api/external-mcp/mcp - Network accessline 266
For raw source-frame inspection, use the local source file directly with Codex-native tools such as `ffmpeg` when the file is available. If Codex has the original path, including an import-helper `sourcePath`, do not call remote ChatCut too
codex/skills/chatcut-plugin-basics/references/connection-diagnostics.md
- Network accessline 60
"source": "host_settings", "serverName": "chatcut", "url": "https://api.chatcut.io/api/external-mcp/mcp", - Network accessline 61
"serverName": "chatcut", "url": "https://api.chatcut.io/api/external-mcp/mcp", "enabled": true - Network accessline 62
"url": "https://api.chatcut.io/api/external-mcp/mcp",
codex/skills/chatcut-plugin-basics/scripts/mcp-doctor.mjs
codex/skills/chatcut-plugin-basics/scripts/mcp-evidence.mjs
- Executable scriptline 1
Executable file
codex/skills/chatcut-plugin-basics/scripts/mcp-failure.mjs
- Executable scriptline 1
Executable file
codex/skills/chatcut-plugin-basics/scripts/mcp-wire.mjs
- Executable scriptline 1
Executable file
codex/skills/multicam-sync/scripts/transcript-offset.mjs
- Executable scriptline 1
#!/usr/bin/env node
codex/skills/product-help/SKILL.md
- Network accessline 11
For a ChatCut product question, the first substantive action is to search the exact topic within `https://chatcut.io/docs` and open the most relevant official - Network accessline 12
exact topic within `https://chatcut.io/docs` and open the most relevant official - Network accessline 64
3. For ordinary usage questions, start with the owning feature or troubleshooting page. For availability, regression, update, or version questions, directly open `https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelo - Network accessline 65
page. For availability, regression, update, or version questions, directly open `https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelog`, then open the matching Changelog entry. - Network accessline 66
`https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelog`, then - Network accessline 68
4. For one user question, issue at most two search queries total: the exact topic, then one narrower query if needed. After that, stop searching and use `https://chatcut.io/docs/llms.txt` only as an index, then open the target page. - Network accessline 69
then one narrower query if needed. After that, stop searching and use `https://chatcut.io/docs/llms.txt` only as an index, then open the target page. If the canonical pages and index are unavailable or still do not identify a - Network accessline 70
`https://chatcut.io/docs/llms.txt` only as an index, then open the target page.
codex/skills/shader-gen/examples/page-curl.md
- Network accessline 1
--- tags: 3d, page, curl, flip, turn, book, peel description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. - Network accessline 2
tags: 3d, page, curl, flip, turn, book, peel description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. complexity: high - Network accessline 3
description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. - Network accessline 7
# Page Curl Transition - Network accessline 13
- **Camera distance from FOV**: `dist = 1 / Math.tan(fovRad / 2)` ensures the plane (height=2) exactly fills the viewport vertically. No hardcoded camera z. - **Radius proportional to page width**: `radius = W * 0.08` scales with aspect rat - Network accessline 14
- **Radius proportional to page width**: `radius = W * 0.08` scales with aspect ratio, preventing the curl from being too tight on wide videos or too loose on tall ones. - Network accessline 15
- **Fold sweeps left→right**: `foldX = -W/2 + eased * (W + radius * PI)`. At progress=0 fold is at left edge (nothing curled), at progress=1 it's past the right edge (fully curled away). - **UV-based position reconstruction**: Original posi - Network accessline 16
- **UV-based position reconstruction**: Original positions are derived from UVs each frame (`ox = uv.getX(i) * W - W/2`), since the position buffer gets overwritten. UVs are immutable. - **Three curl zones**: (1) `ox <= foldX` → flat, not y - Network accessline 17
- **Three curl zones**: (1) `ox <= foldX` → flat, not yet reached. (2) `ox > foldX, angle <= PI` → wrapping around cylinder. (3) `angle > PI` → past 180°, extends flat at z=2\*radius back toward -x (folded-back page visible on top).
codex/skills/video-gen/references/kling.md
- Network accessline 175
| Emotion | Combine 3+ of | | ------- | ------------------------------------------------------------------------------------ | | Sad | eyes glisten, lower lip trembl - Network accessline 176
| ------- | ------------------------------------------------------------------------------------ | | Sad | eyes glisten, lower lip trembles, breath becomes shallow, fingers curl loosely | | Scared | pupils contract, breath catche - Network accessline 177
| Sad | eyes glisten, lower lip trembles, breath becomes shallow, fingers curl loosely |
codex/skills/video-gen/references/omni.md
- Network accessline 95
Sources checked 2026-08-30: [Google announcement](https://blog.google/innovation-and-ai/technology/developers-tools/build-with-gemini-omni-1-1-flash/), [Vertex model](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gem
codex/skills/visual-analysis/scripts/concat-images.mjs
- Executable scriptline 1
#!/usr/bin/env node
grok/skills/asset-import/scripts/serve-local-media.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 28
let port = 0; let ttlSeconds = 900; let origin = "https://app.chatcut.io"; - Network accessline 29
let ttlSeconds = 900; let origin = "https://app.chatcut.io"; const paths = []; - Network accessline 30
let origin = "https://app.chatcut.io"; - Network accessline 163
server.listen(port, "127.0.0.1", () => { const address = server.address(); const base = `http://127.0.0.1:${address.port}/${routePrefix}`; - Network accessline 164
const address = server.address(); const base = `http://127.0.0.1:${address.port}/${routePrefix}`; console.log( - Network accessline 165
const base = `http://127.0.0.1:${address.port}/${routePrefix}`;
grok/skills/asset-import/scripts/upload-media.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 120
); try { return await fetch(url, { ...init, signal: controller.signal }); - Network accessline 121
try { return await fetch(url, { ...init, signal: controller.signal }); } catch (error) { - Network accessline 122
return await fetch(url, { ...init, signal: controller.signal });
grok/skills/multicam-sync/scripts/transcript-offset.mjs
- Executable scriptline 1
#!/usr/bin/env node
grok/skills/product-help/SKILL.md
- Network accessline 8
For a ChatCut product question, the first substantive action is to search the exact topic within `https://chatcut.io/docs` and open the most relevant official - Network accessline 9
exact topic within `https://chatcut.io/docs` and open the most relevant official - Network accessline 58
3. For ordinary usage questions, start with the owning feature or troubleshooting page. For availability, regression, update, or version questions, directly open `https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelo - Network accessline 59
page. For availability, regression, update, or version questions, directly open `https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelog`, then open the matching Changelog entry. - Network accessline 60
`https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelog`, then - Network accessline 62
4. For one user question, issue at most two search queries total: the exact topic, then one narrower query if needed. After that, stop searching and use `https://chatcut.io/docs/llms.txt` only as an index, then open the target page. - Network accessline 63
then one narrower query if needed. After that, stop searching and use `https://chatcut.io/docs/llms.txt` only as an index, then open the target page. If the canonical pages and index are unavailable or still do not identify a - Network accessline 64
`https://chatcut.io/docs/llms.txt` only as an index, then open the target page.
grok/skills/shader-gen/examples/page-curl.md
- Network accessline 1
--- tags: 3d, page, curl, flip, turn, book, peel description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. - Network accessline 2
tags: 3d, page, curl, flip, turn, book, peel description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. complexity: high - Network accessline 3
description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. - Network accessline 7
# Page Curl Transition - Network accessline 13
- **Camera distance from FOV**: `dist = 1 / Math.tan(fovRad / 2)` ensures the plane (height=2) exactly fills the viewport vertically. No hardcoded camera z. - **Radius proportional to page width**: `radius = W * 0.08` scales with aspect rat - Network accessline 14
- **Radius proportional to page width**: `radius = W * 0.08` scales with aspect ratio, preventing the curl from being too tight on wide videos or too loose on tall ones. - Network accessline 15
- **Fold sweeps left→right**: `foldX = -W/2 + eased * (W + radius * PI)`. At progress=0 fold is at left edge (nothing curled), at progress=1 it's past the right edge (fully curled away). - **UV-based position reconstruction**: Original posi - Network accessline 16
- **UV-based position reconstruction**: Original positions are derived from UVs each frame (`ox = uv.getX(i) * W - W/2`), since the position buffer gets overwritten. UVs are immutable. - **Three curl zones**: (1) `ox <= foldX` → flat, not y - Network accessline 17
- **Three curl zones**: (1) `ox <= foldX` → flat, not yet reached. (2) `ox > foldX, angle <= PI` → wrapping around cylinder. (3) `angle > PI` → past 180°, extends flat at z=2\*radius back toward -x (folded-back page visible on top).
grok/skills/video-gen/references/kling.md
- Network accessline 173
| Emotion | Combine 3+ of | | ------- | ------------------------------------------------------------------------------------ | | Sad | eyes glisten, lower lip trembl - Network accessline 174
| ------- | ------------------------------------------------------------------------------------ | | Sad | eyes glisten, lower lip trembles, breath becomes shallow, fingers curl loosely | | Scared | pupils contract, breath catche - Network accessline 175
| Sad | eyes glisten, lower lip trembles, breath becomes shallow, fingers curl loosely |
grok/skills/video-gen/references/omni.md
- Network accessline 93
Sources checked 2026-08-30: [Google announcement](https://blog.google/innovation-and-ai/technology/developers-tools/build-with-gemini-omni-1-1-flash/), [Vertex model](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gem
kimi/skills/chatcut-media-guide/scripts/serve-local-media.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 28
let port = 0; let ttlSeconds = 900; let origin = "https://app.chatcut.io"; - Network accessline 29
let ttlSeconds = 900; let origin = "https://app.chatcut.io"; const paths = []; - Network accessline 30
let origin = "https://app.chatcut.io"; - Network accessline 163
server.listen(port, "127.0.0.1", () => { const address = server.address(); const base = `http://127.0.0.1:${address.port}/${routePrefix}`; - Network accessline 164
const address = server.address(); const base = `http://127.0.0.1:${address.port}/${routePrefix}`; console.log( - Network accessline 165
const base = `http://127.0.0.1:${address.port}/${routePrefix}`;
kimi/skills/multicam-sync/scripts/transcript-offset.mjs
- Executable scriptline 1
#!/usr/bin/env node
kimi/skills/product-help/SKILL.md
- Network accessline 8
For a ChatCut product question, the first substantive action is to search the exact topic within `https://chatcut.io/docs` and open the most relevant official - Network accessline 9
exact topic within `https://chatcut.io/docs` and open the most relevant official - Network accessline 58
3. For ordinary usage questions, start with the owning feature or troubleshooting page. For availability, regression, update, or version questions, directly open `https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelo - Network accessline 59
page. For availability, regression, update, or version questions, directly open `https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelog`, then open the matching Changelog entry. - Network accessline 60
`https://chatcut.io/docs/releases` and `https://chatcut.io/docs/changelog`, then - Network accessline 62
4. For one user question, issue at most two search queries total: the exact topic, then one narrower query if needed. After that, stop searching and use `https://chatcut.io/docs/llms.txt` only as an index, then open the target page. - Network accessline 63
then one narrower query if needed. After that, stop searching and use `https://chatcut.io/docs/llms.txt` only as an index, then open the target page. If the canonical pages and index are unavailable or still do not identify a - Network accessline 64
`https://chatcut.io/docs/llms.txt` only as an index, then open the target page.
kimi/skills/shader-gen/examples/page-curl.md
- Network accessline 1
--- tags: 3d, page, curl, flip, turn, book, peel description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. - Network accessline 2
tags: 3d, page, curl, flip, turn, book, peel description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. complexity: high - Network accessline 3
description: Page curl transition — outgoing page curls away from left to right, revealing incoming underneath. - Network accessline 7
# Page Curl Transition - Network accessline 13
- **Camera distance from FOV**: `dist = 1 / Math.tan(fovRad / 2)` ensures the plane (height=2) exactly fills the viewport vertically. No hardcoded camera z. - **Radius proportional to page width**: `radius = W * 0.08` scales with aspect rat - Network accessline 14
- **Radius proportional to page width**: `radius = W * 0.08` scales with aspect ratio, preventing the curl from being too tight on wide videos or too loose on tall ones. - Network accessline 15
- **Fold sweeps left→right**: `foldX = -W/2 + eased * (W + radius * PI)`. At progress=0 fold is at left edge (nothing curled), at progress=1 it's past the right edge (fully curled away). - **UV-based position reconstruction**: Original posi - Network accessline 16
- **UV-based position reconstruction**: Original positions are derived from UVs each frame (`ox = uv.getX(i) * W - W/2`), since the position buffer gets overwritten. UVs are immutable. - **Three curl zones**: (1) `ox <= foldX` → flat, not y - Network accessline 17
- **Three curl zones**: (1) `ox <= foldX` → flat, not yet reached. (2) `ox > foldX, angle <= PI` → wrapping around cylinder. (3) `angle > PI` → past 180°, extends flat at z=2\*radius back toward -x (folded-back page visible on top).
kimi/skills/video-gen/references/kling.md
- Network accessline 173
| Emotion | Combine 3+ of | | ------- | ------------------------------------------------------------------------------------ | | Sad | eyes glisten, lower lip trembl - Network accessline 174
| ------- | ------------------------------------------------------------------------------------ | | Sad | eyes glisten, lower lip trembles, breath becomes shallow, fingers curl loosely | | Scared | pupils contract, breath catche - Network accessline 175
| Sad | eyes glisten, lower lip trembles, breath becomes shallow, fingers curl loosely |
kimi/skills/video-gen/references/omni.md
- Network accessline 93
Sources checked 2026-08-30: [Google announcement](https://blog.google/innovation-and-ai/technology/developers-tools/build-with-gemini-omni-1-1-flash/), [Vertex model](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gem
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 199 facts
- Network access in prose of the SKILL.mdconnect-chatcut-desktop/SKILL.md:21Low confidence
- Network access in prose of the SKILL.mdconnect-chatcut-desktop/SKILL.md:22Low confidence
- Network access in prose of the SKILL.mdconnect-chatcut-desktop/SKILL.md:23Low confidence
- Executable script in code of a file that runsclaude/skills/asset-import/scripts/serve-local-media.mjs:1High confidence
- Executable script in code of a file that runsasset-import/scripts/serve-local-media.mjs:1High confidence
- Network access in code of a file that runsclaude/skills/asset-import/scripts/serve-local-media.mjs:43High confidence
- Network access in code of a file that runsasset-import/scripts/serve-local-media.mjs:43High confidence
- Network access in code of a file that runsclaude/skills/asset-import/scripts/serve-local-media.mjs:44High confidence
- Network access in code of a file that runsasset-import/scripts/serve-local-media.mjs:44High confidence
- Network access in code of a file that runsclaude/skills/asset-import/scripts/serve-local-media.mjs:45High confidence
- Network access in code of a file that runsasset-import/scripts/serve-local-media.mjs:45High confidence
- Network access in code of a file that runsclaude/skills/asset-import/scripts/serve-local-media.mjs:179High confidence
- Network access in code of a file that runsasset-import/scripts/serve-local-media.mjs:179High confidence
- Network access in code of a file that runsclaude/skills/asset-import/scripts/serve-local-media.mjs:180High confidence
- Network access in code of a file that runsasset-import/scripts/serve-local-media.mjs:180High confidence
- Network access in code of a file that runsclaude/skills/asset-import/scripts/serve-local-media.mjs:181High confidence
- Network access in code of a file that runsasset-import/scripts/serve-local-media.mjs:181High confidence
- Executable script in code of a file that runsclaude/skills/asset-import/scripts/upload-media.mjs:1High confidence
- Executable script in code of a file that runsasset-import/scripts/upload-media.mjs:1High confidence
- Network access in code of a file that runsclaude/skills/asset-import/scripts/upload-media.mjs:120High confidence
- Network access in code of a file that runsasset-import/scripts/upload-media.mjs:120High confidence
- Network access in code of a file that runsclaude/skills/asset-import/scripts/upload-media.mjs:121High confidence
- Network access in code of a file that runsasset-import/scripts/upload-media.mjs:121High confidence
- Network access in code of a file that runsclaude/skills/asset-import/scripts/upload-media.mjs:122High confidence
- Network access in code of a file that runsasset-import/scripts/upload-media.mjs:122High confidence
- Network access in code of the SKILL.mdclaude/skills/chatcut-plugin-basics-claude/SKILL.md:40High confidence
- Network access in code of the SKILL.mdchatcut-plugin-basics-claude/SKILL.md:40High confidence
- Network access in prose of the SKILL.mdclaude/skills/chatcut-plugin-basics-claude/SKILL.md:279Low confidence
- Network access in prose of the SKILL.mdchatcut-plugin-basics-claude/SKILL.md:279Low confidence
- Network access in code of documentationclaude/skills/chatcut-plugin-basics-claude/references/connection-diagnostics.md:60Low confidence
- Network access in code of documentationchatcut-plugin-basics-claude/references/connection-diagnostics.md:60Low confidence
- Network access in code of documentationclaude/skills/chatcut-plugin-basics-claude/references/connection-diagnostics.md:61Low confidence
- Network access in code of documentationchatcut-plugin-basics-claude/references/connection-diagnostics.md:61Low confidence
- Network access in code of documentationclaude/skills/chatcut-plugin-basics-claude/references/connection-diagnostics.md:62Low confidence
- Network access in code of documentationchatcut-plugin-basics-claude/references/connection-diagnostics.md:62Low confidence
- Executable script in code of a file that runsclaude/skills/chatcut-plugin-basics-claude/scripts/mcp-doctor.mjs:1High confidence
- Executable script in code of a file that runschatcut-plugin-basics-claude/scripts/mcp-doctor.mjs:1High confidence
- Access to secrets in code of a file that runsclaude/skills/chatcut-plugin-basics-claude/scripts/mcp-doctor.mjs:92High confidence
- Access to secrets in code of a file that runschatcut-plugin-basics-claude/scripts/mcp-doctor.mjs:92High confidence
- Executable script in code of a file that runsclaude/skills/chatcut-plugin-basics-claude/scripts/mcp-evidence.mjs:1High confidence
- Executable script in code of a file that runschatcut-plugin-basics-claude/scripts/mcp-evidence.mjs:1High confidence
- Executable script in code of a file that runsclaude/skills/chatcut-plugin-basics-claude/scripts/mcp-failure.mjs:1High confidence
- Executable script in code of a file that runschatcut-plugin-basics-claude/scripts/mcp-failure.mjs:1High confidence
- Executable script in code of a file that runsclaude/skills/chatcut-plugin-basics-claude/scripts/mcp-wire.mjs:1High confidence
- Executable script in code of a file that runschatcut-plugin-basics-claude/scripts/mcp-wire.mjs:1High confidence
- Network access in prose of documentationclaude/skills/image-gen/references/gpt-image-2.5.md:20Low confidence
- Network access in prose of documentationimage-gen/references/gpt-image-2.5.md:20Low confidence
- Executable script in code of a file that runsclaude/skills/multicam-sync/scripts/transcript-offset.mjs:1High confidence
- Executable script in code of a file that runsmulticam-sync/scripts/transcript-offset.mjs:1High confidence
- Network access in prose of the SKILL.mdclaude/skills/product-help/SKILL.md:11Low confidence
and 149 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md chatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md chatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md chatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md chatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md chatcut-desktop-codex-plugin/skills/connect-chatcut-desktop/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/chatcut-inc-agent-plugin/)