Agent Skill
Talking Head Guide skill
talking-head-guide0xsline/OpenChatCutsrc/agent/skills/talking-head-guide/SKILL.md
Guide for editing videos where the primary content is people talking — talking-head / 口播, interview / 访谈, lecture, tutorial, podcast, course content, and similar talking-driven formats. Use when the user wants speech editing on a talking video (剪口播 / 口播剪辑 / 去口癖 / clean up fillers / smooth speech), motion graphics layered onto talking video (口播加 MG / 加动画), or B-roll on a talking video (加 B-roll / add B-roll). For motion graphics specifically, use this together with the active Motion Graphics skill/workflow available in the current OpenChatCut environment — this skill adds talking-specific guidance (speech-rhythm timing, frame-aware placement, subject/caption protection, placement verification).
always on
159 tokname + description
once used
13,000 tokSKILL.md body
bundled files
0
repo stars
2.6kGitHub
Install the Talking Head Guide skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/0xsline/OpenChatCut --skill talking-head-guide
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/0xsline/OpenChatCut.git /tmp/OpenChatCut mkdir -p ~/.claude/skills cp -R /tmp/OpenChatCut/src/agent/skills/talking-head-guide ~/.claude/skills/talking-head-guide
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 159 tok |
| When the agent uses it | The SKILL.md instructions | 13,000 tok |
| Only if opened | No bundled files | — |
Until it is used, talking-head-guide costs about 8.6× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 31 skills from 0xsline/OpenChatCut would load 2,031 tokens of descriptions. Skills vs MCP study
Checks
- The instructions are over 5,000 tokens, the Agent Skills specification's guideline for SKILL.md.
- The instructions are over 500 lines; the specification suggests moving detail into reference files.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Talking Head Video Editing
- What this skill covers
- What shapes the edit
- Order of execution
- A-roll editing
- Scenario
- Common A-roll tasks
- Shared A-roll principles
- Cleanup goals and decisions
- Other A-roll task guidance
- A-roll / transcript-based editing workflow
- What transcript editing actually changes
- Tool boundaries
- MG Overlay
- Goal
- MG workflow
- Visual identity
- Where MG is useful
- Repeated Components
- Per-MG decisions
- B-roll
- Goal
- Where B-roll is useful
- Sources
More skills from 0xsline/OpenChatCut
- ai-cinematic-short-film0xsline/OpenChatCut
Plan AI short films with story, shots, prompts, and continuity.
2.6k20 tok idle · 517 in use - asset-import0xsline/OpenChatCut
Use when acquiring or importing media into a OpenChatCut project asset library for video editing or creation, including local/attached videos, user-provided paths, public media URLs, web video/audio/image assets, upload fallback decisions, and deciding between import_media, download_media, or manual user action.
2.6k62 tok idle · 746 in use - batch-montage-variants0xsline/OpenChatCut
Turn one pool of existing project media into a batch of distinct, publishable montage cuts instead of a single hero edit. Use for batch montage, one-source-many-outputs, 一源多出, 批量混剪, 批量出片, 矩阵号, 多账号分发, variant batches, deduped cuts, 去重变体, 防搬运, or when the user asks for N different versions of the same footage.
2.6k101 tok idle · 1,053 in use - beat-sync-montage0xsline/OpenChatCut
Plan and build a finished beat-synced montage where cut placement serves the content, not just the metronome. Use for 卡点混剪, 卡点剪辑, 踩点视频, beat-sync montage, rhythm edit, 节奏剪辑, 音乐驱动剪辑, or when the user wants cuts that land on the beat.
2.6k81 tok idle · 1,032 in use - create-motion-graphics0xsline/OpenChatCut
Use whenever the agent needs to add, create, hand-author, patch, or place Motion Graphic JSX assets in a OpenChatCut project. This is the direct-authoring path: use create_motion_graphic_from_code / edit_asset / edit_item, not motion-graphic-gen or submit_motion_graphic. Covers project/timeline intake, project visual language, editable properties, asset binding, inline JSX authoring, existing asset updates, timeline placement, and verification.
2.6k97 tok idle · 5,976 in use - ecommerce-product-montage0xsline/OpenChatCut
Assemble product footage, UGC, and b-roll into a conversion-oriented montage with a hook → pain → demo → proof → CTA rhythm. Use for 带货混剪, 产品混剪, 商品短视频, 种草视频, ecommerce montage, product reel, UGC cutdown, or when the user wants selling footage cut into a short that converts.
2.6k81 tok idle · 987 in use - explainer-video0xsline/OpenChatCut
Create finished explainer videos from a topic, script, outline, voiceover, product logic, data, technical concept, course material, or reference assets. Use when the user wants narration, motion graphics, stock footage, generated visuals, or mixed visuals to explain an idea.
2.6k59 tok idle · 2,183 in use - export0xsline/OpenChatCut
Use when a OpenChatCut video editing or creation workflow needs export, render, download, share, final delivery, subtitle-file export, render choice, local-only asset handling, or export fallback explanation.
2.6k42 tok idle · 1,934 in use