talking-head-guide
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 guida
Profile →npx skills add 0xsline/OpenChatCut --skill talking-head-guide --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides a talking-head video editing workflow by offering independent treatments that can be applied to talking-head footage: A-roll editing (speech-based cleanup, highlight extraction, restructuring, hooks, or alignment to a target script), Motion graphics overlay to reinforce content and transitions, B-roll to visualize spoken content, Background music to set mood and smooth gaps, Captions for accessibility, and AI Voice Isolation to clean or isolate human voice. It emphasizes using the dedicated Motion Graphics workflow for MG visuals when motion graphics are involved and ensures terminology is presented in product terms when Chinese is used. The workflow requires an existing talking-head video uploaded to the project and provides a widget-based intake flow to select treatments and target the edit before proceeding step by step, with explicit checkpoints after major steps.
How it works
- Require an existing talking-head video as input; if none exists, trigger a widget-based intake flow that bundles file upload with treatment selection via widget-forms.
- Surface the editor link early when a project is created or targeted, and confirm the visible editor matches the project before delivery.
- Offer independent treatments: A-roll editing, Motion graphics overlay, B-roll, Background music, Captions, and AI Voice Isolation.
- For Motion Graphics specifically, use 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).
- Follow a dependency order if multiple treatments are chosen: finalize A-roll editing (speech timing) before committing any visual, audio, or text layer; confirm results with the user after each major step before proceeding to the next (e.g., after A-roll, before MG, after MG, etc.).
- Do not reveal internal tool addresses or indices; explain edits using actual spoken content or plain-language descriptions.
When to use it
Use when editing a talking-head video and the user wants speech editing (clean up fillers, remove口癖, or smooth speech), or when adding MG animations or B-roll to a talking video, or when adding captions or background music as part of the talking-head workflow.
What can touch
- Tools listed as independent treatments: A-roll editing, Motion graphics overlay, B-roll, Background music, Captions, AI Voice Isolation.
- For MG overlays, coordinate with the active Motion Graphics workflow in the OpenChatCut environment.
Caveats
- Requires an existing talking-head video in the project.
- Independent treatments must be aligned and finalized in dependency order with user confirmations between steps.
- Uses product-specific terminology for MG discussions, especially in Chinese language contexts.
- License: AGPL-3.0
# Talking Head Video Editing ## What this skill covers **Required input**: an existing talking-head / 口播 video uploaded to the project. If the user wants to start without one (e.g., generate a fresh talking-head from scratch), this skill doesn't apply. **When the user enters this workflow without a source video uploaded yet, ask via a widget surface — bundle the file upload with the treatment selection in one flow**, not two separate turns or a markdown "drag your file in" instruction. Load `widget-forms` for the host-specific route. Never tell the user to "拖进编辑器" / "点击素材库的上传按钮"; that's friction with no upside. When the task creates or targets a OpenChatCut project for the user, surface the editor link early so they can watch progress, and re-confirm the visible editor matches the project before final delivery. Independent treatments that can be applied to talking-head videos. Pick the ones that match what the user wants — not all are needed every time. - **A-roll editing** (中文称 **语音剪辑** / 含 **去口癖、停顿、重复**) — transcript-based speech editing. Common operations include cleanup, highlight extraction, restructure, opening hook, and others as needed for the aligned outcome. - **Motion gr
- 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
What does the talking-head-guide skill do?
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 guida
How do I install it?
Run `npx skills add 0xsline/OpenChatCut --skill talking-head-guide --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From 0xsline/OpenChatCut, a repository with 805 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.