Capcut Edit

Organization

pockebot

capcut-edit

Edit videos and beautify photos in CapCut on mobile. Use when the user asks to open CapCut, create/edit/export videos, add text/effects/music/captions, use templates, or retouch and enhance photos.

Overview

Publisher	pockebot
Repository	`openpocket`
Skill name	`capcut-edit`
Stars	848
Forks	6
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by pockebot on GitHub. Read the source before you install it.

Installation

Install the Capcut Edit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/pockebot/openpocket/tree/main/skills/capcut-edit
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/pockebot/openpocket.git /tmp/openpocket
mkdir -p .claude/skills
cp -r /tmp/openpocket/skills/capcut-edit .claude/skills/capcut-edit

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Capcut Edit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Capcut Edit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Capcut Edit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

CapCut Edit

Use this skill to complete CapCut editing tasks end-to-end with deterministic, low-risk actions.

This skill follows CapCut official app capabilities (video editing, effects/transitions, text/captions, audio tools, templates, and photo editing/retouch flow).

Preconditions

Confirm CapCut is foreground (com.lemon.lvoverseas).
If not installed, install and launch first.
If sign-in is required for cloud/template assets, use request_human_auth(oauth).
If gallery/media permission is requested, approve locally on Agent Phone.

Human Auth Photo Mapping (Critical)

When photos come from Human Phone authorization, use this strict picker rule:

Prefer Downloads first.
If filename is visible, select openpocket-human-auth-latest.* first.
If the picker is thumbnail-only, select the top-left tile first (most recently imported).
Do not randomly scan old thumbnails before trying the latest slot above.

Runtime summaries may include:

photo_latest_device_path=...
photo_latest_alias_device_path=...
photo_latest_name=...

Use these hints to match the correct media item before editing.

Core Modes

Identify and choose the correct mode before editing:

New project (manual timeline editing)
Templates (fast preset output)
AutoCut (auto-generated edits)
Photo editor / photo-only flow (retouch, filters, color, crop)

If the user did not specify, default to New project for control.

Video Editing Workflow

1) Project setup

Enter New project and select target media.
Confirm orientation and aspect ratio early (9:16, 16:9, 1:1, etc.) to avoid rework.
Place clips in intended order before fine edits.

2) Structural edit first

Trim/split/delete first.
Then set clip speed and timing.
Add transitions only after clip boundaries are stable.

3) Visual polish

Apply filters/effects conservatively.
Add text/stickers after timeline timing is mostly fixed.
For portrait content, use retouch/beauty controls moderately and keep a natural look.

4) Audio and captions

Add music/voiceover and balance volume levels.
Use auto captions/subtitles when requested; then quickly proofread key lines.
Keep caption position away from UI-safe zones (top status area and bottom controls).

5) Export

Verify export settings (resolution/fps) against user intent.
Export once and wait for completion.
Do not publish/share to public platforms unless user explicitly asks.

Photo Edit / Beautify Workflow

Use this when user asks to beautify or edit photos.

Open photo editing entry (Photo editor tool or image-only project).
Apply base corrections first:

crop/rotate/straighten
brightness/contrast/highlight/shadow/color temperature

Then apply style controls:

filters/effects
retouch/beauty (skin smoothing, face/body adjustments when available)

Compare before/after quickly and avoid over-processing.
Export/save edited photo and report output.

Template Workflow (Fast Output)

Open Templates.
Search by user goal/theme.
Preview 1-3 candidates, pick one closest to requested style.
Replace media placeholders.
Check text overlays for clipping/truncation.
Export and return result.

AutoCut Workflow

Open AutoCut and select source clips/photos.
Let CapCut generate draft.
Accept only if pacing and cuts match user intent.
If draft quality is poor, switch to New project instead of repeatedly regenerating.

Safety Guardrails

Never purchase paid assets/subscription without explicit user approval.
Never auto-post to TikTok/other social channels unless user asks.
Never delete original media unless user explicitly requests deletion.
If watermark/pro feature lock appears, report clearly and ask for user decision.

Interaction Guidance

Prefer tap_element when reliable UI candidates exist.
Use swipe for timeline/media panel navigation.
For timeline precision, use small repeated drags instead of one large drag.
After each major edit block, verify visible timeline/result changed as expected.
If the same action fails twice, switch strategy (different panel/entry point).

Failure Handling

Import failed: re-open media picker and retry once.
Export failed: reduce quality preset and retry once.
App stalls/crashes: relaunch CapCut, reopen draft/project, continue from last stable point.
Permission wall loops: close dialog, re-enter editor, confirm permission state.

Completion Report

When finishing, include:

mode used (new project, template, autocut, photo edit)
major edits applied
export status and output type (video/photo)
notable constraints encountered (pro lock, missing asset, permission issue)

Frequently asked questions

What does the Capcut Edit AI skill do?

Edit videos and beautify photos in CapCut on mobile. Use when the user asks to open CapCut, create/edit/export videos, add text/effects/music/captions, use templates, or retouch and enhance photos.

Why use Capcut Edit on TypingMind?

Because you install it once and use it with any model. Capcut Edit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Capcut Edit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pockebot/openpocket/tree/main/skills/capcut-edit. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Capcut Edit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Capcut Edit?

As many as you like. As long as a model supports skills, you can use Capcut Edit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Capcut Edit AI skill free?

Yes. It is published on GitHub by pockebot under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Comfyui

NousResearch

OrganizationPopular

Generate images, video, and audio via diffusion workflows.

Heartmula

HeartMuLa: Suno-like song generation from lyrics + tags.

Hyperframes

Render MP4/WebM videos from HTML compositions.

Kanban Video Orchestrator

NousResearch

OrganizationPopular

Plan and run multi-agent video production pipelines.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

CapCut Edit

Preconditions

Human Auth Photo Mapping (Critical)

Core Modes

Video Editing Workflow

1) Project setup

2) Structural edit first

3) Visual polish

4) Audio and captions

5) Export

Photo Edit / Beautify Workflow

Template Workflow (Fast Output)

AutoCut Workflow

Safety Guardrails

Interaction Guidance

Failure Handling

Completion Report

Frequently asked questions

Related AI Skills

Set up your own AI workspace now