VectCutAPI is a cloud-based video editing API that lets AI agents create and modify videos with features such as subtitles, illustrations, picture-in-picture, voiceovers, and filters. It is intended for automated or bulk video production in agent workflows, and its catalogue skill helps agents use the editing interface.
Borrowing it
Nothing to install: this file belongs to sun-guannan/VectCutAPI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sun-guannan/VectCutAPI/main/.agents/skills/capcut-director/SKILL.mdgit clone --depth 1 https://github.com/sun-guannan/VectCutAPIWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sun-guannan/vectcutapi/capcut-director)<a href="https://agentmods.dev/skills/sun-guannan/vectcutapi/capcut-director"><img src="https://agentmods.dev/badge/skills/sun-guannan/vectcutapi/capcut-director/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sun-guannan/vectcutapi/capcut-director"><img src="https://agentmods.dev/badge/skills/sun-guannan/vectcutapi/capcut-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.01831 |
| Opus 5.5 | $0.00026 | $0.00732 |
| Sonnet 5.5 | $0.00013 | $0.00366 |
| Haiku 4.5 | $0.00007 | $0.00183 |
Grade A, and why
capcut-director scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CapCut Video Director & Timeline Engineering Skill
This skill guides AI agents in programmatically directing, assembling, and polishing video projects using the CapCut MCP server and direct CapCut Desktop timeline engineering.
1. CapCut Desktop Architecture & File System
Project Locations
- Windows:
C:\Users\<Username>\AppData\Local\CapCut\User Data\Projects\com.lveditor.draft\<ProjectName> - macOS:
~/Library/Containers/com.lemon.lvpro/Data/Documents/JianyingPro/User Data/Projects/com.lveditor.draft/<ProjectName>
The Multi-Timeline Architecture (CapCut 9.x+)
Modern CapCut Desktop (v9.0+) uses a nested multi-timeline system:
com.lveditor.draft/<ProjectName>/
├── draft_content.json <-- Root compatibility state
├── draft_meta_info.json <-- Project name, thumbnail, edit time
├── draft_cover.jpg <-- Cover thumbnail
├── .locked <-- Lock file present while project is open in CapCut
└── Timelines/
└── <TIMELINE-UUID>/
├── draft_content.json <-- ACTIVE TIMELINE STATE (Read by CapCut 9.x+!)
├── draft_content.json.bak <-- Autosave backup
└── template.tmp <-- Working buffer
[!IMPORTANT] CapCut 9.x+ reads
Timelines/<UUID>/draft_content.json, NOT the root file alone! If you only write to the rootdraft_content.json(as standard legacy MCP libraries do), CapCut will open an empty timeline. Always write to both the root and the active timeline directory.
2. In-Memory Process Lifecycle & The '.locked' Rule
CapCut Desktop loads project files into C++ RAM upon opening and does not feature a live file watcher.
- Avoid Overwrites: While CapCut is open, its background autosave thread will overwrite any external disk changes with its in-memory state.
- Workflow for External Updates:
# 1. Close CapCut before modifying draft files Get-Process -Name 'CapCut' -ErrorAction SilentlyContinue | Stop-Process -Force Start-Sleep -Seconds 1 # 2. Write updated draft_content.json # ... (write files) # 3. Remove stale lock files Get-ChildItem -Path "$env:LOCALAPPDATA\CapCut\User Data\Projects\com.lveditor.draft" -Recurse -Filter '.locked' | Remove-Item -Force - Reopening: Users must return to the CapCut Home screen or relaunch CapCut to reload the updated project from disk.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 146 lines · 66 tokens per session scan A 47e30ff4254f
capcut-director is a skill published in the GitHub repository sun-guannan/VectCutAPI (2,327 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 1,831 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-13.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.