🔍
QualityTypeScript

Verification

by 0xsline

Verification is a Quality skill for Claude Code, published by 0xsline in OpenChatCut.

935 stars124 forkson 0xsline/OpenChatCutAdded 2026/08/06+2% in starsRepository updated 2026/08/11
agent-skillsagentic-aiai-agentai-video-editorcapcutchatcutclaude-codecodexdesktop-appelectronffmpeglocal-firstmcpopen-sourceopenchatcutremotiontext-based-video-editingtimeline-editorvideo-editingvideo-editor
Install in seconds
Install Verification
Copy Verification into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/0xsline/OpenChatCut/tree/main/src/agent/skills/verification ~/.claude/skills/verification

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/0xsline/OpenChatCut.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
src/agent/skills/verification/SKILL.md in 0xsline/OpenChatCut
Installs to
~/.claude/skills/verification
Collection
One of 27 skills cataloged from this repository
Category
Quality1897 skills

What Verification does

Provides verification levels and tools for confirming agent edits in the OpenChatCut project and editor. Includes static checks, runtime editor observation, and desktop app validation.

Verification is cataloged under Quality on DirSkills. Verification comes from a repository tagged agent-skills, agentic-ai, ai-agent, ai-video-editor and capcut.

Documentation

README

Verification

Use the lowest verification level that proves the requested result:

Level Required evidence
L0 Static checks such as the focused verification script, npx tsc --noEmit, tests, and build.
L1 A real Agent run against the editor at localhost:5199, followed by structural and rendered evidence.
L2 The packaged desktop app completing the user scenario, including human visual review where automation is insufficient.

Runtime behavior changes require L0 + L1. Release and desktop-only changes also require L2 when the packaged app is the behavior under test.

Prefer two signals:

  1. read_project for structure: assets, tracks, items, frame placement, timeline duration.
  2. A visual capture path for rendered evidence at exact frames.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Verification

  • What else does 0xsline publish alongside Verification?

    Verification is one of 27 skills that DirSkills catalogs from 0xsline/OpenChatCut, the repository it ships in. Its siblings there include AI Cinematic Short Film, AI Image Generation and Asset Import. Each one is a separate skill with its own page in this directory, installs the same way Verification does, and is maintained by 0xsline in that same repository. The rest of the collection is listed on the 0xsline/OpenChatCut page.

  • How does Verification compare to other Quality skills?

    Verification ranks #879 by stars among the 1897 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Verification against them. Open each page to compare what they document and how they install.