cut-video — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by louisedesadeleer · Claude Skill · ★ 88

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is cut-video safe to install? View the security audit →

About cut-video

Cut Video A Claude Code skill that tightens long-form recordings — removes silences, ums, fillers, and dead air while preserving laughs and comedic pauses. More accurate than cutting from Whisper alone. Cuts are driven by Montreal Forced Aligner (MFA) word boundaries (10–20ms precision, with true inter-word silences as explicit intervals) rather than Whisper timestamps (±100–300ms, with pauses embedded inside word durations). Whisper is used only to produce the transcript text; MFA aligns it to the audio. The result: tighter cuts, no clipped word onsets/tails, and reliable silence detection. Point it at any video file and it will: Make a proxy — transcodes HEVC/4K → 1080p H.264 with hardware decode so every subsequent step runs in seconds, not minutes. Transcribe with Whisper — , for the transcript text only. Force-align with MFA — snaps the transcript to the audio at 10–20ms precision; this is the timing engine for every cut. Plan the cuts — applies a tone-aware silence heuristic (aggressive / balanced / sentimental / documentary), strips fillers, drops false starts and retakes. Shows you the plan before touching the video.

Quick Facts

Stars88
Forks15
LanguagePython
CategoryClaude Skill
LicenseMIT
Quality Score64.9905255270967/100
Open Issues2
Last Updated2026-07-09
Created2026-05-15
Platformsclaude-code, python
Est. Tokens~4k

Compatible Skills

These tools work well together with cut-video for enhanced workflows:

  • vggt-mps — semantic(0.38)+complementary+similar_pop+shared_platform (48%)
  • local-ai-mac — semantic(0.31)+complementary+similar_pop+shared_platform (46%)
  • ovo-local-llm — semantic(0.30)+complementary+similar_pop+shared_platform (46%)
  • safari-mcp — semantic(0.29)+complementary+similar_pop+shared_platform (45%)

cut-video alternative? Top 2 similar tools

Looking for a cut-video alternative? If you're comparing cut-video with other claude skill tools, these 2 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • claude-ai-mcp by anthropics · ⭐ 432

    Report issues related to MCP integration with Claude here.

  • skyll by assafelovic · ⭐ 240

    A tool for autonomous agents like OpenClaw to discover and learn skills autonomously

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is cut-video?

cut-video is Claude Code skill: tighten long recordings — remove silences, ums, dead air. Preserves laughs and comedic pauses. Fast on Apple Silicon.. It is categorized as a Claude Skill with 88 GitHub stars.

What programming language is cut-video written in?

cut-video is primarily written in Python.

How do I install or use cut-video?

You can find installation instructions and usage details in the cut-video GitHub repository at github.com/louisedesadeleer/cut-video. The project has 88 stars and 15 forks, indicating an active community.

What license does cut-video use?

cut-video is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to cut-video?

The top alternatives to cut-video on Agent Skills Hub include claude-ai-mcp, skyll. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Claude Skill tools