Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Open Video Harness

CSecurity

Make videos with code (video-as-code / code2video) through the OpenVideoHarness workbench. Covers 3Blue1Brown-style math and science explainers, knowledge shorts (vertical or horizontal; 抖音, B站, 小红书, Shorts), product launch films and promos, lyric videos and music videos, data stories, paper explainers, hand-drawn or watercolour shorts, meme or fast-cut edits, and cutting the user's own footage (talking heads, interviews, vlogs; 剪口播). Also covers voiceover (Chinese or English), bilingual capt...

4 stars
0 votes
0 copies
0 views
Added 10/2/2026
ai-agentsbashgit

Security Analysis

C71/100
criticalPipes output to a shell interpreter
mediumUses curl or wget to download content
criticalDownloads and executes remote scripts — classic supply chain attack

Pro shows the line behind each finding and how to fix it

Scanned 10/2/2026

$npx -y skills add ZLHad/OpenVideoHarness --skill open-video-harness --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Open Video Harness?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Open Video Harness
[![Security: C — Skills Directory](https://www.skillsdirectory.com/api/skills/zlhad-open-video-harness/badge)](https://www.skillsdirectory.com/skills/zlhad-open-video-harness)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: open-video-harness
description: Make videos with code (video-as-code / code2video) through the OpenVideoHarness workbench. Covers 3Blue1Brown-style math and science explainers, knowledge shorts (vertical or horizontal; 抖音, B站, 小红书, Shorts), product launch films and promos, lyric videos and music videos, data stories, paper explainers, hand-drawn or watercolour shorts, meme or fast-cut edits, and cutting the user's own footage (talking heads, interviews, vlogs; 剪口播). Also covers voiceover (Chinese or English), bilingual captions, code-composed music, sound effects, and reverse-engineering a reference video. Use it whenever the user asks to make, animate, render, remake or cut a video, 做视频, 做动画, 做科普视频, 做宣传片, 做 MV, 讲解视频, 片头, 剪用户自己录的素材, or 剪口播, even if they don't name the harness.
---

# OpenVideoHarness

Harness path (set by install.sh): ~/OpenVideoHarness

This skill is a thin pointer. All workflows, rules and tools live in the OpenVideoHarness repository.

## 1. Locate the harness

Use the first of these that exists and contains `bin/vh`:

1. `$OVH_DIR`
2. the path on the "Harness path" line above
3. `~/OpenVideoHarness`
4. the current working directory

If none exists, ask the user for permission, then install it:

```bash
curl -fsSL https://raw.githubusercontent.com/ZLHad/OpenVideoHarness/main/install.sh | bash
```

## 2. Follow the harness, not this file

Read `<harness>/CLAUDE.md` (Codex: `<harness>/AGENTS.md`, which is identical) and follow it exactly:

- route the request to one of the 9 `video-types/` docs (09, editing the user's own footage, is experimental);
- create the project with `<harness>/bin/vh new <type> <slug>`;
- stop for the user where effort and director mode say (CLAUDE.md "努力程度" and "导演模式"): `standard` and `studio` stop at the **three human review gates** (concept and outline → storyboard → first draft); `quick` renders straight through. Anything the user said they want to decide themselves (hook, main character, theme music, title and cover …) adds a stop before anything downstream needs it, or rides on the next gate if it can wait. Each stop is by default one local review page from `bin/vh review`, at most three decisions; send the user only the lines it prints, then wait;
- follow the hard rules: every frame is a pure function of t; when there is sound, audio sets the timing; storyboard before code; self-review every scene; fact discipline;
- keep work inside `<harness>/projects/`; when the user names another directory, create the project there with `<harness>/bin/vh new <type> <slug> --dir <that directory>` (or set `OVH_PROJECTS`).

Audio tools:
- `bin/vh tts` — voiceover, Chinese or English, local Qwen3-TTS by default;
- `bin/vh captions` — zh/en/bilingual subtitles;
- `bin/vh music` — code-composed soundtrack;
- `bin/vh sfx` — sound effects;
- `bin/vh mix` and `bin/vh mux` — mixing and muxing.

Run `bin/vh doctor` if anything looks missing.

Attribution

ZLHadZLHad
View sourceSee grades on GitHubMore from ZLHad →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →