Agent skill

Ocv Generate Test Scripts

by IFRIT-Zhou in IFRIT-Zhou/One-Click-VidGen

Generate Chinese test scripts optimized for stable One-Click VidGen (OCV) demonstrations, together with the three UI visual-setting fields: unified visual style, global character settings, and…

AGPL-3.0Auto-check passedMedia & Creative

Install Ocv Generate Test Scripts

skills CLI
$ npx skills add IFRIT-Zhou/One-Click-VidGen --skill ocv-generate-test-scripts -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install IFRIT-Zhou/One-Click-VidGen ocv-generate-test-scripts --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/IFRIT-Zhou/One-Click-VidGen.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ocv-generate-test-scripts .claude/skills/ocv-generate-test-scripts && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ocv-generate-test-scripts
GitHub stars
113
Token cost
~1.8k tokens
SKILL.md length
893 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Generate Chinese test scripts optimized for stable One-Click VidGen (OCV) demonstrations, together with the three UI visual-setting fields: unified visual style, global character settings, and…

  • Works in 5 steps: 基本信息 → 测试文案 → 统一画面风格 → …
  • Expanding OCV demo copy for story
  • SKILL.md covers Determine the request, Default scope, Stability guardrails and Mode-specific writing, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ocv Generate Test Scripts is an agent skill from IFRIT-Zhou/One-Click-VidGen. Generate Chinese test scripts optimized for stable One-Click VidGen (OCV) demonstrations, together with the three UI visual-setting fields: unified visual style, global character settings, and story-world/environment settings. Use when creating or expanding OCV demo copy for story, narration/commentary, popular-science, serious educational, suspense, emotional, or general custom modes, especially when the result should minimize character inconsistency, costume changes, reflection errors, excessive time jumps…

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Media & Creative, covering Test generation, Text to speech and voice and Image generation. The repository describes itself as: An AI-powered desktop workflow that turns scripts into narrated story or explainer videos with voiceover, AI-planned storyboards, generated visuals, captions, and editable… The licence is AGPL-3.0.

When your agent uses it

  • Expanding OCV demo copy for story
  • Narration/commentary
  • Popular-science
  • Serious educational

Example prompts

  • “/ocv-generate-test-scripts”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. 基本信息
  2. 测试文案
  3. 统一画面风格
  4. 全局人物设定
  5. 故事世界与环境设定

What it can do on your machine

Read from SKILL.md and the folder at commit faafad1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ocv Generate Test Scripts loads about 1.8k tokens when it runs. Until then it costs about 150 tokens; SKILL.md has 893 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~150
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from IFRIT-Zhou/One-Click-VidGen at commit faafad1, republished under its AGPL-3.0 licence (© IFRIT-Zhou). 893 words, ~1,819 tokens.

Download SKILL.mdSave it as .claude/skills/ocv-generate-test-scripts/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
ocv-generate-test-scripts
description
Generate Chinese test scripts optimized for stable One-Click VidGen (OCV) demonstrations, together with the three UI visual-setting fields: unified visual style, global character settings, and story-world/environment settings. Use when creating or expanding OCV demo copy for story, narration/commentary, popular-science, serious educational, suspense, emotional, or general custom modes, especially when the result should minimize character inconsistency, costume changes, reflection errors, excessive time jumps, crowded scenes, and other image-generation failure points.

Generate OCV Test Scripts

Create engaging Chinese test material that demonstrates OCV reliably. Optimize for visual continuity without making the writing bland.

Determine the request

Use the mode requested by the user. If unspecified, ask for a mode only when the choice materially matters; otherwise choose one and state it. Support at least:

  • 故事叙事:都市、悬疑、温情、轻奇幻等具有连续事件的短故事。
  • 口播分享:观点、关系沟通、生活经验、社会观察等有具体生活场景支撑的口播。
  • 科普教育:自然科学、医学常识、历史、地理、技术或其他学科的严肃科普。
  • 通用自定义:按用户指定题材、受众和语气生成。

When the user requests a batch covering multiple modes, create separate self-contained cases rather than mixing modes in one script.

Default scope

Unless the user specifies otherwise:

  • Write 600–900 Chinese characters, suitable for a short but meaningful test.
  • Use natural paragraphs and complete punctuation. Do not place every short phrase on a separate line.
  • Keep the main event within one continuous period, preferably several minutes to one day.
  • Use 1–2 recurring characters; allow at most 3 only when necessary.
  • Give each recurring character one fixed outfit for the entire script.
  • Use 2–4 visually distinguishable but connected locations.
  • Give each scene a concrete action, object, spatial relationship, or environmental change that can become a new image.

Respect explicit user length, mode, subject, audience, and tone requirements over these defaults.

Stability guardrails

Apply these rules unless the user explicitly requests an exception:

  1. Avoid mirrors, mirror reflections, water reflections, glass reflections, duplicated shadows, portraits within portraits, and other compositions that can duplicate or distort characters.
  2. Avoid long time spans, repeated flashbacks, rapid season changes, childhood-to-adulthood transitions, aging, body transformations, frequent day/night switches, and repeated costume changes.
  3. Keep recurring characters visually stable: same age band, hairstyle, clothing, accessories, and body type. Do not write plot beats that require removing a signature item.
  4. Avoid crowds, many similar-looking people, complicated fights, dense hand interactions, simultaneous multi-person actions, split screens, collages, comic panels, montage grids, and picture-in-picture.
  5. Use phones, tablets, computers, letters, photographs, charts, and exact on-screen text only when essential. If their content is not narratively explicit, show the person naturally using the device instead of inventing screen content.
  6. Avoid exact brand logos, long readable text, dense formulas, intricate maps, and visually ambiguous pronouns. Give recurring characters distinct names or stable role labels.
  7. Avoid many simultaneous character states. Prefer one clear emotional or physical state per shot-worthy sentence.
  8. Do not repeat the same visual beat with slightly different wording. Make adjacent paragraphs distinguishable through action, location, prop, framing opportunity, or information layer.
  9. Keep safety and platform suitability: no graphic gore, sexualized minors, hateful dehumanization, or instructions for wrongdoing.

Mode-specific writing

故事叙事
  • Build a clear opening hook, escalating discovery or conflict, and a meaningful ending.
  • Let causally connected sentences stay together; do not fragment one event into slogan-like lines.
  • Prefer a single outing, visit, conversation, investigation, work shift, or evening.
  • Use recurring props and locations to strengthen continuity.
口播分享
  • State the tension early, then explain it through one or two concrete everyday examples.
  • Turn abstract claims into observable behavior, setting, and consequences without becoming a PPT outline.
  • Keep any example couple, family, colleague, or narrator in one stable appearance and time period.
  • End with a grounded conclusion or actionable perspective rather than empty motivational slogans.
Show full SKILL.md (379 more words)Show less
科普教育
  • Prioritize correctness and clarity. For unstable or high-stakes facts, verify them with authoritative primary sources before writing.
  • Move from a question or familiar phenomenon to mechanism, example, misconception correction, and concise takeaway.
  • Prefer visually expressible processes, scale comparisons, objects, environments, and stepwise changes.
  • Do not force a recurring host character. Leave the character field empty when people are unnecessary.
  • Avoid relying on large blocks of generated text, exact equations, or complex charts to carry the explanation.

Produce the deliverable

Return the following sections in Chinese. Put each copyable field in its own fenced text block.

1. 基本信息

Include:

  • 标题
  • 推荐模式
  • 预计字数
  • 主要测试点(3–6 concise items)
2. 测试文案

Write the complete narration. Do not insert shot numbers, image prompts, production notes, or bracketed stage directions into the narration unless requested.

3. 统一画面风格

Write one coherent OCV-ready paragraph that defines:

  • visual medium and degree of realism;
  • palette, lighting, texture, and atmosphere;
  • horizontal 2:1 composition and clean image quality;
  • exclusions such as multi-panel collage, dense text, watermark, noisy smearing, or unintended photorealism when an illustration style is requested.

Do not put character identity or costume details here.

4. 全局人物设定

For every recurring character, define a unique stable role label or name, approximate age, gender presentation when relevant, hairstyle, face/body cues, one complete outfit, and one optional signature object. Avoid duplicate generic labels.

For people-free science or environment cases, output 留空(本案例不需要固定人物).

End non-empty character settings with exactly:

当画面中没有这些角色的时候则本段不作为参考。

5. 故事世界与环境设定

Define the narrow time period, region or setting, connected recurring locations, weather/light continuity, technology era, and key recurring props. Explicitly constrain the world to avoid accidental time, season, architecture, or technology jumps.

Final quality check

Before responding, silently verify:

  • The narration is coherent and interesting rather than a list of shots.
  • The time span, locations, cast, and clothing stay within the selected limits.
  • No mirror/reflection-dependent scene or accidental multi-panel instruction remains.
  • Every recurring character in the narration appears in the global character field.
  • Character details do not leak into the unified style field.
  • The three UI fields agree with the narration and can be pasted directly into OCV.
  • A science case does not invent a host merely to fill the character field.
  • The script uses normal sentence and paragraph boundaries suitable for OCV segmentation.

If any check fails, revise before returning the result.

© IFRIT-Zhou, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/ocv-generate-test-scripts of IFRIT-Zhou/One-Click-VidGen.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit faafad1

Compare with similar skills

Ocv Generate Test Scripts next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ocv Generate Test Scripts compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ocv Generate Test Scripts this skillIFRIT-Zhou/One-Click-VidGen113—~1.8kAutomated safety check: PassAGPL-3.0
Wedding Video Guided Wizardaaronyi97/wedding-video-guided-wizard306—~1kAutomated safety check: PassMIT
Hbg Life SimulationMr-funny/hbg-life-simulation140—~5.8kAutomated safety check: PassMIT
RunninghubHM-RunningHub/OpenClaw_RH_Skills141—~1.6kAutomated safety check: PassApache-2.0
Media Genclacky-ai/openclacky1.2k—~7.3kAutomated safety check: PassMIT
Moonlit Book Workflowlincwang123-bot/moonlit-stories174—~1.4kAutomated safety check: PassMIT

Similar skills

  • Wedding Video Guided Wizard

    aaronyi97/wedding-video-guided-wizard

    Guide a creator through a real couple's custom wedding video, from a shareable story intake card and Kimi writing pack through narration, external GPT image prompts, image-to-video packs, music and…

    306 GitHub stars~1k tokensUpdated 29 days ago
    Media & CreativeAuto-check passed
  • Hbg Life Simulation

    Mr-funny/hbg-life-simulation

    Create Chinese HBG “模拟人生 / 人生副本” narrative videos with a consistent comic IP, a rapid multi-life opening, continuous natural-speed narration, synchronized short captions, dense static manga…

    140 GitHub stars~5.8k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Runninghub

    HM-RunningHub/OpenClaw_RH_Skills

    Generate images, videos, audio, and 3D models via RunningHub API (420 endpoints) and run any RunningHub AI Application (custom ComfyUI workflow) by webappId.

    141 GitHub stars~1.6k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Media Gen

    clacky-ai/openclacky

    Generate or edit images, videos, or audio in the current task.

    1.2k GitHub stars~7.3k tokensUpdated today
    Media & CreativeAuto-check passed
  • Moonlit Book Workflow

    lincwang123-bot/moonlit-stories

    Build or resume a reusable 12-page personalized English picture book in the Moonlit watercolor house style, using Codex built-in image generation for a per-book character sheet plus illustrations…

    174 GitHub stars~1.4k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Qwen Edit

    digitalsamba/claude-code-video-toolkit

    AI image editing prompting patterns for Qwen-Image-Edit. An agent skill from digitalsamba/claude-code-video-toolkit.

    2.2k GitHub stars~711 tokensUpdated 3 days ago
    Media & CreativeAuto-check passed

More from IFRIT-Zhou/One-Click-VidGen

  • Ocv Production Bridge

    IFRIT-Zhou/One-Click-VidGen

    通过 OCV 的 Codex 制作桥填写动态视频初始草稿、读取用户确认的真实配音与字幕、设计并校验导入分镜。用于 OCV 视频创作交接、配音后接手规划和续作;适用于不同创作领域,不代替专业内容审核,不自动生成素材或发布。

    113 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Questions about Ocv Generate Test Scripts

What does Ocv Generate Test Scripts do?

Generate Chinese test scripts optimized for stable One-Click VidGen (OCV) demonstrations, together with the three UI visual-setting fields: unified visual style, global character settings, and…. Ocv Generate Test Scripts is an agent skill from IFRIT-Zhou/One-Click-VidGen. Generate Chinese test scripts optimized for stable One-Click VidGen (OCV) demonstrations, together with the three UI visual-setting fields: unified visual style, global character settings, and story-world/environment settings.

When should I use Ocv Generate Test Scripts?

Ocv Generate Test Scripts fits situations like: expanding OCV demo copy for story; narration/commentary; popular-science; serious educational.

How do I install Ocv Generate Test Scripts in Claude Code?

Run `npx skills add IFRIT-Zhou/One-Click-VidGen --skill ocv-generate-test-scripts -a claude-code`. Or copy the skill folder (.agents/skills/ocv-generate-test-scripts in IFRIT-Zhou/One-Click-VidGen) into .claude/skills/ocv-generate-test-scripts in your project. Claude Code loads it when a task matches its description.

How do I install Ocv Generate Test Scripts in Codex?

Run `npx skills add IFRIT-Zhou/One-Click-VidGen --skill ocv-generate-test-scripts -a codex`. Or copy the skill folder (.agents/skills/ocv-generate-test-scripts in IFRIT-Zhou/One-Click-VidGen) into .agents/skills/ocv-generate-test-scripts in your project. Codex loads it when a task matches its description.

Can I use Ocv Generate Test Scripts in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add IFRIT-Zhou/One-Click-VidGen --skill ocv-generate-test-scripts -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ocv-generate-test-scripts, .gemini/skills/ocv-generate-test-scripts, .github/skills/ocv-generate-test-scripts and .opencode/skills/ocv-generate-test-scripts in your project.

What does Ocv Generate Test Scripts need to run?

SKILL.md names no scripts, command-line tools or credentials: Ocv Generate Test Scripts is instructions for the agent only.

Does Ocv Generate Test Scripts access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ocv Generate Test Scripts safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ocv Generate Test Scripts use?

Ocv Generate Test Scripts is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ocv Generate Test Scripts use?

About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ocv Generate Test Scripts?

Skills that share tags, products or a category with Ocv Generate Test Scripts: Wedding Video Guided Wizard (aaronyi97/wedding-video-guided-wizard, 306 stars), Hbg Life Simulation (Mr-funny/hbg-life-simulation, 140 stars), Runninghub (HM-RunningHub/OpenClaw_RH_Skills, 141 stars) and Media Gen (clacky-ai/openclacky, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ocv Generate Test Scripts?

IFRIT-Zhou (a GitHub user) maintains it in IFRIT-Zhou/One-Click-VidGen, which has 113 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 9, 2026.

Source: IFRIT-Zhou/One-Click-VidGen on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.