Cap Cinematic Demo Generator
CapSoftware/Cap
Turns any URL into a short cinematic product-demo video on macOS, scouting the page, recording it with virtual input, then treating the clip with Cap's 3D camera and music.
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。
$ npx skills add IFRIT-Zhou/One-Click-VidGen --skill ocv-production-bridge -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install IFRIT-Zhou/One-Click-VidGen ocv-production-bridge --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/IFRIT-Zhou/One-Click-VidGen.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/codex_bridge/skills/ocv-production-bridge .claude/skills/ocv-production-bridge && rm -rf skills-srcUse ~/.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/
Install the "ocv-production-bridge" agent skill from https://github.com/IFRIT-Zhou/One-Click-VidGen/tree/main/plugins/codex_bridge/skills/ocv-production-bridge into .claude/skills/ocv-production-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ocv-production-bridge", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/IFRIT-Zhou/One-Click-VidGen/tree/main/plugins/codex_bridge/skills/ocv-production-bridgeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add IFRIT-Zhou/One-Click-VidGen --skill ocv-production-bridge -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install IFRIT-Zhou/One-Click-VidGen ocv-production-bridge --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/IFRIT-Zhou/One-Click-VidGen.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/codex_bridge/skills/ocv-production-bridge .agents/skills/ocv-production-bridge && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ocv-production-bridge" agent skill from https://github.com/IFRIT-Zhou/One-Click-VidGen/tree/main/plugins/codex_bridge/skills/ocv-production-bridge into .agents/skills/ocv-production-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ocv-production-bridge", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add IFRIT-Zhou/One-Click-VidGen --skill ocv-production-bridge -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install IFRIT-Zhou/One-Click-VidGen ocv-production-bridge --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/IFRIT-Zhou/One-Click-VidGen.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/codex_bridge/skills/ocv-production-bridge .cursor/skills/ocv-production-bridge && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ocv-production-bridge" agent skill from https://github.com/IFRIT-Zhou/One-Click-VidGen/tree/main/plugins/codex_bridge/skills/ocv-production-bridge into .cursor/skills/ocv-production-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ocv-production-bridge", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/IFRIT-Zhou/One-Click-VidGen.git --path plugins/codex_bridge/skills/ocv-production-bridge--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add IFRIT-Zhou/One-Click-VidGen --skill ocv-production-bridge -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install IFRIT-Zhou/One-Click-VidGen ocv-production-bridge --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/IFRIT-Zhou/One-Click-VidGen.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/codex_bridge/skills/ocv-production-bridge .gemini/skills/ocv-production-bridge && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ocv-production-bridge" agent skill from https://github.com/IFRIT-Zhou/One-Click-VidGen/tree/main/plugins/codex_bridge/skills/ocv-production-bridge into .gemini/skills/ocv-production-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ocv-production-bridge", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install IFRIT-Zhou/One-Click-VidGen ocv-production-bridgeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add IFRIT-Zhou/One-Click-VidGen --skill ocv-production-bridge -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/IFRIT-Zhou/One-Click-VidGen.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/codex_bridge/skills/ocv-production-bridge .github/skills/ocv-production-bridge && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ocv-production-bridge" agent skill from https://github.com/IFRIT-Zhou/One-Click-VidGen/tree/main/plugins/codex_bridge/skills/ocv-production-bridge into .github/skills/ocv-production-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ocv-production-bridge", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add IFRIT-Zhou/One-Click-VidGen --skill ocv-production-bridge -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install IFRIT-Zhou/One-Click-VidGen ocv-production-bridge --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/IFRIT-Zhou/One-Click-VidGen.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/codex_bridge/skills/ocv-production-bridge .opencode/skills/ocv-production-bridge && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ocv-production-bridge" agent skill from https://github.com/IFRIT-Zhou/One-Click-VidGen/tree/main/plugins/codex_bridge/skills/ocv-production-bridge into .opencode/skills/ocv-production-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ocv-production-bridge", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
ocv-production-bridge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。
Ocv Production Bridge is an agent skill from 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。
Its SKILL.md is about 2.5k 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. It works with Python. 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.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 9a8557f. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are powershell).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Ocv Production Bridge loads about 2.5k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 436 words of instructions outside code blocks.
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.
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.
The full file from IFRIT-Zhou/One-Click-VidGen at commit 9a8557f, republished under its AGPL-3.0 licence (© IFRIT-Zhou). 436 words, ~2,477 tokens.
.claude/skills/ocv-production-bridge/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.把创作精力用于稿件和画面设计,通过固定客户端完成机械操作。此 Skill 随 OCV 提供,可直接按路径阅读使用,不依赖全局安装。它是 OCV 插件的操作规范,不是 MCP 服务或自动安装的 Codex 插件。
<OCV>/plugins/codex_bridge/ocv_bridge.py,只用 Python 标准库。优先 <OCV>/runtime/python/python.exe,不存在则用现有 Python 3。不要为连接安装依赖。http://127.0.0.1:8010。用 info 验证;自定义地址通过 --base-url 指定。前端页面端口不一定是后端端口。远程 OCV 的 info 路径属于服务器,不当作本机文件;使用本机同版本客户端并指定远端地址。--cookie-file 指定已有 Netscape cookie 文件;不要读取浏览器凭据库、伪造会话或打印 cookie。404 先检查插件是否启用及版本是否完整,不反复重试。schema,保存到项目工作目录。续作复用;接口版本或验证提示变化时再刷新。不打开客户端/宿主源码研究接口。PowerShell 示例,替换占位符;全局选项放在子命令前:
& '<python>' -X utf8 '<client>' info
& '<python>' -X utf8 '<client>' --out '<项目目录>/bridge-schema.json' schema
& '<python>' -X utf8 '<client>' projects
& '<python>' -X utf8 '<client>' audio-tasksguide 可从认证接口读取本指南。--out 保存完整 JSON,仅打印短回执;随后只阅读当前任务所需字段。工作档案仅记服务地址、草稿/任务/项目 ID、revision、timeline_token、素材 ID 映射和下一步,不保存密钥。服务身份和目标 ID 不确定时先核实,不凭项目名称猜测。
草稿完成后可在首页手动归档,历史归档仍可查看和恢复,不删除制作任务或素材。info.capabilities 含 draft_archive 时,客户端支持 draft-archive <id> --revision <当前版本> 和 draft-restore <id> --revision <当前版本>;操作前读取 draft-get 核对目标及版本,只有用户要求归档时执行,不因已生成素材而自动归档。默认 drafts 仅列未归档草稿,已归档仍可按 ID 读取。
确认口播稿、受众、画幅、风格和参考图角色映射;只有影响结果的缺项才问用户。不要强迫用户填写无关的专业模板。音色采用用户明确选择,不擅自换引擎。
upload '<文件>' 上传用户授权的参考图或音色样本,记录返回的 asset.id,已有素材 ID 复用。参考图先实际查看,不按文件名猜身份。draft.json:顶层 id 为新建的32位小写十六进制 UUID、revision: 0、parameters。重试复用 id;修改已有草稿先 draft-get '<id>' 取得 revision。parameters 最少为 project_name、script。三项视觉字段为 visual_style_prompt、global_character_prompt、story_environment_prompt;video_orientation 为 landscape 或 portrait。其他允许字段以 schema.draft_fields 为准,不能任意塞入 UI 配置。reference_image_ids(最多6),按素材 ID 填 reference_image_labels/notes/kinds。上传的音色样本用 tts_voice_id=upload:<asset.id> 及支持它的 indextts25;集群音色用用户选定的 cluster_voice_id/type。参考音色不等于完整旁白。draft-save '<draft.json>',回读 draft-get 核查关键字段。强制分步制作且不自动推进是预期行为。服务器保存草稿 不等于已经打开用户页面,也不是配音任务。告知用户在 OCV 首页制作桥点“刷新 → 打开并核查”,然后生成配音。保留浏览器未保存编辑,由用户处理覆盖确认。
用户先试听、改发音/字幕并点击 OCV 的“确认配音,交给 Codex 规划”。不要因为音频存在或项目已创建就声称用户已审核。
已有动态项目直接 pack '<项目ID>'。仅持有配音任务时,经用户确认后调用:
& '<python>' -X utf8 '<client>' --out '<项目目录>/pack.json' from-audio '<配音任务ID>' --confirmedfrom-audio 是写操作,会创建/复用动态项目并同步最新配音;不是查询命令。日常读取用 pack,不要重复同步。若重配后接口提示音源未同步,让用户保存配音交接,或在用户确认后再次 from-audio。
资料包提供真实 subtitles、narration_groups、参考图 URL、现有方案、revision 和 timeline_token。参考图通过认证接口查看。原始文献/剧本/客户依据仍须从用户提供的源文件核实;资料包不包含全文证据库。
按全文叙事设计镜头,不把“一段 TTS=一镜”当规则。保持因果、问答和角色归属完整,遵守资料包 rules 与宿主约束。先在真实字幕粒度上确定切分,再设计画面;不能改写已确认配音或编造时间戳。
plan.json 顶层:revision、timeline_token(从 pack 原样带回)、audio_confirmed: true、shots。
每镜字段:
id:稳定唯一编号;slide_ids:连续、顺序且不重不漏覆盖所有字幕。kind: static|video;intent:本镜叙事目的;image_prompt:完整可执行核心图提示词;reference_ids:当前 pack 中真实存在的素材 ID。motion_plan,严格参考 schema.motion_example 的阶段结构、主体和文字清单。核心变化要可辨识,必要的建立与结尾停留允许稳定,不为每阶段强加动作。video_prompt 可省略,由工具确定性编译,不再请求一次模型。evidence 可记录来源页码、客户确认或创作依据及限制,不会作为画面文字发送给模型。不要提交 start/end/duration,工具按字幕计算。动态最长15秒;不能为过检偷偷转静态。不能在字幕间真实空隙切镜(当前合成器约束),应将空隙两侧字幕安排在同镜;如果因此无法满足时长,说明冲突请用户调整,不改音频。
动态参考图不是必须照搬首帧。动态短标签必须在阶段文字清单中明确原文、归属与载体;静态按完整海报/图解设计控制文字量。事实、专业术语和权利由创作审核保障。
& '<python>' -X utf8 '<client>' validate '<项目ID>' '<项目目录>/plan.json'
& '<python>' -X utf8 '<client>' apply '<项目ID>' '<项目目录>/plan.json'validate 无写入;apply 再次校验、备份、原子保存并回读,不运行模型。成功只报告实际回执:导入镜头数、静/动态数量、配音未改变、未生成素材,并请用户打开分镜审核。
已出图后修改一镜或多镜,用 patch-validate / patch-apply,不是完整 apply。先重新读取 pack,依据用户本次要求比较当前方案;用户可能已经手动修过,不能照搬先前计划覆盖。旧请求响应丢失则先原样重试,不重建请求。
patch.json 顶层仍为 revision,timeline_token,audio_confirmed:true,shots,但 shots 只包含本次修改的镜头。每项为稳定 id 加要改的字段:intent,image_prompt,reference_ids,motion_plan,video_prompt,evidence,未提交字段保持原值,不接受 null。用 pack 顺序对应页面镜号,不能把“第19镜”猜成 id=19。禁止提交 kind、slide_ids、时间、生成配置或素材路径;改变动静类型、拆并镜头仍需单独走 OCV 原生编辑。
& '<python>' -X utf8 '<client>' patch-validate '<项目ID>' '<项目目录>/patch.json'
& '<python>' -X utf8 '<client>' patch-apply '<项目ID>' '<项目目录>/patch.json'patch-apply 内部再次预检、备份、原子写入并回读;保存回执的 revision 与 backup_id。无变化时不写入也不增加版本。不可用时先核对 capability/更新,不删除素材或直接改 record.json 绕过保护。
info.capabilities 含 scene_management 时,先用 scene-assets <项目ID> 或 pack 读取场景图、稳定场景 ID、实际绑定镜头和恢复历史。场景图片通过认证 image_url 查看,核对后再操作;不限定医学内容。
请求 JSON 顶层带当前 revision,timeline_token,audio_confirmed:true,动作选一项:
action: disable, scene_id:停用整个场景参考,保留旧图及绑定记录,后续自动出图和手动重绘均不得提交它。action: unbind, shot_ids:只解除指定镜头绑定,并禁止重试自动重新绑回;其他镜头及场景不变。action: replace, scene_id, upload_id, image_confirmed:true:先查看用户已授权且上传的图片,再填写返回的上传 ID。保存为新的场景图文件,不覆盖旧图;不要提交本地路径或凭名称猜图片。action: restore, backup_id:恢复这次场景操作的目标场景/绑定,不整体覆盖其他场景、提示词、配音或字幕。先执行 scene-validate <项目ID> <请求.json>,查看 changed/impacts 受影响镜头,向用户明确说明后取得确认。将返回的 confirmation_token 原样加到请求中,再执行 scene-apply <项目ID> <请求.json> --confirmed。该标志只在用户授权确认后使用,不替用户自动批准。状态、版本、上传文件内容变化后必须重新预检,不能把新 token 偷换进旧确认。
保存 backup_id 与 revision,并回读 pack/scene-assets。素材文件和绑定快照保留;更新只影响下一次参考请求,不自动重绘、不付费,不声称现有分镜图片已经改变。若用户要看新图效果,由用户在 OCV 点击重绘。恢复也走同样预检和确认流程。
用户明确要求“选好参考图并重绘”时,可以执行,不必再让用户逐镜点击。先完成 patch/场景管理并回读 pack,确认目标稳定 shot_id、image_prompt 与参考图绑定;本功能只用当前保存的配置,不擅自更换模型或扩大镜头范围。
请求包含 revision,timeline_token,audio_confirmed:true,shot_id,request_id(每次操作唯一,至少8字符)。可选 use_current_image(基于当前图编辑)、use_scene_reference、image_resolution(1k/2k/4k)、image_size(如1536x1024,仅支持该尺寸的服务使用)。调用 image-validate <项目ID> <请求.json>,核对 references 中本次图号/类型、actual_reference_count、effective_image_config 及 may_charge。用户授权需覆盖这些镜头的图片生成费用;未授权则先询问。将 confirmation_token 加入原请求,再调用 image-apply <项目ID> <请求.json> --confirmed。令牌绑定目标内容、配音、参考图和生成配置;其他镜头返图导致的版本变化不要求重新预检,目标改变则必须重做预检。
多镜使用 image-batch-validate / image-batch-apply --confirmed,不要逐镜反复下载 pack 或自写并行提交脚本。批次顶层为 revision,timeline_token,audio_confirmed:true,batch_id,concurrency,items;items 每项为 shot_id,request_id 加上述可选字段。concurrency 为1–7,实际并发还受服务限额约束,多余任务排队。整批先原子预检后确认提交;同镜已有任务会返回 SHOT_BUSY,不阻止其他独立镜头单独组成批次。成功提交后保留 batch_id/request_id,以 image-status --batch-id ... 或 --request-id ... 查询本次请求,而不是以已有 image_status=completed 判断这轮成功。
路由先看 generation-settings-get <项目ID>。用户明确指定更换路由时,用 generation-settings-patch <项目ID> <文件>,文件如 {"revision":当前版本,"use_cloud_image_pool":false};只修改提交字段,未启动生成、不修改全局配置。不能根据全局开关推断历史项目快照;预检会显示实际路由。登录失败不自动切换个人API;结构化错误中的 code/message 用于排查,CLI --out 在失败时也会覆盖写入失败回执,并以非零码退出。
暂停/续作使用 image-batch-control,文件为 {"batch_id":"原批次编号","action":"pause"},action 可为 pause/resume/cancel_pending。暂停不再提交排队任务;cancel_pending 只取消未提交任务,不宣称取消上游运行中的任务。服务重启后 interrupted_unknown 可能已经扣费,必须先核实,不用新编号自动重试;interrupted_pending 先 cancel_pending 解除旧排队,再重新预检确认才能重提。成功图片 review_status=not_reviewed,仍需人工检查。
通过 image-status <项目ID> 查询异步任务;提交成功不代表图片已完成。保留原请求和 request_id,网络断开只能原样重试,不能新造 ID 造成重复付费。失败只报告原因,不自动付费重试。旧图按原生重绘历史保留,配音/字幕/时间轴不变;核心图改变会正常使对应旧视频待重做,不自动生成视频。
常规路径:读本 Skill → info/schema → 一份 pack → 编写一份方案 → validate/apply。只在需要时读取原始证据,避免重复加载整个项目历史。结构运算交给桥接;语义、事实与美术取舍由 Codex 完成。不承诺固定耗时或 token 降幅,复杂全文审核与视觉规划仍需模型计算。
© 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
SKILL.md and 1 other file in plugins/codex_bridge/skills/ocv-production-bridge of IFRIT-Zhou/One-Click-VidGen.
Open the folder on GitHubat commit 9a8557f
Ocv Production Bridge 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ocv Production Bridge this skillIFRIT-Zhou/One-Click-VidGen | 113 | — | ~2.5k | Automated safety check: Pass | AGPL-3.0 | |
| Cap Cinematic Demo GeneratorCapSoftware/Cap | 23k | — | ~2.4k | Automated safety check: Pass | Custom licence | |
| Edu Math Videowy51ai/edulab | 1.4k | — | ~2.5k | Automated safety check: Notes | Apache-2.0 | |
| Book Video Factorybytec-ai/book-video-factory | 321 | — | ~1.4k | Automated safety check: Notes | None | |
| Jianying EditorisYangs/jianying-editor-skill | 214 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Srt Vox Directorgeeklee/srt-vox-director | 105 | — | ~1.8k | Automated safety check: Pass | None |
CapSoftware/Cap
Turns any URL into a short cinematic product-demo video on macOS, scouting the page, recording it with virtual input, then treating the clip with Cap's 3D camera and music.
wy51ai/edulab
A skill your agent uses when asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a math problem (数学题, geometry, algebra, functions, motion/行程 problems), from a problem screenshot…
bytec-ai/book-video-factory
通用的多账号图书短视频生产工作流。用于用户希望建立图书号项目目录、配置账号级片头/声音/BGM/视觉规范,或只提供一本书后依次完成资料研究、口播稿、分镜、图片、配音、字幕、预览与成片导出。适用于新建工作区、批量管理多个账号、继续已有单书任务和检查生产状态;不绑定特定研究、图片、TTS、转录或视频渲染供应商。
isYangs/jianying-editor-skill
剪映 (JianYing) AI自动化剪辑的高级封装 API。支持录屏、素材导入、字幕生成、Web 动效合成及项目导出。
geeklee/srt-vox-director
把已经写好的字幕(SRT / 配音稿 / 解说词 / 旁白稿)变成 Vox 风格解释视频的分镜与提示词包——参考图提示词、图生视频提示词、分镜表、关键词台账、视觉圣经、风格选择。只交付文本提示词,不生成任何图片或视频。适用于用户已有成片旁白、想做成分镜或配画面、需要切分镜头与处理时长差值、选定视觉风格,或出图/出片失败后诊断修复(字错了、画面没动、风格跑偏等)。
yuyou-dev/dreamina-cli-skill
A skill your agent uses when an agent needs Dreamina(即梦) generation, task querying, account checks, or login/session operations through the packaged Python wrapper scripts around the dreamina CLI.
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…
Works with
Categories
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。. Ocv Production Bridge is an agent skill from IFRIT-Zhou/One-Click-VidGen.
Ocv Production Bridge fits situations like: media & Creative work in your project.
Run `npx skills add IFRIT-Zhou/One-Click-VidGen --skill ocv-production-bridge -a claude-code`. Or copy the skill folder (plugins/codex_bridge/skills/ocv-production-bridge in IFRIT-Zhou/One-Click-VidGen) into .claude/skills/ocv-production-bridge in your project. Claude Code loads it when a task matches its description.
Run `npx skills add IFRIT-Zhou/One-Click-VidGen --skill ocv-production-bridge -a codex`. Or copy the skill folder (plugins/codex_bridge/skills/ocv-production-bridge in IFRIT-Zhou/One-Click-VidGen) into .agents/skills/ocv-production-bridge in your project. Codex loads it when a task matches its description.
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-production-bridge -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-production-bridge, .gemini/skills/ocv-production-bridge, .github/skills/ocv-production-bridge and .opencode/skills/ocv-production-bridge in your project.
SKILL.md names no scripts, command-line tools or credentials: Ocv Production Bridge is instructions for the agent only. Our summary lists: Python 3.
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.
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.
Ocv Production Bridge 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.
About 2.5k tokens (SKILL.md is roughly 9.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Ocv Production Bridge: Cap Cinematic Demo Generator (CapSoftware/Cap, 23k stars), Edu Math Video (wy51ai/edulab, 1.4k stars), Book Video Factory (bytec-ai/book-video-factory, 321 stars) and Jianying Editor (isYangs/jianying-editor-skill, 214 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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 10, 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.