Podcast
zarazhangrui/personalized-podcast
Generate a podcast episode from content you provide. An agent skill from zarazhangrui/personalized-podcast.
从书名或飞书多维表格中的成稿文案出发,结合微信读书资料与公开点评创作图书带货/书评短视频,并用豆包 TTS、Pexels、Codex 生图和本机 OpenChatCut 完成配音、配图、双语字幕、音效、动效、BGM、可编辑初稿与按需导出。用户提出“根据一本书做带货视频”“读取飞书文案制作图书视频”“写书评口播并自动剪成抖音视频”“仿参考样式做图书推荐短视频”时使用;仅查书、仅写普通书评或无关剪辑…
$ npx skills add Kianzzz/book-sales-video --skill book-sales-video -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Kianzzz/book-sales-video book-sales-video --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "book-sales-video" agent skill from https://github.com/Kianzzz/book-sales-video/tree/main into .claude/skills/book-sales-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "book-sales-video", 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.
$ npx skills add Kianzzz/book-sales-video --skill book-sales-video -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Kianzzz/book-sales-video book-sales-video --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "book-sales-video" agent skill from https://github.com/Kianzzz/book-sales-video/tree/main into .agents/skills/book-sales-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "book-sales-video", 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 Kianzzz/book-sales-video --skill book-sales-video -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Kianzzz/book-sales-video book-sales-video --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "book-sales-video" agent skill from https://github.com/Kianzzz/book-sales-video/tree/main into .cursor/skills/book-sales-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "book-sales-video", 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.
$ npx skills add Kianzzz/book-sales-video --skill book-sales-video -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Kianzzz/book-sales-video book-sales-video --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "book-sales-video" agent skill from https://github.com/Kianzzz/book-sales-video/tree/main into .gemini/skills/book-sales-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "book-sales-video", 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 Kianzzz/book-sales-video book-sales-videoInstalls 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 Kianzzz/book-sales-video --skill book-sales-video -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "book-sales-video" agent skill from https://github.com/Kianzzz/book-sales-video/tree/main into .github/skills/book-sales-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "book-sales-video", 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 Kianzzz/book-sales-video --skill book-sales-video -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Kianzzz/book-sales-video book-sales-video --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "book-sales-video" agent skill from https://github.com/Kianzzz/book-sales-video/tree/main into .opencode/skills/book-sales-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "book-sales-video", 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.
book-sales-video从书名或飞书多维表格中的成稿文案出发,结合微信读书资料与公开点评创作图书带货/书评短视频,并用豆包 TTS、Pexels、Codex 生图和本机 OpenChatCut 完成配音、配图、双语字幕、音效、动效、BGM、可编辑初稿与按需导出。用户提出“根据一本书做带货视频”“读取飞书文案制作图书视频”“写书评口播并自动剪成抖音视频”“仿参考样式做图书推荐短视频”时使用;仅查书、仅写普通书评或无关剪辑…
Book Sales Video is an agent skill from Kianzzz/book-sales-video. 从书名或飞书多维表格中的成稿文案出发,结合微信读书资料与公开点评创作图书带货/书评短视频,并用豆包 TTS、Pexels、Codex 生图和本机 OpenChatCut 完成配音、配图、双语字幕、音效、动效、BGM、可编辑初稿与按需导出。用户提出“根据一本书做带货视频”“读取飞书文案制作图书视频”“写书评口播并自动剪成抖音视频”“仿参考样式做图书推荐短视频”时使用;仅查书、仅写普通书评或无关剪辑不触发。
Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 29 other files, including scripts, reference files and assets (for example `README.md`, `agents/openai.yaml` and `assets/carousel/manifest.json`).
It sits in Media & Creative, covering Text to speech and voice. It works with FFmpeg. The repository describes itself as: 中文图书带货视频 Agent Skill:飞书取稿、书籍核验、配音、配图、双语字幕与 OpenChatCut 自动剪辑. The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 4bbd3eb. 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.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
python3npxbrewFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
pexels.comgithub.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
WEREAD_API_KEYPEXELS_API_KEYDOUBAO_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Book Sales Video loads about 3.2k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 55 tokens; SKILL.md has 582 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); the scripts in this folder are not scanned.
The full file from Kianzzz/book-sales-video at commit 4bbd3eb, republished under its MIT licence (© Kianzzz). 582 words, ~3,226 tokens.
.claude/skills/book-sales-video/SKILL.md (or your agent's skills folder). This skill also uses 24 other files; get the full folder from GitHub.从书籍研究到本地可编辑初稿的一体化流程。只设置一次正常审核:先自动选择最佳角度并完成口播和语义分镜,用户确认后自动完成配音、画面、字幕、音效、动效、BGM、时间线和质检,不再逐项确认。
scripts/doubao_tts.py,最终只产生一个 audio/narration.wav。长稿允许脚本内部按句界请求并合并,但不能按镜头人工生成多份配音。book,不根据书名或文案改关键词。library:sound:mechanical-clicking-loop,每个有效峰值硬切一张不同封面;最后经短光溶进入主书揭示。library:sound:cash-register-success,视觉重音与音效锚点对齐。assets/visual-style/approved-rough-paper-oil-v3.png 为主锚点。每个新环境第一次触发本 Skill 时,先读取当前项目的 AGENTS.md,再运行只读预检;使用飞书路线时把用户提供的 Base URL 一并传入,实测机器人身份、Base 权限和文案字段,不以“已经配置过”代替验证:
python3 "${CODEX_HOME:-$HOME/.codex}/skills/book-sales-video/scripts/check_environment.py" --json
python3 "${CODEX_HOME:-$HOME/.codex}/skills/book-sales-video/scripts/check_environment.py" \
--json --base-url "<用户提供的飞书 Base URL>" \
--lark-profile "<profile>" --script-field "<文案字段名>"
python3 "${CODEX_HOME:-$HOME/.codex}/skills/book-sales-video/scripts/openchatcut_mcp.py" status读取预检输出中的 checks、gates 和 actions。缺少依赖、环境变量、应用、Skill、飞书 scope 或资源协作者权限时,先用中文说明“缺什么、影响哪个阶段、如何安装或授权、安装后怎样复验”,提供预检给出的准确命令或官方地址;涉及账号登录、App Secret、API Key 时引导用户在本机安全输入,禁止要求粘贴到对话。只允许安装用户当前路线真正需要的项目,安装或授权完成后重跑同一预检。对应 gate 未通过前不得进入该阶段,也不得伪装已经完成。
若任务使用飞书文案输入,还要确认 larkBase.status 为 ready。App Secret 只允许通过 lark-cli config init --app-secret-stdin 写入本机安全配置;禁止出现在对话、命令参数、工作目录或日志中。
预检发现缺失项时,只引导安装当前路线需要的能力,并在完成后复验:
python3 -m pip install requestsbrew install ffmpeg;其他系统使用对应包管理器,并确认 ffmpeg、ffprobe 可执行。npx @larksuite/cli@latest install;随后运行 lark-cli config init --new,通过本机交互配置企业自建应用。base:field:read、base:record:read、base:table:read、base:view:read,并把机器人加入目标多维表格协作者。npx skills add Tencent/WeChatReading -g,再按该 Skill 的说明安全配置 WEREAD_API_KEY。https://www.pexels.com/api/ 申请只供本机使用的 API Key。https://github.com/0xsline/OpenChatCut/releases 安装桌面版;macOS 放入 /Applications。首次启动后打开目标工程,再复验本地 MCP 工具。涉及网页审批、账号登录或密钥录入时,给出最小权限和操作入口后等待用户完成;不要代替用户公开凭据,也不要要求把 Secret 或 API Key 发到对话中。
OpenChatCut 状态命令会在需要时启动 /Applications/OpenChatCut.app,自动发现随机 localhost 端口,并验证 /api/external-mcp/mcp。不得把某次端口写死到 Skill 或任务状态。
重启后的工程连接检查: OpenChatCut 重启时默认停在“我的工程”列表。此状态只会暴露项目管理工具,read_timeline、edit_item、edit_track 等完整编辑工具不会注册,并可能误报“工程未连接”。对已有项目,必须先核对任务状态中保存的 projectId 与工程名,再让用户或 Computer Use 明确打开该工程;随后重新运行 list-tools 和只读 read_project,确认返回的 projectId、timelineId 与任务状态完全一致,才允许写入。连接失败、点击位置不确定或当前工程 ID 不一致时立即停止,不点击“新建工程”,不调用 create_project,不创建替代项目。
按阶段处理缺失项:
| 阶段 | 必需 | 缺失时处理 |
|---|---|---|
| 飞书文案 | lark-cli、可用的默认或命名 profile、机器人为表格协作者、Base 只读权限 | 停止读取并报告缺失的 scope 或资源权限;不改用浏览器复制、不猜测文案 |
| 研究 | weread-skills、WEREAD_API_KEY | 停止事实研究,不用未知网页代替 |
| 配音 | requests、豆包密钥、资源 ID、音色 | 停止配音,不回退编辑器音色 |
| 开场 | PEXELS_API_KEY | 文案可继续,但不得伪装已取得视频 |
| 配图 | Codex image_gen | 保存分镜与提示词,明确缺口 |
| 本地初稿 | OpenChatCut Desktop、本地 MCP 必需工具、可导入素材 | 修复本地应用或导入后再装配,不回退云端 |
密钥只从安全环境或钥匙串读取,不写入工作目录或日志。豆包变量为 DOUBAO_API_KEY、DOUBAO_TTS_RESOURCE_ID、DOUBAO_TTS_SPEAKER;Pexels 为 PEXELS_API_KEY;微信读书为 WEREAD_API_KEY。
使用项目 AGENTS.md 的 work/ 约定,单次任务目录至少包含:
research.md script.md
storyboard.json shot-plan.json
visual-style.json voice-timeline.json
timeline-plan.json subtitle-pairs.json
asset-manifest.json quality_check.json
review_report.md visuals/
audio/状态文件只保存当前有效状态,并共享同一 stateRevision、projectId、timelineId 和 timeline fps。
当用户提供飞书 Base 链接、记录链接,或明确要求“读取飞书文案制作”时,先读取文案,再进入书籍事实核对和分镜。公开版不内置任何用户表格地址、应用 ID、字段 ID 或记录 ID;首次使用时由用户提供 Base URL、profile 名称和文案字段名:
Base URL: <用户提供>
profile: <用户本机的默认配置或命名 profile>
文案字段: <用户提供,示例:文案仿写.输出结果>读取规则:
base +url-resolve 解析链接,不从 URL 字符串猜测资源类型;确认 base_token、table_id 和 view_id。base +field-list,动态核对字段。界面显示名、口语别名和真实字段名可能不同,必须以实时字段列表返回的名称或字段 ID 为准,不能把某个用户的字段 ID 写死到 Skill。视频标题、书名、作者 和用户指定的文案字段,并限定到链接指定的 view;字段不存在时先让用户确认映射,不读取无关字段或附件。视频标题 精确匹配 → 书名 精确匹配。匹配前只允许去除书名号和首尾空白,不做模糊包含匹配。视频标题、书名、作者 和 record ID,让用户选择;禁止默认取第一条、最长文案或最新文案。script.md,并在 research.md 记录脱敏后的数据源说明、table/view/record ID、字段名和读取时间,不记录完整私有 URL、应用密钥或访问令牌。推荐只读调用:
lark-cli --profile "<profile>" base +url-resolve --url "<Base URL>" --as bot
lark-cli --profile "<profile>" base +field-list \
--base-token "<base_token>" --table-id "<table_id>" --as bot
lark-cli --profile "<profile>" base +record-list \
--base-token "<base_token>" --table-id "<table_id>" --view-id "<view_id>" \
--field-id "视频标题" --field-id "书名" --field-id "作者" \
--field-id "<文案字段名>" --format json --as bot若报 missing_scope,只申请 base:field:read、base:record:read、base:table:read、base:view:read;若报资源无权访问,确认机器人已作为协作者加入当前 Base。bot 身份禁止执行用户 OAuth 登录。
weread-skills,搜索并定位书籍;飞书输入路线优先使用已选记录的 书名,只有重名或版本歧义会影响内容时才请用户选择。bookId,事实与解释分开写入 research.md。飞书输入路线中,步骤 3–5 只用于事实核验和视觉理解,不重写或替换已读取文案,也不再生成候选文案角度。
此阶段读取 references/copywriting-and-storyboard.md。
严格读取 references/reference-copy-style.md 和 references/copywriting-and-storyboard.md。用户另外提供个人风格档案或禁用表达清单时也要读取;已明确提供但不可读时停止创作并报告准确路径,用户未提供时不构成阻塞。
默认结构:
上述默认结构只约束新创作文案。飞书输入路线直接使用已选记录的全文:保留段落、语序和措辞,只基于该全文生成语义分镜、双语字幕草稿和预计画面数量。若文案中的书名或作者与微信读书核验结果冲突,停止并明确指出差异,不静默修正原文。
完成 script.md、storyboard.json 和 draft 状态的 subtitle-pairs.json。分镜按语义、动作、场景或情绪变化切,不按句号平均切图。把主角度、评分摘要、完整口播、分镜摘要、预计图片数量和后续自动生成范围一次性交给用户审核。
用户确认后即授权该视频的完整本地制作。若用户不满意,展示候选角度并按其选择重写;重写完成后直接制作,不再增加确认关卡。
新任务且状态中没有项目时,才用本地桥接调用一次 create_project,明确指定 1080×1920、30fps,并保存真实项目与时间线 ID;继续已有任务时必须重连保存的同一工程,禁止调用 create_project。禁止沿用已确认失败的项目,也禁止在后续阶段再次创建替代项目。
将确认稿保存为 audio/narration.txt,只运行一次:
python3 "${CODEX_HOME:-$HOME/.codex}/skills/book-sales-video/scripts/doubao_tts.py" \
--text-file audio/narration.txt --output audio/narration.wav \
--report audio/narration.wav.json用 ffmpeg/ffprobe 与试听证据检查首尾、第一二句边界、最长句间停顿、段落边界和结尾。异常时先修剪或重跑这一条完整配音,未通过不得生图或装配。
通过 OpenChatCut 本地上传会话导入唯一 WAV 到 A1。不得调用编辑器 TTS,也不得重新拆成多条旁白资产。
优先读取同一次 doubao_tts.py 生成的句段时间账本,从同一 audioAssetId 派生语义 voiceUnitId,生成 voice-timeline.json。该账本记录每段修剪后的真实 PCM 时长及拼接静音,作为可复核对齐证据;不依赖 OpenChatCut 转录。仅在账本缺失时才尝试已获授权的 ASR;不能伪造词时间。
具体 MCP 调用、导入和轨道结构读取 references/openchatcut-build.md。
scripts/search_pexels_videos.py --page 1 --per-page 20,固定 book、竖屏、中等尺寸;实际查看候选后选择,记录 Pexels 页面、创作者、文件和归属。《书名》 与 作者 / 著;从揭示开始持续到视频结束,正文换图时文字内容、位置和样式保持不变。揭示段若口播仅重复书名作者,顶部常驻标题可替代底部重复字幕,避免同屏出现两套相同信息。shot-plan.json。scripts/validate_shot_plan.py shot-plan.json,通过后才调用 image_gen。执行前读取 references/openchatcut-build.md、references/editing-effects-and-rhythm.md 和 references/bilingual-subtitles.md。
scripts/openchatcut_mcp.py,每次动态发现本机端口;工具参数以当前 list-tools schema 为准。type:"image" 放到 V2,再用实例关键帧定位;不得以扁平预合成或全画布 MG 替代。最终画面以封面占画幅约 52%–60% 宽为起点、水平居中、书名下方留一段正常空白、左右均留白为验收,而不是只相信 CSS 或资产的自然尺寸。以当前已验证的竖屏封面为基线:x=0、y≈8、scale≈0.56,但每本书都必须以实际渲染画面微调。opacity 0→1、scale 0.42→0.60→最终值、y 16→最终值,之后保持静止;禁止持续呼吸、横移、旋转或额外复杂动效。收银成功音的重音落在该入场开始处。x=0、y=0 固定,scale 从 1.02(起点)缓慢到 1.085(片段 55% 处),再柔和回落到 1.035(片段末尾)。不得在同一张图中重复第二次呼吸,也不得为赶在片段末尾归零而突然缩小。优先使用本地已验证的 builtin:zoom 慢推近或等价关键帧;必须检查放大后主体和字幕安全区没有被裁坏。library:sound:mechanical-clicking-loop 一段连续资产;揭示音效使用 library:sound:cash-register-success 一次。不得重新生成替代音效。validateOnly,再原子提交;请求超时先读回项目判断是否已写入,禁止盲目重复。先结构、后画面、再声音。quality_check.json 至少包含并通过:
bookFacts、voiceContinuity、timelineStructure、carouselRhythm、bookReveal、bodyMotion、transitions、subtitles、bgmMix、visualStyle、frameReview。
必须逐项验证:
voiceUnitId。shot-plan.json。read_project/read_timeline 读回结构,并检查开场、轮播中点、主书揭示的入场/中段/稳定三帧、每个正文边界和最后一帧。主书封验收同时要求:V2 存在一条 kind:"image" 的可见片段、片段可直接在时间线上选中,且渲染画面中封面居中、不裁边、不压住书名作者。任何结构性修改都会让旧检查变为 stale。修复后必须重新读项目、抽查画面和试听。运行:
python3 scripts/validate_subtitle_cards.py subtitle-pairs.json --voice-timeline voice-timeline.json --strict
python3 scripts/validate_delivery_state.py .全部通过后交付:本机 OpenChatCut 中可编辑项目、文案、字幕对照、分镜、状态文件和 review_report.md。默认停在可编辑初稿供用户检查;用户明确要求或确认最终版后才调用本地导出,并验证导出历史与实际文件。
/Applications/OpenChatCut.app 缺失并停止本地装配。list-tools,按当前 schema 调整调用;不回退旧云端接口。blocked-not-deliverable,不得称为“可审核初稿”。scripts/openchatcut_mcp.pyscripts/check_environment.pyscripts/doubao_tts.pyscripts/search_pexels_videos.pyscripts/validate_shot_plan.py、scripts/validate_subtitle_cards.py、scripts/validate_delivery_state.py© Kianzzz, MIT. 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 24 other files (scripts, references, assets) in the repository root of Kianzzz/book-sales-video.
Open the folder on GitHubat commit 4bbd3eb
Book Sales Video 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 |
|---|---|---|---|---|---|---|
| Book Sales Video this skillKianzzz/book-sales-video | 218 | — | ~3.2k | Automated safety check: Pass | MIT | |
| Podcastzarazhangrui/personalized-podcast | 438 | — | ~2.3k | Automated safety check: Notes | None | |
| Video Assemblezenstory-ai/video-recap-skills | 561 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Video Cutzenstory-ai/video-recap-skills | 561 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Render Value Propgooseworks-ai/goose-skills | 1.2k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Orchardcore Video ProducerOrchardCMS/OrchardCore | 8.2k | — | ~2k | Automated safety check: Pass | BSD-3-Clause |
zarazhangrui/personalized-podcast
Generate a podcast episode from content you provide. An agent skill from zarazhangrui/personalized-podcast.
zenstory-ai/video-recap-skills
合成视频解说最终成片:把旁白音频铺到源视频上,按旁白窗口压低原声,生成 SRT / ASS 字幕并可烧录, 最后做响度标准化。作为最终合成阶段使用。输入源视频、ttsmeta.json 与旁白位置; 输出 recap 成片和字幕。触发词:视频合成、混音、字幕、压字幕、assemble video、mux、ducking、subtitles、成片。
zenstory-ai/video-recap-skills
把长视频按 Agent 选择的原片区间剪成短片。作为两阶段创作流程中的剪辑环节,读取 clipplan.json 与源视频, 输出 editedsource.mp4;随后 Agent 按输出时间线写 narration.json。支持单视频与多视频(sources manifest)拼剪, 本工具不读取、不映射旁白。
gooseworks-ai/goose-skills
Render a designed 'value prop' video from a config — 3-5 noun-phrase benefit claims (<=4 words each) revealed sequentially over per-SKU product visuals, one crisp editorial frame per claim (hook…
OrchardCMS/OrchardCore
Produces narrated Orchard Core videos (feature walkthroughs, module overviews, pull request demos) with one unified look and specification - 1080p, Orchard Core logo, colors and fonts, the same…
Alisa0808/vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all…
Works with
Categories
从书名或飞书多维表格中的成稿文案出发,结合微信读书资料与公开点评创作图书带货/书评短视频,并用豆包 TTS、Pexels、Codex 生图和本机 OpenChatCut 完成配音、配图、双语字幕、音效、动效、BGM、可编辑初稿与按需导出。用户提出“根据一本书做带货视频”“读取飞书文案制作图书视频”“写书评口播并自动剪成抖音视频”“仿参考样式做图书推荐短视频”时使用;仅查书、仅写普通书评或无关剪辑…. Book Sales Video is an agent skill from Kianzzz/book-sales-video.
Book Sales Video fits situations like: tasks that involve Text to speech and voice.
Run `npx skills add Kianzzz/book-sales-video --skill book-sales-video -a claude-code`. Or copy the skill folder (the Kianzzz/book-sales-video repository) into .claude/skills/book-sales-video in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Kianzzz/book-sales-video --skill book-sales-video -a codex`. Or copy the skill folder (the Kianzzz/book-sales-video repository) into .agents/skills/book-sales-video 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 Kianzzz/book-sales-video --skill book-sales-video -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/book-sales-video, .gemini/skills/book-sales-video, .github/skills/book-sales-video and .opencode/skills/book-sales-video in your project.
Going by SKILL.md and its folder, Book Sales Video needs the command-line tools its instructions call (python3, npx and brew) and credentials named WEREAD_API_KEY, PEXELS_API_KEY and DOUBAO_API_KEY. Our summary lists: Python 3; Node.js; A credential in WEREAD_API_KEY; A credential in PEXELS_API_KEY.
SKILL.md names 2 domains. In commands or code: pexels.com and github.com; the agent is likely to contact these when it follows the instructions. 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Book Sales Video is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 11k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Book Sales Video: Podcast (zarazhangrui/personalized-podcast, 438 stars), Video Assemble (zenstory-ai/video-recap-skills, 561 stars), Video Cut (zenstory-ai/video-recap-skills, 561 stars) and Render Value Prop (gooseworks-ai/goose-skills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Kianzzz (a GitHub user) maintains it in Kianzzz/book-sales-video, which has 218 GitHub stars. The repository was last updated on August 10, 2026.
Source: Kianzzz/book-sales-video on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.