SKILLS & AGENTS/Skill 与 Agent·CLAUDE-SKILL

video-talkcraft

Vincentwei1021/video-talkcraft

109 张动效卡 + 字级同步，口播稿自动变成电影感解说视频Drop a script and voiceover, get a cinematic explainer video with word-level sync and 109 motion recipe cards.

一个让AI助手帮你做口播视频的工具，自动配音、配画面、生成成品。Turn a script and voiceover into a cinematic explainer video with word-level sync, 109 motion recipe cards, and an anti-slideshow camera system.

打开仓库Open repository 官网Homepage 上升中Rising

怎么装：Install: npx skills add Vincentwei1021/video-talkcraft

02 / 现在的位置02 / Why now

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

04 OCT 202604 OCT 2026

增长GROWTH

+2.7%+2.7%

1.3k → 1.4k stars · 3 个快照1.3k → 1.4k stars · 3 snapshots

状态STATUS

持续活跃Active

项目在GitHub上获得1384颗星，说明社区认可度高。Active project with 1384 stars and recent commits

03 / 它能帮你做什么03 / What it helps you do

它能帮你做成什么What it helps you do

01
Sync voiceover to video at the word level
02
Generate cinematic explainer videos from a script and audio
03
Apply 109 motion recipe cards for visual variety
04
Use an anti-slideshow camera system for dynamic shots
05
Render final video with Remotion

04 / 安装04 / Install

怎么装How to install

SKILLS-CLI

$

README 里给出的安装方式。The installation method given in the README.

GIT-CLONE

$

README 里给出的安装方式。The installation method given in the README.

两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.

使用 `npx skills add Vincentwei1021/video-talkcraft` 安装，或通过git克隆并手动链接到Claude Code的skills目录。Install via `npx skills add Vincentwei1021/video-talkcraft` or clone the repo and symlink it into your Claude Code skills directory.

05 / 限制与风险05 / Limits and risk

限制与风险Limits and risk

风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

需检查Needs review

01需要 API KeyREQUIRES API KEY: 是Yes
02需要本地环境NEEDS LOCAL RUNTIME: 是Yes
03需要 DockerNEEDS DOCKER: 未在文档中发现Not found in the docs
04难度DIFFICULTY: 需要本地环境Needs a local runtime

PROVENANCE · 这些结论的依据是什么Where these conclusions come from

来源 URLSource URL: https://github.com/Vincentwei1021/video-talkcraft
原始数据哈希Raw data hash: b1bc21d86477c0149d501a1f7005c9d6
解析时间Parsed at: 2026-10-06T23:27:53.146Z
最后一次验证Last verified: 2026-10-06T22:09:57.556Z
增长测量时间Growth measured: 2026-10-06T23:30:22.083Z
发现查询Discovery queries: focus:design:repo:design-agent, focus:design:repo:design-skill
分类来源Category source: rules
焦点Focus

静态扫描STATIC SCAN

01控制浏览器Controls a browserreadme

- 🌐 **网页拍摄不贴图**——网页素材不再静态贴屏，改为镜头滚动 / 巡游 / 放大镜 / 划重点"拍"出来，坐标全吃 Playwright 实测（→ SKILL.md §③、`references/shot-design.md` §2④）。

02控制浏览器Controls a browserSKILL.md

`纯动效`——如"B-roll 打底 + 截图证据卡"。新闻/信息类话题证据优先：Playwright 实时截图比泛用 B-roll 更有信息量。

静态扫描发现两项中等风险：控制浏览器（Playwright 实时截图）。未发现高风险项。The static scan flagged medium-risk browser control via Playwright, used for live screenshot capture in shot design. Review the Playwright usage in `references/shot-design.md` before running in production.

这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.

完整解析证据 JSONFull parse evidence JSON

{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "readme: …video-shotcraft) 系列的口播视频篇：一个把 Claude Code / Codex 变成口播视频动效工作室的 AI agent…"
    }
  ],
  "apiKey": "制 `.env.example` 为 `.env`，填写 `FISH_AUDIO_API_KEY`。`FISH_AUDIO_REFERENCE_ID` 可填音色库中的音色 ID",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 1,
      "ai-tools": 1,
      "dev-tools": 0,
      "indie-web": 0,
      "skill-agent": 11,
      "productivity": 0
    },
    "primary": "skill-agent",
    "secondary": "claude-skill"
  },
  "localRuntime": "stat 文件）：`- 素材：V（public/broll/gpu.mp4）· 图（public/stills/a.jpg, public/sti",
  "skillMdTotal": 1,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 0,
    "media": 9,
    "design": 10,
    "browser": 2,
    "devtool": 0,
    "security": 0,
    "marketing": 0,
    "productivity": 1
  },
  "classification": [
    {
      "signal": "1 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "README describes a Claude / Agent Skill",
      "weight": 0.7
    },
    {
      "signal": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme",
    "SKILL.md"
  ],
  "skillMdFetched": 1
}