Menu

Not in the top 1,000 by GitHub stars

chenyuxiaojin/video-agent-skills

Multi-agent Claude Code skills that turn a topic into a DaVinci/CapCut-ready video timeline — research to publish.

WritingResearch

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

live-sharing-writer/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → fc80890c7578

No earlier version was observed for comparison.

Compare on GitHub

video-agent-editor/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fc80890c7578

No earlier version was observed for comparison.

Compare on GitHub

video-agent-jianying-editor/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → fc80890c7578

No earlier version was observed for comparison.

Compare on GitHub

video-agent-operator/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fc80890c7578

No earlier version was observed for comparison.

Compare on GitHub

video-agent-producer/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fc80890c7578

No earlier version was observed for comparison.

Compare on GitHub

video-agent-publisher/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fc80890c7578

No earlier version was observed for comparison.

Compare on GitHub

video-agent-researcher/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → fc80890c7578

No earlier version was observed for comparison.

Compare on GitHub

video-agent-storyboarder/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fc80890c7578

No earlier version was observed for comparison.

Compare on GitHub

video-agent-visual/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → fc80890c7578

No earlier version was observed for comparison.

Compare on GitHub

video-agent-voice/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fc80890c7578

No earlier version was observed for comparison.

Compare on GitHub

video-agent-writer/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → fc80890c7578

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit fc80890c7578279279bee301370a9f58d8123ec0

15GitHub stars
4stars in 7 days
11skills in this repository
0commits in 30 days

Heat

4.8
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Nov 6, 202615

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

live-sharing-writer

When your agent uses it

Use when user wants to prepare a live sharing script, livestream talk, or presentation speech. Triggers include "写分享稿", "准备直播", "做一个分享", "帮我写演讲稿", "直播分享".

What it loads into context

Frontmatter

56 tokens

Always available to the agent

SKILL.md

1,753 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 职责边界
  2. 与视频编剧（04-video-agent-writer）的区别
  3. 输入 → 输出
  4. 执行步骤
  5. 逐字稿格式
  6. 字数与时长对应表
  7. 质量检查
  8. 依赖

Files

  • SKILL.mdcore5,856 bytes
Read SKILL.md

# 直播分享撰稿人（Live Sharing Writer）

## 职责边界

撰稿人只负责文字内容，围绕演讲者本人的经历和观点展开。

- ✅ 逐字稿撰写（口语化，可直接说的文字）
- ✅ 结构设计（开场、主体、升华、收尾）
- ✅ 轻量标记（互动点、操作点、节奏休息点）
- ✅ 朗读检查提醒
- ❌ 外部资料调研（素材全来自演讲者）
- ❌ 画面设计 / 分镜
- ❌ PPT 制作
View the complete source on GitHub

Skills included

  • live-sharing-writer
  • video-agent-editor
  • video-agent-jianying-editor
  • video-agent-operator
  • video-agent-producer
  • video-agent-publisher
  • video-agent-researcher
  • video-agent-storyboarder
  • video-agent-visual
  • video-agent-voice
  • video-agent-writer

Repository facts

License
MIT
Created
Feb 7, 2026
Last pushed
Jun 8, 2026
Forks
2
Open issues
0
Project activity
Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 34 notes
  • video-agent-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-jianying-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-jianying-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-jianying-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-jianying-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-jianying-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-jianying-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-jianying-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-jianying-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-jianying-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-jianying-editor/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-producer/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-producer/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-producer/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • video-agent-producer/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 124 signals by file

video-agent-editor/scripts/generate_placeholders.py

  • Executable scriptline 1
    Executable file

video-agent-editor/scripts/import_subtitles.py

  • Executable scriptline 1
    Executable file

video-agent-editor/scripts/import_to_resolve.py

  • Executable scriptline 1
    #!/usr/bin/env python3

video-agent-jianying-editor/SKILL.md

  • Network accessline 74
    git clone https://github.com/sun-guannan/VectCutAPI.git
  • Network accessline 86
    source venv-capcut/bin/activate python capcut_server.py # 服务启动后监听 http://localhost:9001
  • Network accessline 88
    # 服务启动后监听 http://localhost:9001
  • Network accessline 144
    CAPCUT_API = "http://localhost:9001"
  • Network accessline 158
    # ── 2. 创建草稿 ── resp = requests.post(f"{CAPCUT_API}/create_draft", json={
  • Network accessline 159
    resp = requests.post(f"{CAPCUT_API}/create_draft", json={
  • Network accessline 165
    # ── 3. 添加语音到主音频轨 ── voiceover_path = os.path.abspath(f"{project_dir}/audio/voiceover.mp3") requests.post(f"{CAPCUT_API}/add_audio", json={
  • Network accessline 166
    voiceover_path = os.path.abspath(f"{project_dir}/audio/voiceover.mp3") requests.post(f"{CAPCUT_API}/add_audio", json={     "draft_id": draft_id,
  • Network accessline 167
    requests.post(f"{CAPCUT_API}/add_audio", json={
  • Network accessline 196
    # 添加到主视频轨     requests.post(f"{CAPCUT_API}/add_video", json={
  • Network accessline 197
    requests.post(f"{CAPCUT_API}/add_video", json={
  • Network accessline 208
    subtitles = parse_srt(srt_path)     for sub in subtitles:         requests.post(f"{CAPCUT_API}/add_subtitle", json={
  • Network accessline 209
    for sub in subtitles:         requests.post(f"{CAPCUT_API}/add_subtitle", json={             "draft_id": draft_id,
  • Network accessline 210
    requests.post(f"{CAPCUT_API}/add_subtitle", json={
  • Network accessline 221
    # ── 6. 保存草稿 ── resp = requests.post(f"{CAPCUT_API}/save_draft", json={
  • Network accessline 222
    resp = requests.post(f"{CAPCUT_API}/save_draft", json={

video-agent-operator/scripts/analyze_competitors.py

  • Executable scriptline 1
    Executable file

video-agent-operator/scripts/analyze_performance.py

  • Executable scriptline 1
    Executable file

video-agent-operator/scripts/generate_topics.py

  • Executable scriptline 1
    Executable file

video-agent-producer/scripts/pipeline_manager.py

  • Executable scriptline 1
    #!/usr/bin/env python3

video-agent-publisher/scripts/compile_sources_list.py

  • Executable scriptline 1
    #!/usr/bin/env python3

video-agent-publisher/scripts/generate_metadata.py

  • Executable scriptline 1
    #!/usr/bin/env python3

video-agent-researcher/scripts/compile_sources.py

  • Executable scriptline 1
    #!/usr/bin/env python3

video-agent-researcher/scripts/generate_outline.py

  • Executable scriptline 1
    #!/usr/bin/env python3

video-agent-researcher/scripts/web_search_collector.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Network accessline 37
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36"     }     req = urllib.request.Request(url, headers=headers)
  • Network accessline 38
    }     req = urllib.request.Request(url, headers=headers)     with urllib.request.urlopen(req, timeout=timeout) as resp:
  • Network accessline 39
    req = urllib.request.Request(url, headers=headers)
  • Network accessline 40
    with urllib.request.urlopen(req, timeout=timeout) as resp:

video-agent-researcher/scripts/youtube_transcript_collector.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Network accessline 112
    if len(sys.argv) < 3:         print("用法: python youtube_transcript_collector.py <video_url> <output_dir>")         print("示例: python youtube_transcript_collector.py 'https://youtube.com/watch?v=xxx' ./materials")
  • Network accessline 113
    print("用法: python youtube_transcript_collector.py <video_url> <output_dir>")         print("示例: python youtube_transcript_collector.py 'https://youtube.com/watch?v=xxx' ./materials")         print("\n支持多个 URL，用逗号分隔")
  • Network accessline 114
    print("示例: python youtube_transcript_collector.py 'https://youtube.com/watch?v=xxx' ./materials")

video-agent-storyboarder/SKILL.md

  • Access to secretsline 171
    [Credential-related source omitted]

video-agent-storyboarder/scripts/generate_storyboard.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 13
    [Credential-related source omitted]
  • Network accessline 30
    GEMINI_MODEL = "gemini-2.5-flash" GEMINI_API_URL = "https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent"
  • Network accessline 31
    GEMINI_API_URL = "https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent"
  • Access to secretsline 62
    [Credential-related source omitted]
  • Access to secretsline 64
    [Credential-related source omitted]
  • Access to secretsline 235
    [Credential-related source omitted]
  • Access to secretsline 236
    [Credential-related source omitted]
  • Access to secretsline 237
    [Credential-related source omitted]
  • Access to secretsline 253
    [Credential-related source omitted]

video-agent-visual/SKILL.md

  • Access to secretsline 147
    [Credential-related source omitted]
  • Network accessline 149
    | 环境变量 | 用途 | |----------|------| | GPTIMG2_BASE_URL | GPTIMG2 服务基址（如 `https://api.chatgpt-code.com`，**末尾不带 `/v1`**，脚本自动拼 `/v1/images/generations`） |
  • Network accessline 150
    |----------|------| | GPTIMG2_BASE_URL | GPTIMG2 服务基址（如 `https://api.chatgpt-code.com`，**末尾不带 `/v1`**，脚本自动拼 `/v1/images/generations`） | | GPTIMG2_API_KEY | GPTIMG2 API 密钥 |
  • Network accessline 151
    | GPTIMG2_BASE_URL | GPTIMG2 服务基址（如 `https://api.chatgpt-code.com`，**末尾不带 `/v1`**，脚本自动拼 `/v1/images/generations`） |
  • Access to secretsline 152
    [Credential-related source omitted]
  • Access to secretsline 161
    [Credential-related source omitted]

video-agent-visual/scripts/align_timestamps.py

  • Executable scriptline 1
    Executable file

video-agent-visual/scripts/generate_image.py

  • Executable scriptline 1
    Executable file

video-agent-visual/scripts/generate_images.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Network accessline 12
    [Credential-related source omitted]
  • Access to secretsline 12
    [Credential-related source omitted]
  • Network accessline 13
    GPTIMG2_BASE_URL — GPTIMG2 服务基址（如 https://api.chatgpt-code.com，末尾不带 /v1）
  • Access to secretsline 14
    [Credential-related source omitted]
  • Access to secretsline 31
    [Credential-related source omitted]
  • Access to secretsline 45
    [Credential-related source omitted]
  • Access to secretsline 49
    [Credential-related source omitted]
  • Access to secretsline 50
    [Credential-related source omitted]
  • Access to secretsline 59
    [Credential-related source omitted]
  • Access to secretsline 104
    [Credential-related source omitted]
  • Access to secretsline 125
    [Credential-related source omitted]
  • Network accessline 137
    for attempt in range(max_retries):         try:             resp = requests.post(gen_url, headers=headers, json=payload, timeout=180)
  • Network accessline 138
    try:             resp = requests.post(gen_url, headers=headers, json=payload, timeout=180)             resp.raise_for_status()
  • Network accessline 139
    resp = requests.post(gen_url, headers=headers, json=payload, timeout=180)
  • Network accessline 144
    image_url = resp_data["data"][0]["url"]             img_resp = requests.get(image_url, timeout=120)
  • Network accessline 145
    img_resp = requests.get(image_url, timeout=120)
  • Access to secretsline 220
    [Credential-related source omitted]
  • Access to secretsline 221
    [Credential-related source omitted]
  • Access to secretsline 222
    [Credential-related source omitted]
  • Access to secretsline 264
    [Credential-related source omitted]

video-agent-visual/scripts/generate_report.py

  • Executable scriptline 1
    Executable file

video-agent-visual/scripts/parse_storyboard.py

  • Executable scriptline 1
    Executable file

video-agent-visual/scripts/search_stock.py

  • Executable scriptline 1
    Executable file

video-agent-visual/scripts/search_web_images.py

  • Executable scriptline 1
    Executable file

video-agent-voice/SKILL.md

  • Network accessline 201
    <speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="zh-CN">
  • Access to secretsline 282
    [Credential-related source omitted]
  • Access to secretsline 284
    [Credential-related source omitted]

video-agent-voice/scripts/build_emotion_map.py

  • Executable scriptline 1
    Executable file

video-agent-voice/scripts/edge_tts_generate.py

  • Executable scriptline 1
    #!/usr/bin/env python3

video-agent-voice/scripts/elevenlabs_tts.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 24
    [Credential-related source omitted]
  • Access to secretsline 26
    [Credential-related source omitted]
  • Access to secretsline 28
    [Credential-related source omitted]
  • Access to secretsline 29
    [Credential-related source omitted]
  • Access to secretsline 85
    [Credential-related source omitted]
  • Network accessline 91
    url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}"
  • Network accessline 102
    # 使用 curl 调用 API（避免额外 Python 依赖）
  • Access to secretsline 106
    [Credential-related source omitted]
  • Access to secretsline 162
    [Credential-related source omitted]
  • Access to secretsline 184
    [Credential-related source omitted]
  • Access to secretsline 192
    [Credential-related source omitted]
  • Access to secretsline 216
    [Credential-related source omitted]
  • Access to secretsline 228
    [Credential-related source omitted]
  • Access to secretsline 231
    [Credential-related source omitted]

video-agent-voice/scripts/extract_plain_text.py

  • Executable scriptline 1
    #!/usr/bin/env python3

video-agent-voice/scripts/generate_subtitles.py

  • Executable scriptline 1
    #!/usr/bin/env python3

video-agent-voice/scripts/minimax_tts.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 17
    [Credential-related source omitted]
  • Network accessline 38
    API_BASE = "https://api.minimaxi.com/v1"
  • Access to secretsline 41
    [Credential-related source omitted]
  • Access to secretsline 42
    [Credential-related source omitted]
  • Access to secretsline 44
    [Credential-related source omitted]
  • Access to secretsline 45
    [Credential-related source omitted]
  • Access to secretsline 51
    [Credential-related source omitted]
  • Access to secretsline 58
    [Credential-related source omitted]
  • Access to secretsline 63
    [Credential-related source omitted]
  • Access to secretsline 81
    [Credential-related source omitted]
  • Access to secretsline 109
    [Credential-related source omitted]
  • Access to secretsline 190
    [Credential-related source omitted]
  • Access to secretsline 203
    [Credential-related source omitted]
  • Access to secretsline 230
    [Credential-related source omitted]
  • Access to secretsline 249
    [Credential-related source omitted]
  • Access to secretsline 269
    [Credential-related source omitted]
  • Access to secretsline 276
    [Credential-related source omitted]
  • Access to secretsline 300
    [Credential-related source omitted]
  • Access to secretsline 302
    [Credential-related source omitted]
  • Access to secretsline 319
    [Credential-related source omitted]
  • Access to secretsline 328
    [Credential-related source omitted]

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Declared and executed: 4 facts
Signal confidence: 124 facts

and 74 more

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md live-sharing-writer/SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md live-sharing-writer/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md live-sharing-writer/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md live-sharing-writer/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md live-sharing-writer/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md live-sharing-writer/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

zenstory-ai/drama-skills

AI 短剧与漫剧制作 skill 合集：小说改剧本、角色设定三视图、分镜脚本、生图/生视频提示词与成片审片，适配 Claude Code / Codex 等 ｜ Open-source agent skills for AI short dramas & moti…

3.9kGitHub stars

aliang2052/aliang-skills

阿亮开源的 Skills 合集：短剧成片 / 电商详情图 / 儿童故事 / 有声绘本 / 配音 / 多人播客。一句话触发，AI 走完整 AIGC 流程。

30GitHub stars

SallyRS/video-director

Claude Code skill that directs short videos from brief to render: design options, storyboard, motion spec, HyperFrames build and render checks. Rules measured from 59 films; 8 vid…

24GitHub stars

mehbylabs/creator-skills

Creator agent skills (image, video, voice incl. Arabic dialects, thumbnails, ads, explainers) that work with whatever you have — Higgsfield, Gemini, OpenAI, ElevenLabs, Azure, Ant…

7GitHub stars

NarratorAI-Studio/narrator-ai-cli-skill

AI 电影/短剧解说视频自动生成（AI 解说大师 CLI Skill）。当用户需要创建电影解说视频、短剧解说、影视二创、AI 配音旁白视频、film commentary、video narration、drama dubbing、movie narr…

3.2kGitHub stars

wshobson/agents

Plugins, agents, skills, and commands for Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi, written once in Markdown and adapted to each tool by g…

42.3kGitHub stars