New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Douyin Downloader

by OpenMinis in OpenMinis/MinisSkills

Download Douyin (TikTok) videos from share links. An agent skill from OpenMinis/MinisSkills.

MITAuto-check passedMedia & Creative

Install Douyin Downloader

skills CLI
$ npx skills add OpenMinis/MinisSkills --skill douyin-downloader -a claude-code

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

GitHub CLI
$ gh skill install OpenMinis/MinisSkills douyin-downloader --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/OpenMinis/MinisSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/douyin-downloader .claude/skills/douyin-downloader && 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
douyin-downloader
GitHub stars
446
Token cost
~1.4k tokens
SKILL.md length
373 words
Files
4 (incl. scripts)
Skills in repo
49
Repo updated
First seen
Licence
MIT

At a glance

Download Douyin (TikTok) videos from share links. An agent skill from OpenMinis/MinisSkills.

  • Works in 3 steps: Parse Share Link → Download Video → Transcribe Audio
  • Tasks that involve Transcription
  • SKILL.md covers Dependencies, Workflow, Complete Example and Notes, plus 1 more section
  • Runs Python scripts from its folder; calls python3 and pip3; reaches v.douyin.com and iesdouyin.com; needs VOLC_APP_KEY and VOLC_ACCESS_KEY

What it does

Douyin Downloader is an agent skill from OpenMinis/MinisSkills. Download Douyin (TikTok) videos from share links. Parse Douyin share text and links, download watermark-free videos, and transcribe audio to text using Volcano Engine ASR (Doubao Speech). Uses Python for iSH compatibility.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/download_video.py`, `scripts/parse_douyin.py` and `scripts/transcribe_audio.py`).

It sits in Media & Creative, covering Transcription, Speech recognition and synthesis and Video production. It works with Douyin, Python and TikTok. The repository describes itself as: Skills collection for Minis. The licence is MIT.

When your agent uses it

  • Tasks that involve Transcription
  • Tasks that involve Speech recognition and synthesis
  • Tasks that involve Video production

Example prompts

  • “/douyin-downloader”

Requirements

  • Python 3
  • Node.js
  • A credential in VOLC_APP_KEY
  • A credential in VOLC_ACCESS_KEY

Workflow steps

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

  1. Parse Share Link
  2. Download Video
  3. Transcribe Audio

What it can do on your machine

Read from SKILL.md and the folder at commit ae8c5db. 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

    Ships 3 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • pip3

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • v.douyin.com
    • iesdouyin.com
    • aweme.snssdk.com

    Also links to:

    • console.volcengine.com

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • VOLC_APP_KEY
    • VOLC_ACCESS_KEY

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

Context cost

Douyin Downloader loads about 1.4k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 373 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from OpenMinis/MinisSkills at commit ae8c5db, republished under its MIT licence (© OpenMinis). 373 words, ~1,357 tokens.

Download SKILL.mdSave it as .claude/skills/douyin-downloader/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
douyin-downloader
description
Download Douyin (TikTok) videos from share links. Parse Douyin share text and links, download watermark-free videos, and transcribe audio to text using Volcano Engine ASR (Doubao Speech). Uses Python for iSH compatibility.

Douyin Video Downloader

Parse Douyin share links and download videos without watermarks.

Note: The original version used Node.js. Because of iSH environment limitations, it has been converted to Python.

Dependencies

  • Python 3
  • requests library (pip3 install requests)
Environment Variables (Transcription Feature)
  • VOLC_APP_KEY - Volcano Engine App Key
  • VOLC_ACCESS_KEY - Volcano Engine Access Key

Workflow

When the user provides Douyin share text or a link, extract the video metadata:

bash
python3 scripts/parse_douyin.py "<share text or link>"

Input examples:

  • Full share text: 7.43 FuL:/ You know what? It really is pretty nice. https://v.douyin.com/iFDbjn2M/ Copy this link...
  • Just the URL: https://v.douyin.com/iFDbjn2M/

Output (JSON):

json
{
  "video_id": "7445842287652441376",
  "title": "You_know_what_It_really_is_pretty_nice",
  "download_url": "https://...play.../video/...",
  "raw_url": "https://...playwm.../video/...",
  "share_url": "https://v.douyin.com/iFDbjn2M/",
  "redirected_url": "https://www.iesdouyin.com/share/video/7445842287652441376",
  "iesdouyin_url": "https://www.iesdouyin.com/share/video/7445842287652441376"
}

Key fields:

  • download_url - Watermark-free version (playwm to play)
  • title - Sanitized video description, safe for filenames
  • video_id - Unique video identifier
2. Download Video

Use the download_url from step 1:

bash
python3 scripts/download_video.py "<download_url>" "<output_path>"

Example:

bash
python3 scripts/download_video.py "https://aweme.snssdk.com/aweme/v1/play/?video_id=..." "./downloads/You_know_what_It_really_is_pretty_nice.mp4"

Output:

json
{
  "status": "success",
  "path": "./downloads/You_know_what_It_really_is_pretty_nice.mp4"
}

Progress is written to stderr during download.

3. Transcribe Audio

Transcribe audio or video to text using Volcano Engine ASR (Doubao Speech):

bash
python3 scripts/transcribe_audio.py "<audio_or_video_file>" --app-key "$VOLC_APP_KEY" --access-key "$VOLC_ACCESS_KEY"

Parameters:

  • --app-key - Volcano Engine App Key (required, or set the VOLC_APP_KEY environment variable)
  • --access-key - Volcano Engine Access Key (required, or set the VOLC_ACCESS_KEY environment variable)
  • --resource-id - Resource ID: volc.bigasr.auc_turbo (flash) or volc.seedasr.auc (standard)
  • --mode - Mode: auto | flash | standard (default: auto)
  • --out - Output JSON file path (optional)
  • --text-out - Output text file path (optional)

Example:

bash
# Using env vars
export VOLC_APP_KEY="your_app_key"
export VOLC_ACCESS_KEY="your_access_key"
python3 scripts/transcribe_audio.py "./downloads/video.mp4" --mode flash

# Or inline
python3 scripts/transcribe_audio.py "./downloads/video.mp4" \
  --app-key "your_app_key" \
  --access-key "your_access_key" \
  --resource-id "volc.bigasr.auc_turbo" \
  --mode flash \
  --text-out "./downloads/transcript.txt"

Output (JSON):

json
{
  "status": "success",
  "mode": "flash",
  "result_text": "When you feel that fate has been unfair to you, you might want to listen to what Tong Guowei said to Long Keduo...",
  "result": { ... }
}

Getting API credentials:

  1. Visit the Volcano Engine Console
  2. Create a speech recognition (ASR) application
  3. Get the App Key and Access Key from the application settings
Show full SKILL.md (143 more words)Show less

Complete Example

bash
# Step 1: Parse
result=$(python3 scripts/parse_douyin.py "7.43 FuL:/ You know what? It really is pretty nice. https://v.douyin.com/iFDbjn2M/")

# Step 2: Extract fields
download_url=$(echo "$result" | python3 -c "import sys,json; print(json.load(sys.stdin)['download_url'])")
title=$(echo "$result" | python3 -c "import sys,json; print(json.load(sys.stdin)['title'])")

# Step 3: Download
python3 scripts/download_video.py "$download_url" "./downloads/${title}.mp4"

Notes

  • Watermark removal: The script automatically converts playwm URLs to play URLs
  • Title sanitization: Removes invalid filename characters (\/:*?"<>|)
  • Both video and note: Supports both /video/ and /note/ URLs
  • Mobile UA required: Uses an iPhone user agent for compatibility
  • Timeout: 60 seconds per download
  • Progress: Displays progress every 10% on stderr
  • Filename length: Use short filenames (English or pinyin) for saved files. Long filenames with URL encoding may break minis:// preview links.
Examples
  • Bad: High_Definition_Lens_41_years_old_Qi_Xi_How_is_her_condition_The_Role_of_Film_Beijing_Premiere.mp4
  • Good: qixi_short.mp4

Error Handling

Common errors:

  • No valid share link found - Invalid or missing URL in input
  • Failed to access the share link - Network error or blocked request
  • Failed to parse video information from HTML - Page structure changed (script needs an update)
  • Download timed out - Network timeout (try again)

When errors occur, scripts return JSON with { "status": "error", "error": "<message>" } on stderr and exit with code 1.

© OpenMinis, MIT. 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 3 other files (scripts) in douyin-downloader of OpenMinis/MinisSkills.

  • SKILL.md
  • scripts/download_video.py
  • scripts/parse_douyin.py
  • scripts/transcribe_audio.py

Open the folder on GitHubat commit ae8c5db

Compare with similar skills

Douyin Downloader 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.

Douyin Downloader compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Douyin Downloader this skillOpenMinis/MinisSkills446—~1.4kAutomated safety check: PassMIT
Watchmathiaschu/watch142—~4kAutomated safety check: WarnMIT
Ffmpeg Skillkajisho5/ffmpeg-skill1.9k—~7.4kAutomated safety check: PassMIT
Bggg Tiktok Readvideobinggandata/bggg-skills605—~1.6kAutomated safety check: PassMIT
Videohubcacity/VideoHub168—~405Automated safety check: PassMIT
Karaoke CaptionsAI-Builder-Club/skills1.3k—~850Automated safety check: PassNone

Similar skills

  • Watch

    mathiaschu/watch

    Watch a video from YouTube, Instagram, X/Twitter, Vimeo, TikTok or any of ~1800 yt-dlp sites (or a local path).

    142 GitHub stars~4k tokensUpdated 4 mo ago
    Media & CreativeAuto-check: warnings

  • Ffmpeg Skill

    kajisho5/ffmpeg-skill

    Edit video and audio with local FFmpeg from natural-language requests: cut, trim, join, resize/reframe (9:16, 1:1), speed change, captions and subtitles (SRT/ASS, animated, karaoke), logos and text…

    1.9k GitHub stars~7.4k tokensUpdated yesterday
    Media & CreativeAuto-check passed

  • Bggg Tiktok Readvideo

    binggandata/bggg-skills

    把 TikTok、Reels、YouTube Shorts、UGC 广告、本地 MP4/MOV/WebM 等视频拆成 Codex 可读的视频上下文。

    605 GitHub stars~1.6k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

  • Videohub

    cacity/VideoHub

    VideoHub 总入口。用于识别用户要处理的平台或功能，并路由到更具体的 VideoHub skills，如 YouTube、抖音、闲时队列、FFmpeg、字幕、故事剪辑、影视封面、音乐卡点剪辑和直播录制。

    168 GitHub stars~405 tokensUpdated 9 days ago
    Media & CreativeAuto-check passed

  • Karaoke Captions

    AI-Builder-Club/skills

    Generate TikTok/Shorts-style karaoke captions using MLX Whisper, ASS subtitles, and FFmpeg libass.

    1.3k GitHub stars~850 tokensUpdated 25 days ago
    Media & CreativeAuto-check passed

  • Autoshorts

    Upload-Post/skill-autoshorts

    Daily pipeline that picks one long video from a folder, transcribes it with Whisper, uses Gemini 3 Flash multimodal to find every viral short-form moment, cuts each candidate with FFmpeg, adds a…

    151 GitHub stars~5.3k tokensUpdated 5 mo ago
    Media & CreativeAuto-check: notes

More from OpenMinis/MinisSkills

All 49 skills in this repo

  • Android UI Automation

    OpenMinis/MinisSkills

    Automate Android apps that have no public API or web version by driving the UI layer through the Accessibility Service.

    446 GitHub stars~1.6k tokensUpdated 3 days ago
    Auto-check passed

  • Codex On Ish

    OpenMinis/MinisSkills

    Install and run OpenAI Codex CLI inside the Minis/iSH Alpine sandbox on iOS, where rustls TLS and async sockets are broken.

    446 GitHub stars~1k tokensUpdated 3 days ago
    Auto-check passed

  • Evidence Chain Builder

    OpenMinis/MinisSkills

    Score a claim against the evidence behind it. An agent skill from OpenMinis/MinisSkills.

    446 GitHub stars~2.4k tokensUpdated 3 days ago
    Auto-check passed

  • Hyperframes CLI

    OpenMinis/MinisSkills

    HyperFrames CLI and Minis rendering. An agent skill from OpenMinis/MinisSkills.

    446 GitHub stars~3.5k tokensUpdated 3 days ago
    Auto-check passed

  • Whenpeak

    OpenMinis/MinisSkills

    Predict when a person's brain works best from their sleep, using the WhenPeak performance-intelligence API, and turn it into concrete scheduling advice.

    446 GitHub stars~2.3k tokensUpdated 3 days ago
    Auto-check passed

  • Openstreetmap Marker

    OpenMinis/MinisSkills

    Generate a mobile-first, immersive, Amap(Gaode)-style custom landmark marker HTML map for travel itinerary planning, place showcasing, location sharing, etc.

    446 GitHub stars~1.9k tokensUpdated 3 days ago
    Auto-check passed

Works with

Categories

Questions about Douyin Downloader

What does Douyin Downloader do?

Download Douyin (TikTok) videos from share links. An agent skill from OpenMinis/MinisSkills. Douyin Downloader is an agent skill from OpenMinis/MinisSkills. Download Douyin (TikTok) videos from share links.

When should I use Douyin Downloader?

Douyin Downloader fits situations like: tasks that involve Transcription; tasks that involve Speech recognition and synthesis; tasks that involve Video production.

How do I install Douyin Downloader in Claude Code?

Run `npx skills add OpenMinis/MinisSkills --skill douyin-downloader -a claude-code`. Or copy the skill folder (douyin-downloader in OpenMinis/MinisSkills) into .claude/skills/douyin-downloader in your project. Claude Code loads it when a task matches its description.

How do I install Douyin Downloader in Codex?

Run `npx skills add OpenMinis/MinisSkills --skill douyin-downloader -a codex`. Or copy the skill folder (douyin-downloader in OpenMinis/MinisSkills) into .agents/skills/douyin-downloader in your project. Codex loads it when a task matches its description.

Can I use Douyin Downloader 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 OpenMinis/MinisSkills --skill douyin-downloader -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/douyin-downloader, .gemini/skills/douyin-downloader, .github/skills/douyin-downloader and .opencode/skills/douyin-downloader in your project.

What does Douyin Downloader need to run?

Going by SKILL.md and its folder, Douyin Downloader needs Python for the scripts in its folder, the command-line tools its instructions call (python3 and pip3) and credentials named VOLC_APP_KEY and VOLC_ACCESS_KEY. Our summary lists: Python 3; Node.js; A credential in VOLC_APP_KEY; A credential in VOLC_ACCESS_KEY.

Does Douyin Downloader access the network?

SKILL.md names 4 domains. In commands or code: v.douyin.com, iesdouyin.com and aweme.snssdk.com; the agent is likely to contact these when it follows the instructions. As links in the text: console.volcengine.com. This is read from the text; nothing was executed.

Is Douyin Downloader 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Douyin Downloader use?

Douyin Downloader is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Douyin Downloader use?

About 1.4k tokens (SKILL.md is roughly 5.4k 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 Douyin Downloader?

Skills that share tags, products or a category with Douyin Downloader: Watch (mathiaschu/watch, 142 stars), Ffmpeg Skill (kajisho5/ffmpeg-skill, 1.9k stars), Bggg Tiktok Readvideo (binggandata/bggg-skills, 605 stars) and Videohub (cacity/VideoHub, 168 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Douyin Downloader?

OpenMinis (a GitHub organization) maintains it in OpenMinis/MinisSkills, which has 446 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 7, 2026.

Source: OpenMinis/MinisSkills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.