Video Podcast Maker
Agents365-ai/video-podcast-maker
A skill your agent uses when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat…
Multi-platform account video extractor — provide a platform name and account ID/link to automatically fetch homepage works from Douyin, Kuaishou, Bilibili, and YouTube, resolve download links, and…
$ npx skills add hashgraph-online/awesome-codex-plugins --skill account-video-downloader -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins account-video-downloader --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/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader .claude/skills/account-video-downloader && 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 "account-video-downloader" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader into .claude/skills/account-video-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "account-video-downloader", 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/hashgraph-online/awesome-codex-plugins/tree/main/plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloaderType 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 hashgraph-online/awesome-codex-plugins --skill account-video-downloader -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins account-video-downloader --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader .agents/skills/account-video-downloader && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "account-video-downloader" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader into .agents/skills/account-video-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "account-video-downloader", 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 hashgraph-online/awesome-codex-plugins --skill account-video-downloader -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins account-video-downloader --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader .cursor/skills/account-video-downloader && 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 "account-video-downloader" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader into .cursor/skills/account-video-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "account-video-downloader", 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/hashgraph-online/awesome-codex-plugins.git --path plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader--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 hashgraph-online/awesome-codex-plugins --skill account-video-downloader -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins account-video-downloader --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader .gemini/skills/account-video-downloader && 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 "account-video-downloader" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader into .gemini/skills/account-video-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "account-video-downloader", 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 hashgraph-online/awesome-codex-plugins account-video-downloaderInstalls 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 hashgraph-online/awesome-codex-plugins --skill account-video-downloader -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader .github/skills/account-video-downloader && 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 "account-video-downloader" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader into .github/skills/account-video-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "account-video-downloader", 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 hashgraph-online/awesome-codex-plugins --skill account-video-downloader -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins account-video-downloader --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader .opencode/skills/account-video-downloader && 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 "account-video-downloader" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader into .opencode/skills/account-video-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "account-video-downloader", 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.
account-video-downloaderMulti-platform account video extractor — provide a platform name and account ID/link to automatically fetch homepage works from Douyin, Kuaishou, Bilibili, and YouTube, resolve download links, and…
Account Video Downloader is an agent skill from hashgraph-online/awesome-codex-plugins. Multi-platform account video extractor — provide a platform name and account ID/link to automatically fetch homepage works from Douyin, Kuaishou, Bilibili, and YouTube, resolve download links, and batch-download. Use cases: breaking down competitor content frame by frame, saving all works from favorite creators before they get deleted, gathering material for re-editing, backing up your own account works locally, hoarding course/tutorial videos for offline viewing, and pulling a creator's works for due diligence…
Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts (for example `README.md`, `README.zh.md` and `scripts/__init__.py`).
It sits in Media & Creative, covering Video production and Fundraising and pitch decks. It works with Bilibili, YouTube and Douyin. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.
Read from SKILL.md and the folder at commit 3e1456a. 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 7 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3pip3From 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:
youtube.comspace.bilibili.comAlso links to:
redfox.hkFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
REDFOX_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Account Video Downloader loads about 3.4k tokens when it runs. Until then it costs about 206 tokens; SKILL.md has 863 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 hashgraph-online/awesome-codex-plugins at commit 3e1456a, republished under its Apache-2.0 licence (© hashgraph-online). 863 words, ~3,409 tokens.
.claude/skills/account-video-downloader/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.Note:
{SKILL_DIR}in the commands below means the absolute path of the directory containing this SKILL.md — resolve it before execution.
Channel attribution: replace
claudein theREDFOX_CHANNEL=claudeprefix below with the AI client you are currently running in:claude(Claude Code),codex(OpenAI Codex),cursor(Cursor),gemini(Gemini CLI). If the client is unknown, omit the prefix entirely — the script auto-detects the client from environment markers and falls back togithub.
Platform + account -> fetch works list -> resolve download links -> one-click download to local
A batch downloader for account homepage videos across multiple platforms. It supports Douyin, Kuaishou, Bilibili, and YouTube: provide the platform name and account identifier, and it automatically fetches the account's recent works, resolves the direct download link for each video/image post, and supports one-click batch downloading to your machine.
| Feature | Description |
|---|---|
| 📋 Work fetching | Get recent homepage works by account (title, engagement data, work link) |
| 🔗 Link resolution | Call the resolve API per work to get the direct video/image download link |
| 📥 Batch download | One-click download of all works (video + image posts) to the local output/ directory |
| 📊 Data display | Markdown table / JSON dual-format output with full engagement data |
| 📄 Pagination | Page through to view more works |
| 📅 Date filtering | Filter by work publish date |
| 🌐 Multi-platform | One tool covering Douyin / Kuaishou / Bilibili / YouTube |
| --platform | Platform | Account identifier | Example |
|---|---|---|---|
douyin | Douyin | Douyin ID | e.g. Fish688688 |
kuaishou | Kuaishou | Kuaishou ID (kwaiId) | e.g. Fish688688 |
bilibili | Bilibili | Homepage URL (accountUrl) | e.g. https://space.bilibili.com/123456 |
youtube | YouTube | Channel URL (channel) | e.g. https://www.youtube.com/@channel |
This skill calls the redfox.hk API. Each platform takes two steps:
| Step | Endpoint | Description |
|---|---|---|
| 1. Fetch works | POST /story/api/{platform}/... | Get the works list by account identifier |
| 2. Resolve download | POST /story/api/parseWork/videoDownload/{platform} | Get the direct download link by work URL |
Get an API Key at RedfoxHub and set it as an environment variable:
# macOS / Linux
export REDFOX_API_KEY=ak_your_key
# Windows PowerShell
$env:REDFOX_API_KEY="ak_your_key"# Douyin: basic usage
REDFOX_CHANNEL=claude python3 "{SKILL_DIR}/scripts/main.py" --platform douyin --account "Fish688688"
# Kuaishou: basic usage
REDFOX_CHANNEL=claude python3 "{SKILL_DIR}/scripts/main.py" --platform kuaishou --account "kwaiId"
# Bilibili: fetch works and resolve download links (no file download)
REDFOX_CHANNEL=claude python3 "{SKILL_DIR}/scripts/main.py" --platform bilibili --account "https://space.bilibili.com/123456"
# YouTube: download videos to local
REDFOX_CHANNEL=claude python3 "{SKILL_DIR}/scripts/main.py" --platform youtube --account "https://www.youtube.com/@channel" --download
# YouTube: specify a download directory
REDFOX_CHANNEL=claude python3 "{SKILL_DIR}/scripts/main.py" --platform youtube --account "https://www.youtube.com/@channel" --download --output-dir ./my_videos
# Set the number of works (default 10, max 50)
REDFOX_CHANNEL=claude python3 "{SKILL_DIR}/scripts/main.py" --platform bilibili --account "MID" --count 20 --download
# Page through to view more works
REDFOX_CHANNEL=claude python3 "{SKILL_DIR}/scripts/main.py" --platform kuaishou --account "userID" --page 2
# Filter works by date range
REDFOX_CHANNEL=claude python3 "{SKILL_DIR}/scripts/main.py" --platform bilibili --account "MID" --date-start 2026-07-01 --date-end 2026-07-31
# Multiple accounts (comma-separated)
REDFOX_CHANNEL=claude python3 "{SKILL_DIR}/scripts/main.py" --platform bilibili --accounts "MID1,MID2" --download
# Combined: page 2 + date filter + download
REDFOX_CHANNEL=claude python3 "{SKILL_DIR}/scripts/main.py" --platform bilibili --account "MID" --page 2 --count 20 --date-start 2026-06-01 --download| Parameter | Description |
|---|---|
--platform | Target platform (required, see table above) |
--account | A single account identifier |
--accounts | Multiple account identifiers, comma-separated |
--count | Number of works to fetch (default 10, max 50) |
--page | Page number (default 1) |
--date-start | Start date YYYY-MM-DD |
--date-end | End date YYYY-MM-DD |
--download | Download video files to local |
--output-dir | Download directory (default output/) |
--json | Output in JSON format |
--rate-limit | Seconds between requests (default 1.0) |
| Dependency | Install command |
|---|---|
requests | pip3 install requests |
Each platform has different requirements for the account identifier — you must provide the platform's unique identifier:
| Platform | Requirement | URL support | How to obtain |
|---|---|---|---|
| Bilibili | Homepage URL (accountUrl) | ✅ Supported | Copy the personal-space page URL directly |
| YouTube | Channel URL (channel) | ✅ Supported | Copy the channel page URL directly |
| Douyin | Douyin ID (uniqueName) | ❌ Not supported | Douyin APP -> target profile -> the 'Douyin ID: xxx' field below the avatar |
| Kuaishou | Account ID (kwaiId) | ❌ Not supported | Kuaishou APP -> target profile -> the ID shown below the nickname |
⚠️ Douyin and Kuaishou do not support homepage links! If the user pastes a URL, you must prompt them for the unique identifier above.
Important: if the user only enters an account name without the unique identifier, you must prompt them for the exact unique identifier.
📸 How to find the Douyin ID: open the Douyin APP -> go to the target user's profile -> below the avatar and follower stats you'll see the 'Douyin ID: xxx' field. If the user isn't sure where it is, show an annotated screenshot (with the 'Douyin ID' location highlighted) to help them locate it.
Step 1: Confirm the user's intent, platform, and account identifier
- Identify the target platform from the user's input (Douyin/Kuaishou/Bilibili/YouTube)
- If the platform is unclear, ask: "Which platform do you want to download from?"
- Confirm the account identifier format is correct; if the user gave a nickname, prompt for the unique ID
Step 2: Recognize any time range in the user's input
- If the user mentions a work time range, recognize it and convert to --date-start / --date-end:
- "7.1~7.20" -> --date-start 2026-07-01 --date-end 2026-07-20
- "July 1 to July 20" -> --date-start 2026-07-01 --date-end 2026-07-20
- "the last week" -> 7 days back from today
- "last month" -> the 1st to the last day of the previous month
- "works from July" -> --date-start 2026-07-01 --date-end 2026-07-31
- Dates are always YYYY-MM-DD; the year defaults to the current year
- If the user asks to "continue"/"next page", add --page N
Step 3: Call the script to fetch works + resolve download links
REDFOX_CHANNEL=claude python3 "{SKILL_DIR}/scripts/main.py" --platform <platform> --account "<id>"
Step 4: Show results + ask about pagination
- Show the Markdown table with clickable work links and download links
- On failures: note "the video may have been deleted by its author; for data verification contact redfoxdata@proton.me"
- If more pages exist: tell the user "more works are available — view the next page?" and page on request
- Remind the user that extracting by time range is supported
Step 5: Ask whether the user wants a batch download
- Use AskUserQuestion: "Batch-download the downloadable videos to your machine?"
- Options: "Download to local" / "Just show the links"
Step 6: Run the download after the user confirms
REDFOX_CHANNEL=claude python3 "{SKILL_DIR}/scripts/main.py" --platform <platform> --account "<id>" --download
- Tell the user where the files were savedAfter resolution, output in the following format (natural-language style, aimed at ordinary users).
The Agent MUST render the full table returned by the script verbatim. The following are forbidden:
- ❌ Do not drop or merge any column (Published, Work, Likes, Comments, Saves, Shares, Download — all are required)
- ❌ Do not omit the pagination hint line
- ❌ Do not omit the date-range hint ("💡 You can specify a publish-date range to extract…")
- ❌ Do not omit the download prompt ("💾 Want to batch-download these X works to your machine?")
- ❌ Do not replace the full table content with "..." or a summary
- ✅ Every work must be shown line by line with its full info (including resource download links)
## 📥 {Platform} Video Download — @accountName (followers: X)
Currently on **page 1**, 10 works in total | more works available, pass `--page 2` to view the next page
| # | Published | Work | Likes | Comments | Saves | Shares | Download |
| --- | --------- | ----------------- | ----- | -------- | ----- | ------ | --------------------------------------------- |
| 1 | 07-28 | [Work title](link)| 5.2k | 67 | 689 | 5.8k | [🎬Video](...) · [🖼Cover](...) · [🎵Audio](...) |
| 2 | 07-24 | [Work title 2](link)| 3.1k | 22 | 136 | 865 | [🖼Cover](...) |
| 3 | … | … | … | … | … | … | … |
**Total:** 10 works, 8 downloadable, 2 failed
> ⚠️ A failed video may have been deleted by its author. For data verification, contact the support email **redfoxdata@proton.me**.
> 💡 Want works from a specific time range? Just tell me the range, e.g. "7.1~7.20" or "the last week".
> 💾 Want to batch-download these X works to your machine? Just let me know.The platform name is substituted automatically for the actual platform (Kuaishou / Bilibili / YouTube).
Q: How do I get an API Key? A: Register at redfox.hk to get one.
Q: Are the downloaded videos watermarked? A: No. The direct video/image links returned by the API are watermark-free.
Q: Can image posts be downloaded? A: Yes. Image posts (slideshows, galleries) automatically download the first image as JPG/PNG/WebP.
Q: Why do I see "rate limit exceeded"?
A: The API returns code=3108 when requests come too fast and trigger throttling. Increase the interval with --rate-limit 2.0.
Q: Which platforms are supported? A: Douyin, Kuaishou, Bilibili, and YouTube.
Q: Where do I find each platform's account identifier? A: Douyin needs the Douyin ID (e.g. JCLjiangchenglan); Kuaishou needs the account ID / kwaiId (below the account name); Bilibili needs the homepage link; YouTube needs the channel URL.
© hashgraph-online, Apache-2.0. 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 9 other files (scripts) in plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader of hashgraph-online/awesome-codex-plugins.
Open the folder on GitHubat commit 3e1456a
Account Video 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Account Video Downloader this skillhashgraph-online/awesome-codex-plugins | 1.3k | — | ~3.4k | Automated safety check: Pass | Apache-2.0 | |
| Video Podcast MakerAgents365-ai/video-podcast-maker | 1.7k | — | ~4.9k | Automated safety check: Pass | MIT | |
| Ra Video Wash PipelinePluviobyte/rnskill | 1.6k | — | ~2.4k | Automated safety check: Pass | Custom licence | |
| Video Downloaderkangarooking/kangarooking-skills | 662 | — | ~8.3k | Automated safety check: Pass | None | |
| Video To Subtitle Summaryimlewc/video-to-subtitle-summary-skill | 218 | — | ~4.6k | Automated safety check: Notes | MIT | |
| Media To TranscriptbozhouDev/video-skills-toolkit | 150 | — | ~1.8k | Automated safety check: Notes | MIT |
Agents365-ai/video-podcast-maker
A skill your agent uses when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat…
Pluviobyte/rnskill
End-to-end Chinese video washing pipeline. An agent skill from Pluviobyte/rnskill.
kangarooking/kangarooking-skills
Download or open videos and recover platform captions, audio transcripts, keyframes, screen text, visual facts, and editing observations as a plain multimodaltranscript.md.
imlewc/video-to-subtitle-summary-skill
A skill your agent uses when user provides a short video platform URL or local video/audio file and wants subtitles/AI summary, or when user asks to list their own AI Douyin historical tasks.
bozhouDev/video-skills-toolkit
Convert audio/video URLs or local media into corrected Markdown transcripts through Volcengine recording-file ASR 2.0.
linzzzzzz/openclip
Processes videos to identify engaging moments, generate transcripts, and create highlight clips with artistic titles and custom cover images.
hashgraph-online/awesome-codex-plugins
Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.
hashgraph-online/awesome-codex-plugins
Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).
hashgraph-online/awesome-codex-plugins
A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…
hashgraph-online/awesome-codex-plugins
Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…
hashgraph-online/awesome-codex-plugins
Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.
hashgraph-online/awesome-codex-plugins
Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.
Categories
Multi-platform account video extractor — provide a platform name and account ID/link to automatically fetch homepage works from Douyin, Kuaishou, Bilibili, and YouTube, resolve download links, and…. Account Video Downloader is an agent skill from hashgraph-online/awesome-codex-plugins. Multi-platform account video extractor — provide a platform name and account ID/link to automatically fetch homepage works from Douyin, Kuaishou, Bilibili, and YouTube, resolve download links, and batch-download.
Account Video Downloader fits situations like: words: homepage video download; batch video download; account video extraction; kuaishou homepage download.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill account-video-downloader -a claude-code`. Or copy the skill folder (plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader in hashgraph-online/awesome-codex-plugins) into .claude/skills/account-video-downloader in your project. Claude Code loads it when a task matches its description.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill account-video-downloader -a codex`. Or copy the skill folder (plugins/redfox-data/redfox-agent-plugins/skills/account-video-downloader in hashgraph-online/awesome-codex-plugins) into .agents/skills/account-video-downloader 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 hashgraph-online/awesome-codex-plugins --skill account-video-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/account-video-downloader, .gemini/skills/account-video-downloader, .github/skills/account-video-downloader and .opencode/skills/account-video-downloader in your project.
Going by SKILL.md and its folder, Account Video Downloader needs Python for the scripts in its folder, the command-line tools its instructions call (python3 and pip3) and credentials named REDFOX_API_KEY. Our summary lists: Python 3; A credential in REDFOX_API_KEY.
SKILL.md names 3 domains. In commands or code: youtube.com and space.bilibili.com; the agent is likely to contact these when it follows the instructions. As links in the text: redfox.hk. 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.
Account Video Downloader is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.4k tokens (SKILL.md is roughly 14k 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 Account Video Downloader: Video Podcast Maker (Agents365-ai/video-podcast-maker, 1.7k stars), Ra Video Wash Pipeline (Pluviobyte/rnskill, 1.6k stars), Video Downloader (kangarooking/kangarooking-skills, 662 stars) and Video To Subtitle Summary (imlewc/video-to-subtitle-summary-skill, 218 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,267 GitHub stars. The repository holds 716 skills in this directory. The repository was last updated on October 10, 2026.
Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.