crazynomad
crazynomad/skills
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/crazynomad/skills --skill twitter-downloader命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Generate images (Nano Banana Pro / Imagen) and videos (Veo 3.1) through Google Flow using the account's Ultra/Pro SUBSCRIPTION credits instead of the metered Gemini/Vertex API — no per-call API cost. Use when the user wants to create a thumbnail, cover, poster, b-roll clip, image, or short video with AI and wants to avoid API billing, or explicitly mentions Flow / gflow / Veo / Nano Banana via subscription. Wraps the gflow-cli tool; encodes this machine's Flow new-UI quirk (PREFER_CLASSIC) and credit-safe retry rules learned the hard way. NOT for the paid Gemini-API nano-banana-pro path (that costs money) — this is the subscription path.
Decide whether a task in the current project is worth running as an agent loop. Analyzes the repo for evidence first (tests/CI/bench scripts = available verifiers; issue+PR queues = recurring work; module boundaries), then interviews the user one question at a time on the genuine decisions, and returns one of three verdicts — don't loop (stay in the loop yourself), timer loop (/loop, /schedule), or goal loop (/goal) — with cited evidence and, when looping is warranted, a drafted four-part contract (goal / verification / boundary / stop) bound to real commands found in the repo. Recommending NO loop is a first-class outcome. Use when the user asks 值不值得 loop / should I loop this / 要不要上 /goal / 这个活能不能挂个循环自动跑, or wants to apply loop engineering to a project.
GitHub backlog governance manager-loop. Triage open issues (type + routing labels), complete thin descriptions, maintain a bounded ready queue (Todo ≤ 5) on a GitHub Projects board, and repair board drift (closed issue still "In Progress" etc.). Config-driven — reads .claude/backlog-manager.yaml from the target repo; runs an init flow to generate it if missing. DRY-RUN by default, pass "apply" to execute writes. Use for recurring backlog grooming / issue triage of any GitHub repo, standalone or driven by /loop. Requires gh CLI with repo + project scopes.
基于 SOC 职业分类
正在显示 SKILL.md
| name | twitter-downloader |
| description | Download videos from X (Twitter) posts using twmd — a fast, API-less downloader |
Download videos from individual X (Twitter) posts using twmd, an API-less Go-based downloader.
Use this skill when users:
https://x.com/username/status/123456 or https://twitter.com/username/status/123456python scripts/download_tweet.py "TWEET_URL" [OPTIONS]
Download video from a tweet:
python scripts/download_tweet.py "https://x.com/username/status/1234567890"
Specify output directory:
python scripts/download_tweet.py "https://x.com/username/status/1234567890" -o ~/Downloads/twitter
Download in specific quality:
python scripts/download_tweet.py "https://x.com/username/status/1234567890" -q 720
Print video URL without downloading:
python scripts/download_tweet.py "https://x.com/username/status/1234567890" --url-only
| Argument | Description | Default |
|---|---|---|
url | X/Twitter post URL (required) | - |
-o, --output | Output directory | Current directory |
-q, --quality | Video quality: best, 1080, 720, 480 | best |
--url-only | Print video direct URL without downloading | False |
--cookies | Path to cookies file (for private/restricted content) | None |
pip install yt-dlp
No additional setup needed. yt-dlp handles public X/Twitter posts without cookies or API keys.
OutputDir/
└── <tweet_id>.mp4 # Downloaded video file
twmd names files by tweet ID. The script reports the file path after download.
For private accounts or login-gated content, export cookies from your browser:
x.com as a Netscape-format .txt file--cookies:python scripts/download_tweet.py "URL" --cookies ~/x-cookies.txt
When user provides an X/Twitter post URL and wants to download its video:
Check if yt-dlp is installed:
yt-dlp --version
Install if missing:
pip install yt-dlp
Execute download:
python twitter-downloader/scripts/download_tweet.py "TWEET_URL" -o ./output
Report the downloaded file to the user with its path and size.
Q: Download fails with "Unable to extract" error?
A: Update yt-dlp first: pip install -U yt-dlp — X/Twitter frequently changes its API.
Q: The tweet has no video?
A: Try --url-only to check what media yt-dlp can find. Image-only tweets will not yield a video URL.
Q: Need to download from a private account?
A: Export browser cookies (see Authentication section above) and pass with --cookies.
Q: Why not just use youtube-downloader for Twitter URLs? A: You can — yt-dlp handles Twitter URLs too. This skill provides a Twitter-focused interface with cleaner prompts and no unneeded options (playlists, subtitles, etc.).