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 podcast-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 | podcast-downloader |
| description | Download podcast episodes from Apple Podcasts using iTunes API with RSS fallback |
Download podcast episodes from Apple Podcasts using iTunes API with RSS fallback.
Enhanced podcast downloader that prioritizes iTunes API for faster, more reliable downloads compared to traditional RSS parsing. Automatically detects region codes (cn/us/jp), supports multiple fallback methods, and includes rich metadata extraction.
Use this skill when users:
python scripts/download_podcast.py "APPLE_PODCAST_URL" [-n COUNT] [-o OUTPUT_DIR]
Download specific episode (URL with ?i= parameter):
python scripts/download_podcast.py "https://podcasts.apple.com/cn/podcast/id1711052890?i=1000744375610"
Download latest N episodes:
python scripts/download_podcast.py "https://podcasts.apple.com/cn/podcast/id1711052890" -n 5
Download all available episodes (up to 200):
python scripts/download_podcast.py "https://podcasts.apple.com/us/podcast/id123456789"
Specify output directory:
python scripts/download_podcast.py "URL" -n 10 -o /mnt/user-data/outputs
url (required): Apple Podcast URL-n, --count: Number of latest episodes to download (default: all available)-o, --output: Output directory (default: current directory)pip install requests feedparser --break-system-packages
PodcastName/
├── podcast_info.json # Podcast metadata
├── 001 - Episode Title.m4a # Audio file
├── 001 - Episode Title.json # Episode metadata
├── 002 - Episode Title.m4a
└── ...
podcast_info.json:
{
"podcast_name": "Podcast Name",
"artist": "Author Name",
"country": "cn",
"total_episodes": 272,
"download_date": "2026-01-13T14:30:00"
}
Episode metadata:
{
"title": "Episode Title",
"release_date": "2025-01-10",
"duration_minutes": 40,
"description": "Episode description...",
"audio_file": "001 - Episode Title.m4a"
}
When user requests podcast download:
Read skill documentation:
view("/mnt/skills/user/podcast-downloader-v2/SKILL.md")
Install dependencies (if needed):
pip install requests feedparser --break-system-packages
Execute download:
python /mnt/skills/user/podcast-downloader-v2/scripts/download_podcast.py \
"USER_URL" -n COUNT -o /mnt/user-data/outputs
Present files to user:
present_files(["/mnt/user-data/outputs/PodcastName/..."])
https://itunes.apple.com/lookup?id={episode_id}&entity=podcastEpisode&country={country}https://itunes.apple.com/lookup?id={podcast_id}&entity=podcastEpisode&country={country}&limit=200https://itunes.apple.com/lookup?id={podcast_id}&country={country}&entity=podcastQ: Can't find old episodes?
A: iTunes API returns max 200 recent episodes. Script automatically falls back to RSS for older content.
Q: Getting 403 errors?
A: User-Agent headers are included to prevent most 403 errors. If persists, may be source restriction.
Q: Which regions are supported?
A: All Apple Podcasts regions (cn, us, jp, uk, etc.). Auto-detected from URL.
User: "帮我下载这个播客的最新 3 集: https://podcasts.apple.com/cn/podcast/id1711052890"
Claude:
# View skill
view("/mnt/skills/user/podcast-downloader-v2/SKILL.md")
# Install dependencies
pip install requests feedparser --break-system-packages
# Download
python /mnt/skills/user/podcast-downloader-v2/scripts/download_podcast.py \
"https://podcasts.apple.com/cn/podcast/id1711052890" \
-n 3 \
-o /mnt/user-data/outputs
# Present files
present_files([...])
v2.0 (Current)
v1.0 (Original)
See /references/ directory for:
usage_guide.md: Detailed usage instructions and examplestechnical_details.md: In-depth technical documentationapi_reference.md: iTunes API documentationPersonal use tool. Please respect Apple Podcasts terms of service. For personal listening and learning only.