agentleFS
AtmoskunAtmoskun/claude-skills/skills/podwise-downloader/SKILL.md

podwise-downloader

Skill0 starsChanged 9 months agoMITView on GitHub

Download podcast transcripts from Podwise.ai and manage deduplication. Reuses existing Podcast-downloader program. Use when the user invokes /podwise-downloader followed by an optional subcommand (download, dedup).

  • Reads credentials

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the download script in background with a 10-minute timeout:

    line 30
  2. Very specific:

    Use run_in_background=true and timeout=600000 (10 minutes)

    line 35
  3. Very specific:

    Stream progress: Use TaskOutput with block=false every 15-20 seconds to check progress.

    line 37
  4. Very specific:

    When the script completes, display the full final summary to the user (the Done!

    line 39
  5. Distinctive:

    If the script fails or times out, report the error and any partial output.

    line 41
  6. Very specific:

    Run dedup.py directly (fast, no background needed):

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Podwise Downloader Skill

Overview

Download podcast transcripts from Podwise.ai using Playwright browser automation. Transcripts are saved as Markdown files to Info-Lake/Podwise-transcripts/ organized by podcast name.

Program Location

  • Scripts: C:\Users\10444\Desktop\Claude WorkSpace\Podcast-downloader\
  • download.py: Main downloader (login, scrape episodes, download transcripts)
  • dedup.py: Deduplicate transcript files
  • Config: .env in the same directory (Podwise credentials, DAYS_LOOKBACK)
  • Output: C:\Users\10444\Desktop\Claude Download\Info-Lake\Podwise-transcripts\

Command Format

  • /podwise-downloader or /podwise-downloader download — Download recent transcripts (default: past 7 days)
  • /podwise-downloader dedup — Dry-run deduplication (preview only)
  • /podwise-downloader dedup --apply — Apply deduplication (actually delete duplicates)

Workflow: Download

CRITICAL: The download process takes several minutes (Playwright browser automation). You MUST run it in background and stream progress to the user.

  1. Run the download script in background with a 10-minute timeout:
cd "C:/Users/10444/Desktop/Claude WorkSpace/Podcast-downloader" && python download.py
  • Use run_in_background=true and timeout=600000 (10 minutes)
  1. Stream progress: Use TaskOutput with block=false every 15-20 seconds to check progress. Each time new output appears, report it to the user immediately. This gives real-time feedback matching the experience of running the script directly.
  2. When the script completes, display the full final summary to the user (the Done! Downloaded: X | Skipped: Y | Queued: Z | Failed: W line).
  3. If the script fails or times out, report the error and any partial output.

Progress reporting format

As output streams in, relay key status lines to the user:

  • Login status: [LOGIN] ...
  • Podcast being processed: [1/6] Processing podcast ID ...
  • Episode downloads: "title" - downloading... / done (X KB) / already exists, skipping
  • Final summary: the Done! line

Workflow: Dedup

Run dedup.py directly (fast, no background needed):

cd "C:/Users/10444/Desktop/Claude WorkSpace/Podcast-downloader" && python dedup.py

For apply mode:

cd "C:/Users/10444/Desktop/Claude WorkSpace/Podcast-downloader" && python dedup.py --apply

Display output directly to user.

Environment

  • Python 3.12 (system) with playwright and python-dotenv installed globally
  • .env is loaded by load_dotenv() from the script's working directory
  • Always cd to the Podcast-downloader directory before running scripts
  • Playwright runs headless by default (HEADED=false in .env)

Important Notes

  • Session is cached in .session.json — login is usually instant after first run
  • DAYS_LOOKBACK in .env controls how far back to look (default: 7 days)
  • Episodes already downloaded are tracked in downloaded.json index and skipped
  • "AI Process" button click means the episode isn't processed yet on Podwise — it will be ready on the next run
  • PODCAST_IDS in download.py defines which podcasts to check (edit the script directly to add/remove)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.