hn-podcast-archiveAutomate podcast archiving by detecting new HN episodes from RSS, downloading audio, transcribing locally with Whisper, and generating markdown archives with...
Install via ClawdBot CLI:
clawdbot install terrycarter1985/hn-podcast-archiveGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://example.com/podcast.rssAudited Apr 18, 2026 · audit v1.0
Generated Oct 8, 2026
A media company wants to maintain a searchable, text-based archive of their Hacker News podcast episodes. They set up the skill with a cron job to automatically detect new RSS episodes, download and transcribe them, and generate markdown files for their CMS. The archive improves content discoverability and SEO.
An independent podcaster uses the skill to transcribe each new episode of their show locally with Whisper, ensuring privacy and avoiding cloud costs. They run the script manually after publishing to generate transcripts for show notes and accessibility. The state file prevents re-processing old episodes.
A university research group archives interviews and lectures from an RSS-based academic podcast. They use the skill to download audio, transcribe it, and extract metadata for qualitative analysis. The local Whisper model ensures sensitive data stays on-premises.
A news aggregator platform ingests Hacker News podcast episodes to enrich their article database with transcripts. The skill's idempotent design allows scheduled runs without duplicating content. Markdown archives are indexed for internal search and recommendation engines.
A nonprofit provides transcriptions for popular podcasts to improve accessibility. They use the skill to automate transcription of the Hacker News podcast, generating markdown files that are then published on their website. The pipeline runs every few hours to keep transcripts up-to-date.
Offer a paid subscription for searchable, human-readable transcripts of popular podcasts. Customers get access to a full-text searchable archive with metadata and downloadable markdown files. The skill automates ingestion, keeping the archive current with minimal manual effort.
Provide a free tier for limited transcriptions and a paid tier for higher volume or faster processing. The skill handles the backend pipeline, and customers integrate via API to archive their own RSS feeds. Revenue comes from usage-based pricing or premium features like higher accuracy models.
Sell an enterprise solution that integrates podcast transcription into existing CMS or knowledge management systems. The skill's outputs (markdown, index, state) can be adapted to feed into enterprise search or compliance archives. Licensing fees are charged per seat or per installation.
💬 Integration Tip
Ensure ffmpeg, whisper, and feedparser are installed before first run; use the --dry-run and --limit flags to test the pipeline safely. Schedule cron jobs with a stable output directory and monitor run-log.jsonl for failures.
Scored Oct 8, 2026
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...
Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcript...
Text-to-Speech (TTS) and Speech-to-Text (ASR) using coze-coding-dev-sdk. Returns results directly to stdout.