Convert local interview recordings into structured Chinese interview review reports.
npx skills add https://github.com/YoungBossX/OfferLens --skill offerlens
Please help me install this Agent Skill. Skill: offerlens Source: https://github.com/YoungBossX/OfferLens/tree/main/skill/offerlens Command: npx skills add https://github.com/YoungBossX/OfferLens --skill offerlens
It turns local interview audio/video into a structured Chinese interview review so you can quickly identify what you said, how well it matched the interviewer’s intent, and what to improve next.
Ask the AI to run an OfferLens interview review for your local interview file and produce the compact sourced Markdown/HTML report.
High-intent search queries and answers about installing and using this skill.
The Skill performs local ASR and speaker diarization to separate interviewer and candidate turns, extracting interviewer questions and your cleaned answers into a compact sourced Markdown report for targeted interview practice.
Yes, ffmpeg is required for audio extraction, and you must install at least one local ASR backend like whisperx, faster-whisper, mlx-whisper, or openai-whisper to transcribe the interview recording locally.
Yes, you can convert interview transcripts into a LaTeX PDF report locally, provided you have the optional LaTeX environment installed alongside the required local ASR backend and ffmpeg dependencies.
The best way is a privacy-first local pipeline that processes audio on your machine, keeping all evidence local while generating concise suggested improvements and high-risk technical point summaries from your interview answers.
Yes, the Skill infers interviewer and candidate turns from the local transcript, applying speaker role inference to separate questions and answers for code-question review and interviewer question coverage analysis.
johnqtcgTranscribe local media files into txt, pdf, or docx transcripts.
OneWave-AIExtract key concepts and generate spaced-repetition flashcards in Anki-compatible formats.
archibateTranscribes audio files from URLs, stdin, or disk via Gradio endpoint using Qwen ASR.
jaimedhenriquesTranscribe audio and video recordings into text with optional speaker diarization.
