Loading...
Loading...
Found 55 Skills
Match spoken edit beats to candidate B-roll assets using a normalized transcript, subtitle chunking, optional A-roll analysis, and a reusable B-roll catalog. Use this when the goal is to decide what B-roll should support each beat, not just to list assets or describe the video.
Use when writing or modifying Python code that imports `genoray` to read genotypes/dosages from VCF, PGEN, or SparseVar (`.svar`) files. Covers the public API surface, mode constants, range queries, chunking, filtering, and the SparseVar workflow. Skip for unrelated bioinformatics work.
Iterate on RAG systems with structured evals instead of eyeballing. This skill should be used when the user is tuning a RAG pipeline — changing retrieval prompts, swapping models, adjusting chunking, or debugging poor answers — and wants a cheap, ranked set of experiments with cost tracking and structured feedback on the stack. Also use when the user asks "how do I know if my RAG is working?", "this RAG eval is burning money", or "what should I try next on retrieval?".
Transcribe audio with StepFun's stepaudio-2.5-asr — an SSE endpoint (NOT /v1/audio/transcriptions) with 32K context, ~85-101x RTF on long audio, and a single-call ceiling around 30 minutes (no client-side chunking). Use when transcribing Chinese / English audio with StepFun, when long-form recordings (5-30 min) need to land in one request, when migrating from step-asr / step-asr-1.1, or when hitting the misleading `model stepaudio-2.5-asr not supported` error (which actually means wrong endpoint). Triggers on 阶跃 ASR, StepFun ASR, stepaudio-2.5-asr, 转录, 语音识别, 长音频转写, 语音转文字. For TTS with the sibling stepaudio-2.5-tts model, use the stepfun-tts skill instead.
Extract text and data from PDF documents
Apply Miller's Law — chunk information into groups of ~4 to work within working memory limits.
tokenization과 context window를 중심으로 긴 입력 처리 한계와 실무 대응 방법(분할, 요약, 우선순위화)을 학습시키는 모듈.