Menu
Explain and summarize token consumption from lifecycle reports.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
全栈视频后期制作 Skill：Whisper 转录 → auto-editor 去静音 → ffmpeg 精剪（PIP放大镜/章节标题/加速/字幕烧录）→ Remotion 动画片段 → HyperFrames 品牌视频。 适用场景：教程视频后期、口播去死空气、宣传片生成、多平台导出。
Universal document to Markdown converter. Convert any file (PDF, Word, Excel, PPT, images, audio, video, YouTube URLs) to clean LLM-ready Markdown. Use when: - User wants to convert documents to Markdown - User needs to process entire directories of files - User has YouTube videos or audio files to transcribe - User wants to prepare content for LLM processing Triggers: "convert to markdown", "anything to md", "document to md", "pdf to md", "batch convert", "youtube transcript" PDF Backend Priority: 1. MinerU (mineru CLI) - High-quality OCR-based extraction with layout detection, table recognition, formula extraction. Best for Chinese/CJK PDFs, scanned documents, and image-heavy presentations. 2. MarkItDown (Microsoft) - Fast text-based extraction for simple text PDFs. 3. pypdf - Last resort fallback for basic text extraction. Video Intelligent Routing: 1. PROBE: Detect embedded subtitles, sidecar files, audio tracks, on-screen text (sample frame OCR) 2. DECIDE: Choose optimal strategy based on content typ
Define, update, and validate recurring cron jobs for OpenClaw workflows.
| name | token-usage-reporter |
| description | Explain and summarize token consumption from lifecycle reports. |
Use this skill to read .openclaw/reports/token-usage-latest.json and summarize:
