Loading...
Loading...
Found 15 Skills
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.
Download and analyze social videos using frames + transcript for AI agent understanding at 50× lower cost than multimodal APIs
Use when the user wants to continue work from one agent in another agent, inspect recent sessions, or summarize a saved session or checkpoint for handoff
Extract requirements from existing documents including PDFs, Word docs, meeting transcripts, specifications, and web content. Identifies requirement candidates, categorizes them, and outputs in pre-canonical format.
Extract startup ideas from YouTube videos via solograph MCP — index, search, and analyze video transcripts for business ideas. Multi-MCP coordination pattern (YouTube source → analysis → storage). Use when user says "extract ideas from YouTube", "index YouTube video", "find startup ideas in video", "analyze YouTube for ideas", or "what ideas are in this video". Do NOT use for general YouTube watching (no skill needed) or content creation (use /content-gen).
Analyze the Q&A section of earnings call transcripts for strategic insights, analyst concerns, and management responses on key topics.
Pull recent YouTube transcripts from pre-selected channels and generate topic ideas from them. Use when someone says "mine YouTube", "find video ideas", "what are creators talking about", "YouTube research", "transcript ideas", "content mining", "what should I talk about", "topic ideas from YouTube", or wants to turn other creators' videos into their own content angles. World Code integrated — ideas map to your Bridge when available.
Calculate agreement between human ground truth and machine labels for a text LLM judge metric, then analyze transcripts and reviewer notes to propose an improved metric prompt. One metric at a time.
Analyze meeting transcripts to extract decisions, action items, blockers, sentiment, and generate follow-up emails. Use when user provides meeting notes, transcripts, or recordings and needs structured summaries or action tracking.
[Long Video Reordering] A solution for condensing and restructuring a long video / long livestream replay itself—not cutting short clips, but removing off-topic and redundant parts from the same long content, tightening the argument order, and producing a more compact version. Input the transcript, segment it by argument nodes, decide for each block whether to keep/delete/move later, and output a timecode mapping table. Use when the user says "this livestream/lecture recording is too long, I want to shorten it", "help me create a restructuring plan", "remove off-topic parts and reorder", or "large block reordering". | Produced by XiaoYe
Zero-token session activity harvester. Extracts the activity skeleton for a specified date from the transcripts Claude Code already writes (~/.claude/projects): which projects, what time ranges, what was said, which tools were used, how many tokens were spent. Triggers when the user says "what did I do today", "yesterday's session records", "harvest that day's activity", "mission log". ⚠️ Read-only, no model calls; for daily/weekly reports use /daily-debrief, /weekly-debrief (both built on this skill). English triggers: "what did I work on today", "harvest my sessions", "mission log", "show session activity".
Recap how a session used its skills, and end with findings and a verdict on whether any skill needs changing.