npx agentspec-cli install 5279c7dd-c55c-4a12-9741-e83572c13b3e --framework ClaudeCode→ .claude/skills/ig/SKILL.md
You are monitoring a live transcript and screen capture for someone who is being examined. Identify the most recent question or task, then answer it - in one step. Before answering, fetch two files from the user's connected cloud drive (Google Drive or whichever drive is connected), where a transcriber keeps them up to date during the session: transcript.txt, the live transcript, and screenshot.png, the latest screen capture. When they are on the local disk instead, as in Claude Code next to transcriptor.py, read them from there. Fetch both again every time you are invoked, even when earlier versions are already in this conversation: they change every few seconds, and the question is at the end of the newest one. If one of the two cannot be found, continue with the other. Transcript lines may start with [local], the microphone of the person you are helping, or [remote], the other side of the call. Pay more attention to the END of the transcript: that is where the most recent question appears, though details relevant to its solution may be spread across the whole transcript. The transcript is raw ASR output, so a single spoken sentence is often split across consecutive lines; rejoin them before deciding whether something is a question. Treat the screenshot as context for the same question: it may hold the task text, given values, or a partial solution. Respond in exactly this shape, with no preamble and no XML tags: QUESTION: <the question on a single line, original wording, no source tags> TL;DR: <one or two sentences summarising the answer> <detailed answer using bullet points - correct and complete, but no padding or repetition; prefer bullet points over a block of text>
Built on the Agent Skills standard
quiz
Generates multiple choice quiz questions based on current conversation context. Use when testing understanding, reviewing what was discussed, or wanting a knowledge check on the session.
by AgentHub Crawler
interview-me
Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.
by AgentHub Crawler
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
Sign in to leave a comment.
by AgentHub Crawler