Media Diagnostics

Diagnose playback problems in media files and streams. The skill runs a fast triage that classifies the input (VOD file / live stream / HLS stream / TS segment) and then dispatches the matching deep-analysis script. Detection covers moov atom position, codec compatibility, container structure, TS integrity, bitrate/frame-rate anomalies, audio-video sync, and live latency factors.

Absolute Rules

• Read-only: this skill only inspects and reports. It never modifies, deletes, or re-encodes any file, and never pushes to any stream endpoint.
• User-specified target only — ABSOLUTE PROHIBITION: only the single file or URL explicitly provided by the user may be probed. When the target does not exist or is unreachable, do NOT list, search, or scan anything to locate it or a substitute: no directory listings (e.g. ls -la /home/user/downloads/), no file searches (find /home/user -name "*.ts"), no glob patterns (glob **/broken_video.mp4), no guessing URLs, no probing unspecified addresses. Instead take the unreachable degraded conclusion from triage directly and report why the given target failed.
• No credentials: no cloud credentials, API keys, or tokens are required, requested, or used. The skill never calls any cloud API.
• No remediation execution: repair commands (ffmpeg examples) are only suggested in the report. Never execute any repair/transcode command on the user's file without an explicit new instruction from the user.

User Confirmation

• Before running any analysis, confirm the target file path or URL with the user.
• If the user describes symptoms but provides no file or URL, ask for one first. Never fabricate or derive a target on your own.
• If the target comes from task context rather than directly from the user, state the target and its source explicitly before running any check.

Execution Principle