Skill Claude CodeCodex
Analyze narrated screen recordings and audio files through the talkthrough MCP server — triage feedback into findings, extract specs/backlogs/action items from recordings, and correlate spoken remarks with logs via wall-clock timestamps. Use when the user mentions a screen recording, screencast, narrated video/audio…
Plugin Claude Code
Plugin marketplace listing 1 plugin: talkthrough.
MCP server Claude CodeCodexCursor +2
MCP server "talkthrough-dev" as configured in korovin-aa97/talkthrough-mcp. Runs locally from the diarization Python package.
Instructions file CodexOpenCode
Instructions for korovin-aa97/talkthrough-mcp, covering agents.md, what this is, commands, architecture in one breath and hard rules.
Instructions file
Instructions for korovin-aa97/talkthrough-mcp: Read AGENTS.md — it is the single instruction file for all coding agents in this repository, Claude Code included. No Claude-specific overrides exist.
Agent
Turns one narrated screen recording (processed by the talkthrough MCP server) into precise, evidence-backed findings plus a numbered confirm digest. Never files issues itself — it produces the findings JSON; filing happens only after the recording author approves.
Plugin Claude Code
Turn screen recordings into transcript, exact frames, OCR and wall-clock evidence — then into ready-to-file bug drafts, specs, backlogs and meeting actions. Bundles the talkthrough MCP server, six workflow commands, a triage agent, and an agent skill.
Command
Turn a recorded product demo into a prioritized backlog with timestamped evidence.
Command
Turn one screen recording of a bug into an evidence-backed GitHub issue draft (quote, frames, OCR identifiers, wall-clock; silent recordings work too).
Command
Walk a recording's remarks against system logs using wall-clock timestamps.
Command
Turn a recorded meeting (audio is enough) into action items, decisions, and open questions with timestamps.
Command
Turn a recorded workshop or design walkthrough into a structured spec with quoted decisions and open questions.
Command
Turn a narrated screencast into precise, evidence-backed findings JSON (bug / feature / question routing with frame evidence).
Skill Claude CodeCodex
Analyze narrated screen recordings and audio files — timestamped transcript, scene keyframes, OCR text, and wall-clock anchoring via the local talkthrough MCP server. Use when the user shares a recording or asks to triage feedback, extract meeting actions, or correlate a recording with logs.
MCP server Claude CodeCodexCursor +2
Local MCP server: turn screen recordings into transcript, exact frames, OCR and wall-clock evidence for coding agents. Runs locally from the talkthrough-mcp Python package. Needs 4 environment variables to run.