How do I install the Talkthrough skill?

Run npx skillmds@latest add korovin-aa97/talkthrough-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Talkthrough safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Talkthrough?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Talkthrough free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Talkthrough?

korovin-aa97 (@korovin-aa97) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Talkthrough by korovin-aa97 — Agent Skill

Name: Talkthrough
Author: korovin-aa97

Talkthrough

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.

korovin-aa97 affa167 1.8 KB Updated Sep 17, 2026

File contents

talkthrough for OpenClaw

This skill wires the talkthrough MCP server into OpenClaw and teaches the workflow. Everything runs locally: recordings never leave the machine.

Setup (once)

Add the MCP server:

openclaw mcp add talkthrough --command uvx --arg --python --arg ">=3.11,<3.14" --arg "talkthrough-mcp[diarization,url]"

Requires uv (https://astral.sh/uv). First processing downloads a whisper model once (~460 MB for the default small).

Workflow

process_media(path) — idempotent by content hash; returns a compact summary with job_id (re-calls on the same file are instant). For one public video/audio URL use process_url(url): the source is downloaded once (the only network step), then everything below is local.
get_transcript(job_id) / search(job_id, "<word>") — orient; search covers speech AND on-screen OCR text.
get_moment(job_id, t0-2000, t1+2000) — evidence bundle per remark: transcript slice + up to 3 frames + OCR + wall-clock range.
extract_frame(job_id, at_ms, crop=...) — exact instant, native resolution, when keyframes miss the moment.
list_jobs() — recordings processed earlier remain queryable.

Timestamps: t_ms is video-relative; t_wall is real wall-clock time when the recording start is known — use it to correlate remarks with logs (±30 s window). Audio-only files (.m4a/.mp3/…) have transcripts but no frames; frame tools erroring on them is expected.

Full docs: https://github.com/korovin-aa97/talkthrough-mcp

Frequently asked questions