# 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.

- **Type:** Skill
- **Install:** `agentstack add skill-korovin-aa97-talkthrough-mcp-clawhub`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [korovin-aa97](https://agentstack.voostack.com/s/korovin-aa97)
- **Installs:** 0
- **Category:** [Content & Media](https://agentstack.voostack.com/c/content-and-media)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [korovin-aa97](https://github.com/korovin-aa97)
- **Source:** https://github.com/korovin-aa97/talkthrough-mcp/tree/main/integrations/openclaw/clawhub

## Install

```sh
agentstack add skill-korovin-aa97-talkthrough-mcp-clawhub
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 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:

```bash
openclaw mcp add talkthrough --command uvx --arg talkthrough-mcp
```

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

## Workflow

1. `process_media(path)` — idempotent by content hash; returns a compact
   summary with job_id (re-calls on the same file are instant).
2. `get_transcript(job_id)` / `search(job_id, "")` — orient; search
   covers speech AND on-screen OCR text.
3. `get_moment(job_id, t0-2000, t1+2000)` — evidence bundle per remark:
   transcript slice + up to 3 frames + OCR + wall-clock range.
4. `extract_frame(job_id, at_ms, crop=...)` — exact instant, native
   resolution, when keyframes miss the moment.
5. `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

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [korovin-aa97](https://github.com/korovin-aa97)
- **Source:** [korovin-aa97/talkthrough-mcp](https://github.com/korovin-aa97/talkthrough-mcp)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-korovin-aa97-talkthrough-mcp-clawhub
- Seller: https://agentstack.voostack.com/s/korovin-aa97
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.