メニュー
Use when asked to analyze, review, or describe a local video file (e.g., .mp4, .mov). Describes how to use the `mt watch` command to stream large videos to Gemini securely with server-side context caching and multi-turn thread support.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | watch |
| description | Use when asked to analyze, review, or describe a local video file (e.g., .mp4, .mov). Describes how to use the `mt watch` command to stream large videos to Gemini securely with server-side context caching and multi-turn thread support. |
mt watchUse this skill when you need to analyze a local video file. Large video files cannot be processed directly in your local context or uploaded as standard attachments without hitting token and size limits. The mt watch command provides a dedicated workflow to securely upload the video in chunks, cache it server-side, and stream Gemini model responses.
To start a new analysis on a video, run mt watch with the file path and your prompt:
mt watch "/path/to/video.mp4" "Describe what happens in this video in detail."
If the prompt is long or complex, you can construct it first and pass it via a variable:
PROMPT="Look closely at the UI transitions. What color is the primary button before and after the click?"
mt watch "/path/to/video.mp4" "$PROMPT"
The command will output the model's text response.
Note: For machine-readable output or extra diagnostics (like file deduplication or cache telemetry), append --json or --verbose.
When you run mt watch with the --verbose flag (or inspect the JSON output), you will receive a thread_id. You can use this thread_id to ask follow-up questions without re-uploading or re-processing the entire video from scratch.
# Add --verbose to see the thread_id
mt watch "/path/to/video.mp4" "Describe the video" --verbose
# Use the returned thread_id for a follow-up:
mt watch "/path/to/video.mp4" "What was the text on the second screen?" --thread <thread_id>
Guide for creating, configuring, and leveraging Mighty actions (action_def), specifically focusing on sandbox_command bindings and the use of setup/teardown commands to execute safe repo-local operations. Use when users ask to define actions, leverage setup_commands/teardown_commands, or understand the action execution model.
Upload local screenshot/video artifacts from agent runs and return renderable file embeds (`![[file ...]]`) plus `mighty-file:` refs for thread UI previews.
Upload files and reference them correctly in Mighty specs/tasks/decisions. Use when asked to attach screenshots, logs, PDFs, or other file artifacts and ensure they are represented in both rich text and graph evidence links.
Use when the user uploads files or a .zip archive (like user research or logs). Describes how to locate attached files in the sandbox, extract archives if necessary, synthesize findings, and save results back to Mighty.
Use the `mt` tool to work with this repo’s Mighty graph: run `mt prime` at session start; prefer `mt search`/`mt tree`/`mt show` before reading code; create specs/decisions/tasks and link evidence; triage `mt inbox`; and close out with `mt closeout` then `mt commit`. For full workflow + templates, run `mt prime`.
Plan work using Mighty (mt) by creating/updating specs and recording decisions, then spawning/structuring implementation tasks. Use when asked to plan/outline/break down a change, draft a spec (feature/rule/invariant/bug), record an ADR-style decision, or turn a fuzzy request into a structured Mighty spec tree with linked tasks.