メニュー
Agent Skill for uploading files to Gemini File API and questioning them with Gemini models. Use when a task requires analyzing, transcribing, or asking questions about files (video, audio, images, PDFs, documents, etc.)
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
Agent Skill for planning implementation work into comprehensive, testable steps. Use before implementation to create a clear roadmap for execution.
Agent Skill for writing and reviewing durable design specs. Use when the user asks to write, formalize, save, review, or approve a spec, design document, RFC, or implementation-ready proposal. If the direction is still vague or unsettled, use `brainstorming` first before producing the spec. If the direction is already clear and no spec is needed, use `plan`.
Agent Skill for spawning new AI agents with interactive TUI in tmux. Use when work can be offloaded to new or existing AI agents (exploration, code review, second opinions, parallel work, etc.). Can also be used if spawning new agents with different model families (e.g. Spawn GPT models when you are Claude Code, Spawn Claude models when you are Codex, Or spawn any other models (e.g. DeepSeek, Gemini) with Pi). Prefer harness's own subagent tools when no need for a different model.
Agent Skill for OpenCLI. Use when the user wants to control websites through the `opencli` CLI, run or inspect OpenCLI site/app/external adapters, use the OpenCLI browser bridge/CDP automation
Agent Skill for collaborative brainstorming and design exploration. Use when the user wants to think through an idea, compare options, clarify trade-offs, or get a quick recommendation, without forcing a written artifact. If the user wants a saved, reviewed design spec, use `design-spec`.
Agent Skill for working with Python. Use when writing, editing, or reviewing Python code and scripts.
| name | gemini-files |
| description | Agent Skill for uploading files to Gemini File API and questioning them with Gemini models. Use when a task requires analyzing, transcribing, or asking questions about files (video, audio, images, PDFs, documents, etc.) |
Set GEMINI_API_KEY in the environment or pass --api-key <key> on the command line.
Global options:
--api-key KEY: Gemini API key. Falls back to GEMINI_API_KEY.--json: Return structured JSON instead of plain text.upload: Upload a local file and wait until it becomes ACTIVE or FAILED. Example: uv run scripts/gemini_files.py upload ./clip.mp4query: Ask Gemini a question about an uploaded file. Example: uv run scripts/gemini_files.py query files/abc123 "Summarize this document"list: List uploaded Gemini files. Example: uv run scripts/gemini_files.py liststatus: Show the state and metadata for an uploaded file. Example: uv run scripts/gemini_files.py status files/abc123Usage:
uv run scripts/gemini_files.py upload <file-path> [--timeout SECONDS]
Examples:
uv run scripts/gemini_files.py upload ./meeting.mp4
uv run scripts/gemini_files.py upload ./report.pdf --timeout 600
uv run scripts/gemini_files.py --json upload ./song.wav
Usage:
uv run scripts/gemini_files.py query <file-name> "<question>" \
[--model MODEL] [--system-prompt "..."]
Examples:
uv run scripts/gemini_files.py query files/abc123 "Transcribe this video."
uv run scripts/gemini_files.py query files/abc123 \
"List the action items in this PDF."
uv run scripts/gemini_files.py query files/abc123 \
"Identify the chorus timestamps." \
--system-prompt "Answer as a music analyst."
uv run scripts/gemini_files.py --json query files/abc123 \
"Describe this image." \
--model gemini-3.1-pro-preview
Usage:
uv run scripts/gemini_files.py list
Examples:
uv run scripts/gemini_files.py list
uv run scripts/gemini_files.py --json list
Usage:
uv run scripts/gemini_files.py status <file-name>
Examples:
uv run scripts/gemini_files.py status files/abc123
uv run scripts/gemini_files.py --json status files/abc123
uv run scripts/gemini_files.py upload ./meeting.mp4
uv run scripts/gemini_files.py query files/abc123 \
"Transcribe this video with speaker changes and timestamps when possible."
uv run scripts/gemini_files.py upload ./contract.pdf
uv run scripts/gemini_files.py query files/abc123 \
"Summarize the key obligations and deadlines in this document."
uv run scripts/gemini_files.py upload ./diagram.png
uv run scripts/gemini_files.py query files/abc123 \
"Explain the architecture shown in this image."
uv run scripts/gemini_files.py upload ./research-paper.pdf
uv run scripts/gemini_files.py query files/abc123 "Summarize the paper."
uv run scripts/gemini_files.py query files/abc123 "What are the main limitations?"
uv run scripts/gemini_files.py query files/abc123 "Extract the evaluation metrics."
uv run scripts/gemini_files.py upload ./song.wav
uv run scripts/gemini_files.py query files/abc123 \
"Identify the chorus section timestamps and describe the overall mood."
PROCESSING for a while. Use status to check progress.gemini-3.1-pro-preview. Override it with --model when needed.--model explicitly instead of editing the script in the middle of a task.