deep-research

What this skill does

# Deep Research Skill

Perform deep research powered by Google Gemini's deep research agent. Upload documents to file search stores for RAG-grounded answers. Manage research sessions with persistent workspace state.

## For AI Agents

Get a full capabilities manifest, decision trees, and output contracts:

```bash
uv run {baseDir}/scripts/onboard.py --agent
```

See [AGENTS.md]({baseDir}/AGENTS.md) for the complete structured briefing.

| Command | What It Does |
|---------|-------------|
| `uv run {baseDir}/scripts/research.py start "question"` | Launch deep research |
| `uv run {baseDir}/scripts/research.py start "question" --context ./path --dry-run` | Estimate cost |
| `uv run {baseDir}/scripts/research.py start "question" --context ./path --output report.md` | RAG-grounded research |
| `uv run {baseDir}/scripts/store.py query <name> "question"` | Quick Q&A against uploaded docs |

## Security & Transparency

**Credentials**: This skill requires a Google/Gemini API key (one of `GOOGLE_API_KEY`, `GEMINI_API_KEY`, or `GEMINI_DEEP_RESEARCH_API_KEY`). The key is read from environment variables and passed to the `google-genai` SDK. It is never logged, written to files, or transmitted anywhere other than the Google Gemini API.

**File uploads**: The `--context` flag uploads local files to Google's ephemeral file search stores for RAG grounding. Sensitive files are automatically excluded: `.env*`, `credentials.json`, `secrets.*`, private keys (`.pem`, `.key`), and auth tokens (`.npmrc`, `.pypirc`, `.netrc`). Binary files are rejected by MIME type filtering. Build directories (`node_modules`, `__pycache__`, `.git`, `dist`, `build`) are skipped. The ephemeral store is auto-deleted after research completes unless `--keep-context` is specified. Use `--dry-run` to preview what would be uploaded without sending anything. Only files you explicitly point `--context` at are uploaded -- no automatic scanning of parent directories or home folders.

**Non-interactive mode**: When stdin is not a TTY (agent/CI use), confirmation prompts are automatically skipped. This is by design for agent integration but means an autonomous agent with file system access could trigger uploads. Restrict the paths agents can access, or use `--dry-run` and `--max-cost` guards.

**No obfuscation**: All code is readable Python with PEP 723 inline metadata. No binary blobs, no minified scripts, no telemetry, no analytics. The full source is auditable at [github.com/24601/agent-deep-research](https://github.com/24601/agent-deep-research).

**Local state**: Research session state is written to `.gemini-research.json` in the working directory. This file contains interaction IDs, store mappings, and upload hashes -- no credentials or research content. Use `state.py gc` to clean up orphaned stores from crashed runs.

## Prerequisites

- A Google API key (`GOOGLE_API_KEY` or `GEMINI_API_KEY` environment variable)
- [uv](https://docs.astral.sh/uv/) installed (see [uv install docs](https://docs.astral.sh/uv/getting-started/installation/))

## Quick Start

```bash
# Run a deep research query
uv run {baseDir}/scripts/research.py "What are the latest advances in quantum computing?"

# Check research status
uv run {baseDir}/scripts/research.py status <interaction-id>

# Save a completed report
uv run {baseDir}/scripts/research.py report <interaction-id> --output report.md

# Research grounded in local files (auto-creates store, uploads, cleans up)
uv run {baseDir}/scripts/research.py start "How does auth work?" --context ./src --output report.md

# Export as HTML or PDF
uv run {baseDir}/scripts/research.py start "Analyze the API" --context ./src --format html --output report.html

# Auto-detect prompt template based on context files
uv run {baseDir}/scripts/research.py start "How does auth work?" --context ./src --prompt-template auto --output report.md
```

## Environment Variables

Set one of the following (checked in order of priority):

| Variable | Description |
|----------|-------------|
| `GEMINI_DEEP_RESEARCH_API_KEY` | Dedicated key for this skill (highest priority) |
| `GOOGLE_API_KEY` | Standard Google AI key |
| `GEMINI_API_KEY` | Gemini-specific key |

Optional model configuration:

| Variable | Description | Default |
|----------|-------------|---------|
| `GEMINI_DEEP_RESEARCH_MODEL` | Model for file search queries | `gemini-3.1-pro-preview` |
| `GEMINI_MODEL` | Fallback model name | `gemini-3.1-pro-preview` |
| `GEMINI_DEEP_RESEARCH_AGENT` | Deep research agent identifier | `deep-research-pro-preview-12-2025` |

## Research Commands

### Start Research

```bash
uv run {baseDir}/scripts/research.py start "your research question"
```

| Flag | Description |
|------|-------------|
| `--report-format FORMAT` | Output structure: `executive_summary`, `detailed_report`, `comprehensive` |
| `--store STORE_NAME` | Ground research in a file search store (display name or resource ID) |
| `--no-thoughts` | Hide intermediate thinking steps |
| `--follow-up ID` | Continue a previous research session |
| `--output FILE` | Wait for completion and save report to a single file |
| `--output-dir DIR` | Wait for completion and save structured results to a directory (see below) |
| `--timeout SECONDS` | Maximum wait time when polling (default: 1800 = 30 minutes) |
| `--no-adaptive-poll` | Disable history-adaptive polling; use fixed interval curve instead |
| `--context PATH` | Auto-create ephemeral store from a file or directory for RAG-grounded research |
| `--context-extensions EXT` | Filter context uploads by extension (e.g. `py,md` or `.py .md`) |
| `--keep-context` | Keep the ephemeral context store after research completes (default: auto-delete) |
| `--dry-run` | Estimate costs without starting research (prints JSON cost estimate) |
| `--format {md,html,pdf}` | Output format for the report (default: md; pdf requires weasyprint) |
| `--prompt-template {typescript,python,general,auto}` | Domain-specific prompt prefix; auto detects from context file extensions |
| `--depth {quick,standard,deep}` | Research depth: quick (~2-5min), standard (~5-15min), deep (~15-45min) |
| `--max-cost USD` | Abort if estimated cost exceeds this limit (e.g. `--max-cost 3.00`) |
| `--input-file PATH` | Read the research query from a file instead of positional argument |
| `--no-cache` | Skip research cache and force a fresh run |

The `start` subcommand is the default, so `research.py "question"` and `research.py start "question"` are equivalent.

**Important**: When `--output` or `--output-dir` is used, the command blocks until research completes (2-10+ minutes). Do not background it with `&`. Use non-blocking mode (omit `--output`) to get an ID immediately, then poll with `status` and save with `report`.

### Check Status

```bash
uv run {baseDir}/scripts/research.py status <interaction-id>
```

Returns the current status (`in_progress`, `completed`, `failed`) and outputs if available.

### Save Report

```bash
uv run {baseDir}/scripts/research.py report <interaction-id>
```

| Flag | Description |
|------|-------------|
| `--output FILE` | Save report to a specific file path (default: `report-<id>.md`) |
| `--output-dir DIR` | Save structured results to a directory |

## Structured Output (`--output-dir`)

When `--output-dir` is used, results are saved to a structured directory:

```
<output-dir>/
  research-<id>/
    report.md          # Full final report
    metadata.json      # Timing, status, output count, sizes
    interaction.json   # Full interaction data (all outputs, thinking steps)
    sources.json       # Extracted source URLs/citations
```

A compact JSON summary (under 500 chars) is printed to stdout:

```json
{
  "id": "interaction-123",
  "status": "completed",
  "output_dir": "research-output/research-interaction-1/",
  "report_file": "research-output/research-interaction-1/report.md",
  "report_size_bytes": 45000,
  "duration_seconds": 154,
  "summary": "First 200 chars of the report..."
}
```

This