# Deep Research

Deep research on any topic using parallel sub-agents, the available search tool...

- Repository: https://github.com/XiaomiMiMo/MiMo-Code (13741 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add XiaomiMiMo/MiMo-Code --skill deep-research -g -a claude-code -y`
Codex: `npx skills add XiaomiMiMo/MiMo-Code --skill deep-research -g -a codex -y`
Cursor: `npx skills add XiaomiMiMo/MiMo-Code --skill deep-research -g -a cursor -y`
Gemini CLI: `npx skills add XiaomiMiMo/MiMo-Code --skill deep-research -g -a gemini-cli -y`

## Description

Deep research on any topic using parallel sub-agents, the available search tool (websearch or a search MCP server), WebFetch and free APIs. Use when the user asks for a thorough multi-source investigation with a cited report, "深度调研X"、"deep research"、"帮我全面研究一下"、"多方求证"、"写一份调研报告". NOT for simple lookups (a single search suffices) and NOT for academic literature surveys (use auto-research skill instead).

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Deep Research

Orchestrate parallel research sub-agents, then write one coherent cited report. Research is parallel; writing is single-point, never let multiple agents write report sections.

## Step 0, Always first

1. Run `date +%Y-%m-%d` via Bash. Never assume the current year from training data.
2. Triage:
   - Answerable with 1-2 searches? → STOP, just search directly. Do not use this skill.
   - Enumeration task (N items × M fields, e.g. "compare 20 frameworks")? → still this skill, but use table-oriented decomposition (one sub-agent per item batch).
   - Open-ended investigation? → continue below.
3. Pick depth (default **standard**; user can override with words like "quick"/"exhaustive"):

| Mode | Sub-agents (round 1) | Max follow-up rounds | Sources target |
|---|---|---|---|
| quick | 2-3 | 0 | 8+ |
| standard | 3-5 | 1 | 15+ |
| deep | 5-8 | 2 | 25+ |

These are hard budgets. Reflection (Phase 4) can spend them but never exceed them.

## Workspace

All state lives on disk at `./research/<slug>/`, never only in context (survives compaction):

```
research/<slug>/
├── brief.md         # research brief, the single contract for all phases
├── findings/        # F1.md, F2.md ... one per sub-agent, structured evidence
└── REPORT.md        # final deliverable
```

On resume: re-read `brief.md` + list `findings/`, skip completed angles, continue.

## Phase 1, Scope

Ask at most one round of clarifying questions (AskUserQuestion), only if genuinely ambiguous: audience, time frame, region, decision at stake. If the user said "just run it" or intent is clear, skip asking and write assumptions into the brief instead.

Then write `brief.md`: refined question, scope boundaries (in/out), assumptions, depth mode, today's date. This brief, not the raw conversation, is what every later phase measures against.

## Phase 2, Plan

The rest: https://github.com/XiaomiMiMo/MiMo-Code/blob/HEAD/packages/cli/src/skill/builtin/.bundle/deep-research/SKILL.md