Skip to content
All Skills

Research

Deep research on a topic, creating persistent documentation for future reference. Use for technology decisions, competitive analysis, or complex topics.

Data, AI & Research|v1|Updated 7/14/2026|GitHub source
MCP get_skill({ skillId: "research-1b8df63f" })

Use this skill with your agent

Create a free account and connect via MCP

Get Started Free
# /research

Deep research creating persistent documentation for future reference. Uses Ultrathink for comprehensive analysis.

## Usage

```bash
/research "authentication patterns for multi-tenant SaaS"
/research "real-time collaboration architectures"
/research "Jira vs Linear competitive analysis"
/research "WebSocket vs SSE trade-offs"
```

## Output Locations

```
ideas/
├── [project]/notes/research/     # Project-specific
├── shared/docs/research/         # Cross-project
└── resources/research/           # General reference
```

**Location rules:**
- Project-specific: `ideas/{project}/notes/research/`
- Cross-project: `shared/docs/research/`
- General reference: `resources/research/`

## Process

### 1. Check Existing Research
```bash
grep -r "authentication" ideas/*/notes/research/
grep -r "authentication" shared/docs/research/
```

If found, ask: "Research exists. Update, view, or create new?"

### 2. Deep Research Phase

Invoke `research-specialist` agent:

**Research scope:**
- Official documentation (via Context7)
- Technical blogs and tutorials
- Stack Overflow (high-vote answers)
- GitHub discussions and issues
- Community forums
- Existing solutions/products

**Volume**: Read 20-30+ sources, distill to 3-5 pages

### 3. Create Research Document

**Naming**: lowercase kebab-case (e.g., `auth-patterns-saas.md`)

**Structure:**
```markdown
---
created: YYYY-MM-DD
updated: YYYY-MM-DD
sources: NUMBER
related:
  - path/to/related/file.md
tags: ["primary-tag", "secondary-tag"]
---

# Research: [Topic]

## Executive Summary
[2-3 paragraphs of key findings]

## Detailed Findings

### [Subtopic 1]
[Analysis]

### [Subtopic 2]
[Analysis]

## Recommendations
[What to do based on research]

## Must-Read Resources
1. **[Title]** - [url]
   - Why: [Reason]
   - Key point: [Takeaway]

## Additional Resources
- [Title] - [url]

## Gotchas & Warnings
- [Warning 1]

## Decision Matrix (if comparing)

| Criteria | Option A | Option B |
|----------|----------|----------|
| Ease of use | ⭐⭐⭐ | ⭐⭐ |
| Scalability | ⭐⭐⭐⭐ | ⭐⭐⭐ |
```

### 4. Link to Related Work

If research relates to a spec or issue:
- Add reference in research doc
- Update spec/issue to reference research

## When to Use

**Good candidates:**
- Technology decisions affecting architecture
- Competitive analysis for product positioning
- Complex topics with many options
- Best practices you'll reference multiple times
- Market research for product ideas

**Not needed for:**
- Quick one-off questions (just ask)
- Simple API lookups (use Context7)
- Project-specific debugging

## Updating Research

If research exists but is outdated:
```
Options:
1. Update existing (add new findings)
2. Replace entirely (fresh research)
3. View existing
4. Cancel
```

## Integration

Research documents are discovered by:
- `/plan` - Checks for relevant research before planning
- `/spec` - References research in technical notes
- Future sessions - Research persists for reference

```
/research "topic" → ideas/{project}/notes/research/topic.md
                           ↓
              Future work automatically references this
```
#personal-productivity#daily-routine#weekly-review#life-planning#personal-knowledge#deep#research

Related Skills

More skills in Data, AI & Research

Ablation Planner

Use when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent designs ablations from a reviewer's perspective; the local executor reviews feasibility and implements.

#broad-capability#wanshuiyin-arisMIT

Ablation Planner

Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.

#broad-capability#wanshuiyin-arisMIT

About

Provides information about the bitwize-music plugin, its version, and its creator. Use when the user asks about the plugin, its purpose, version, or capabilities.

#github#broad-capabilityCC0-1.0

Ab Test Analysis

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.

#work-life#productivityMIT

Academic Search

Search and analyze academic literature. Find papers, understand research methodologies, and synthesize academic findings for research projects.

#work-life#officeMIT

Adaptyv

How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.

#broad-capability#scienceMIT