comprehensive-research

Files (2)

• SKILL.md
• evaluations.json · evals/

SKILL.md (first lines)

# Comprehensive Research Skill

## Critical Importance

**Thorough research is critical to solving complex problems correctly.** Poor or incomplete research leads to wrong solutions, wasted time building the wrong things, and repeating past mistakes. Missing a key file, misunderstanding historical decisions, or overlooking relevant patterns causes rework and frustration. Comprehensive research upfront saves orders of magnitude more time than it costs. Every implementation decision should be grounded in thorough understanding.

## Systematic Approach

** approach research systematically.** Research is not linear—it requires iterative discovery, parallel investigation, and constant refinement. Don't jump to conclusions—gather evidence from multiple sources, cross-reference findings, and validate assumptions. Use the multi-phase methodology: scope definition, parallel discovery, sequential analysis, and synthesis. Each phase builds on the previous one. Rushing research guarantees missing important information.

## The Challenge

**The conduct truly comprehensive research without getting lost in the details or missing the big picture, but if you can:**

- Your solutions will be well-founded and robust
- You'll avoid repeating historical mistakes
- Your documentation will be authoritative
- Team members will trust your research

The challenge is balancing breadth (covering everything relevant) with depth (understanding deeply) while staying focused on the research objective. Can you find the critical information efficiently without drowning in noise?

## Research Confidence Assessment

After completing research, rate your confidence from **0.0 to 1.0**:

- **0.8-1.0**: Found comprehensive evidence, all claims documented, historical context understood, clear conclusions
- **0.5-0.8**: Good coverage but some areas could use deeper investigation, minor uncertainty about certain findings
- **0.2-0.5**: Basic investigation completed but likely missed important information, significant gaps remain
- **0.0-0.2**: Research insufficient, critical areas uninvestigated, conclusions speculative

Identify uncertainty areas: What evidence is weak or missing? Which sources are unreliable? What questions remain unanswered? What risks exist due to research limitations?

## Methodology

A systematic multi-phase research orchestration skill that coordinates specialized agents to conduct thorough investigations across codebases, documentation, and external sources. Based on proven patterns from codeflow research workflows with incentive-based prompting enhancements.

## How It Works

This skill orchestrates a disciplined research workflow through three primary phases:

1. **Discovery Phase** (Parallel): Multiple locator agents scan simultaneously
2. **Analysis Phase** (Sequential): Deep analyzers process findings with evidence chains
3. **Synthesis Phase**: Consolidated insights with actionable recommendations

## Research Methodology

### Phase 1: Context & Scope Definition

Before spawning agents, establish:

```markdown
## Research Scope Analysis
- **Primary Question**: [Core research objective]
- **Decomposed Sub-Questions**: [Derived investigation areas]
- **Scope Boundaries**: [What's in/out of scope]
- **Depth Level**: shallow | medium | deep
- **Expected Deliverables**: [Documentation, recommendations, code refs]
```

**Critical Rule**: Always read primary sources fully BEFORE spawning agents.

### Phase 2: Parallel Discovery

Spawn these agents concurrently for comprehensive coverage:

| Agent | Purpose | Timeout |
|-------|---------|---------|
| `codebase-locator` | Find relevant files, components, directories | 5 min |
| `research-locator` | Discover existing docs, decisions, notes | 3 min |
| `codebase-pattern-finder` | Identify recurring implementation patterns | 4 min |

**Discovery Output Structure**:
```json
{
  "codebase_files": ["path/file.ext:lines"],
  "documentation": ["docs/path.md"],
  "patterns_identified": ["pattern-name"],
  "coverage_map": {"area": "percentage"}
}
```

### Phase 3: Sequential Deep Analysis

After discovery completes, run analyzers sequentially:

| Agent | Purpose | Depends On |
|-------|---------|------------|
| `codebase-analyzer` | Implementation details with file:line evidence | codebase-locator |
| `research-analyzer` | Extract decisions, constraints, insights | research-locator |

**For Complex Research, Add**:
| Agent | Condition |
|-------|-----------|
| `web-search-researcher` | External context needed |
| `system-architect` | Architectural implications |
| `database-expert` | Data layer concerns |
| `security-scanner` | Security assessment needed |

### Phase 4: Synthesis & Documentation

Aggregate all findings into structured output:

```markdown
---
date: YYYY-MM-DD
researcher: Assistant
topic: 'Research Topic'
tags: [research, relevant, tags]
status: complete
confidence: high|medium|low
---

## Synopsis
[1-2 sentence summary of research objective and outcome]

## Summary
[3-5 bullet points of high-level findings]

## Detailed Findings

From v1truv1us/ai-eng-system, MIT.

More from v1truv1us/ai-eng-system