Research Methodology Skill

SkillSearch

Structured research protocol: investigate technologies, patterns, APIs before implementation. Multi-tool search, research logs, training data fallback honesty.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Research Methodology Skill skill

What this skill tells your AI

The instructions your AI receives, as published by irahardianto/awesome-agv in .agents/skills/research-methodology/SKILL.md and read by ahel’s review.

Ensure code is informed by accurate, up-to-date knowledge — not stale training data.

When to Invoke

  • Before implementing with unfamiliar tech
  • Evaluating library/framework options
  • Architect informing design decisions
  • Builder encountering unknown API/pattern

Process

1. Topic Decomposition

Break into 2-5 keyword searchable topics:

"Task CRUD API with Supabase":
  1. Supabase client library JS/TS
  2. Supabase RLS policies
  3. Supabase real-time subscriptions
  4. PostgreSQL UUID PK patterns
  5. TS type generation from Supabase

2. Multi-Tool Search

PriorityToolBest For
1stQurio MCPDeep doc search, official docs
2ndContext7/similar MCPLibrary-specific API refs
3rdSupabase MCPSupabase-specific docs
4thsearch_webGeneral, blogs, SO
5thread_url_contentDeep reading specific pages

Strategy: broad search → find doc page → deep read → search gotchas + edge cases.

3. Document Findings

Path: docs/research_logs/{feature_name}.md

# Research: {Topic}
Date: {date}
Researcher: {agent}

## Topics Investigated
1. {topic} — {tool} — {finding}

## Key Patterns
- {Pattern}: {description + code}

## API Signatures
```{lang}
// Exact API from docs

Gotchas

  • {Gotcha}: {avoidance}

Code Examples

// Working examples from docs

Sources

Training Data Reliance

  • {topic}: Relying on training data. No external verification.

### 4. Training Data Fallback

If no search yields results:
1. Document queries attempted + tools used
2. Explicitly state: "Relying on training data for {topic}. External verification unavailable."
3. Flag for human review
4. If critical, ask user for docs

**Never silently use training data when verification is available.**

### 5. ADRs

If research reveals choice between 2+ approaches, new dependency, or arch change → create ADR via `adr` skill at `docs/decisions/NNNN-short-title.md`. The `adr` skill template produces structured-spec-compatible ADRs with YAML frontmatter and `<!-- decision -->` annotations.

## Agent Integration

| Agent | Usage |
|---|---|
| Architect | Research before design, inform ADRs |
| Backend | Unfamiliar APIs, library patterns |
| Frontend | Component libs, CSS patterns |
| Mobile | Platform APIs, Flutter packages |
| Database | Query patterns, extensions |

Research logs persist in `docs/research_logs/` for cross-session knowledge. ADRs follow `adr` skill format.

Signals

GitHub stars
156
Forks
53
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
research-methodology
Source
github.com/irahardianto/awesome-agv