# Research Playbook

> Use this skill when the user asks for a comparison, ecosystem analysis, or synthesis of open versus managed agent harnesses. It helps the agent gather sources, extract tradeoffs, and turn them into durable markdown artifacts.

- Skill: `cwijayasundara/research-playbook` (Agent Skill)
- Install (CLI): `npx skillmds@latest add cwijayasundara/research-playbook`
- Raw SKILL.md: https://api.skillmd.com/api/skills/cwijayasundara/research-playbook/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: cwijayasundara (https://skillmd.com/u/cwijayasundara)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/cwijayasundara/research-playbook

---


# research-playbook

## Overview
This skill is for requests where the agent must compare approaches, gather external references, and explain design tradeoffs clearly.

## Instructions
1. Gather 2-5 primary sources with `fetch_url`.
2. Extract specific claims about memory ownership, context management, deployment, and lock-in risk.
3. Separate source-backed claims from your own synthesis.
4. Write long findings to `/docs/`.
5. If the result should be machine-readable, call `save_brief` and store the brief in `/docs/briefs/`.

## Output Shape
- Start with the core decision.
- Then explain tradeoffs.
- Then describe what should be owned by the company versus delegated to a model or vendor.