research

Research

Persistent project-scoped store for deep research findings in Codex. You activated this skill because the user asked a substantive research question, or invoked it explicitly with /research <topic>.

If invoked with a topic argument (e.g. /research tailwind-v5), use it as the seed for Retrieval - start by looking up that topic in INDEX.md. Don't research blindly; the lookup may answer immediately.

Four rules carry this skill. They are stated here first because they matter most, and restated at the end:

1. Investigations start from zero context. Everything they need goes in one self-contained brief, whether run inline or by a subagent.
2. The contrarian pass is mandatory. An investigation without it is incomplete; re-run or fill it yourself.
3. The main agent owns all file writes. Investigations return text; only you touch .research/.
4. Investigation always ends in Storage. Fresh research that never reaches .research/ is a failed run; verify the write before reporting done.

When to use

• "what's the latest npm package that does X"
• "compare A vs B vs C for 2026"
• "which engines / frameworks / libraries can clone X fast"
• "research how Y works under the hood"
• "deep dive on Z"
• User pastes a long markdown research dump and asks you to save it

When NOT to use

• Plan-stage notes
• Small facts or one-line preferences
• Code-level decisions tied to one file
• Casual lookups answerable from a single source with no synthesis
• Recording personal ideas or musings
• As a substitute for a single focused web search or page fetch

If a single web search + 1-2 sentences answers the question, you don't need this skill.

A subjective or ambiguous question ("best X", "which is better") is not automatically casual: "best" means a comparison across current options, which is exactly what this skill does. Pick the most common reading of the question, state it in one line, and proceed; put alternative readings in ## Open questions. Do not stall by asking the user which variant they meant.