---
name: hq-new-research
description: Use when starting a new research effort in HQ — an idea, technology or approach worth investigating before it is committed to design. Triggers on "research X", "investigate X", "spike X", "should we use X", "is X worth doing".
---

# hq-new-research

Scaffolds a new research effort. **Authoritative playbook:**
[`00-META/process/01-research.md`](../../../00-META/process/01-research.md) — read it;
this skill only does the mechanical setup.

## Steps

1. Find the next free number: list `01-RESEARCH/NNN-*`, take the highest plus one, zero-padded
   to three digits.
2. Create `01-RESEARCH/NNN-descriptive-name/` (kebab-case from the topic).
3. Create `00-overview.md` in it with exactly this frontmatter, then a prose summary of **what** is
   being investigated, **why**, and **what it touches**:

   ```yaml
   ---
   status: active
   initiated: YYYY-MM-DD
   touches: []
   became: []
   ---
   ```

4. Do the research in further documents in the same folder. Keep the summary current.

## Do not

- Do not restate the status in prose. It lives in frontmatter, in one place.
- Do not fill `became:` while the effort is open — `hq-graduate` sets it at closure.
- Do not skip or reuse a sequence number.
- Do not write into `03-DESIGN` from an open effort.
- Do not name the mesh being observed. Evidence is required; identification is forbidden.

## Closing

An effort never just stops. It closes through `hq-graduate` as `graduated` or `abandoned`,
always with `became:` pointing at what it turned into. Nothing is deleted.