目标研究

---
name: target-research
description: Research a target company and write a dossier into shared/companies/ — what they actually build, which team an intern would join, recent specific news, and the overlap with the candidate. Use before writing any first-contact email, when deciding whether a company is worth targeting, or when preparing for an interview.
---

# /target-research, build the company dossier

Usage: `/target-research Space42` · `/target-research "Technology Innovation Institute" --for "<Person Name>"`

The dossier is what makes paragraph 1 of the email possible. Without it, there is only a template with a name pasted in.

## Steps

1. **Check for existing work.** Read `shared/companies/<slug>.md` if it exists. If it was researched inside the last month, refresh the recent-news section rather than starting over. Also run `/obsidian-find <company>` — the vault may already know something.

2. **Add the company to `shared/targets.md`** if it is not there.

3. **Read the candidate's `evidence.md` before searching.** The point is to find overlap, and it is much easier to spot overlap when the search already knows what to look for.

4. **Delegate the search to the `company_researcher` agent.** It has the full method. It reads job postings before marketing pages, because job postings are where the real stack is written down.

5. **Look specifically for:**
   - Open engineering roles, including senior ones. They list the stack
   - The engineering blog, GitHub org, published papers
   - Whether they run an internship programme and through what route
   - One recent, dated, specific, linkable event
   - Which team the candidate would plausibly sit in

6. **Write the dossier** to `shared/companies/<slug>.md` in the format specified in `agents/company_researcher.md`.

7. **Assign a tier** and record why:
   - **Tier 1** — strong technical overlap, plausible route in, worth a properly researched email
   - **Tier 2** — real overlap but a harder route, or a less exact fit
   - **Tier 3** — worth an application through their formal process, not worth a cold email

8. **Say if the answer is no.** A company with no overlap or no reachable route is a legitimate finding. Recording it stops the next session repeating the search.

## Output format

```
## Researched: <company> — Tier <n>

**What they build:** <two sentences of engineering reality>
**Stack:** <from job postings>
**Team to target:** <name>
**Takes interns:** yes | no | formal programme only | unknown

**Paragraph-1 material**
- <specific recent fact> — <URL> (as of YYYY-MM)

**Overlap with <person>**
| They need | <person> has | Strength |
|---|---|---|

**Angle:** <one sentence>
**Gaps:** <what could not be verified>
**Recommendation:** cold email | formal application | skip

**Next:** /find-contact <company>
```

## Rules

- Job postings before marketing pages. Always.
- Date every unstable fact. Team structures and funding move quarterly.
- Never invent a recent event. "No recent public activity found" is a real answer and it changes the angle rather than blocking it.
- Mark inferences as inferences.
- Do not research companies not on the target list. Add them there first so the list stays honest.
- One dossier per company, shared by both people. The overlap section gets a subsection per person.