agentleFS
Sign inStart free
Duckz289Duckz289/Pipeline-to-proposal-Plugin-STANDARD/skills/research-prospect/SKILL.md

research-prospect

Skill2 starsChanged 4 months agoMITView on GitHub

Quickly researches a company before outreach and suggests who to target. Triggered by "tìm hiểu công ty [tên]", "công ty này thế nào", "có nên tiếp cận không", "ai là người quyết định ở [công ty]", "research [company]", "who should I contact at".

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use when the user only needs to know about a company.

    line 11
  2. Distinctive:

    Add a "what's missing" section of at most 2 lines, only when it genuinely matters.

    line 46
  3. Distinctive:

    If the user has nothing more → write the neutral persona version.

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Research a prospect

Use when the user only needs to know about a company. Email or proposal too → run-pipeline.

Method: ${CLAUDE_PLUGIN_ROOT}/playbooks/research.md.

Goal

A short brief that helps the user decide how to approach them — not a report.

100–220 words. Thin data means an even shorter brief, not a longer one padded with guesses.

Source order

  1. What the user just said.
  2. An existing deal file in <DATA>/deals/.
  3. Website or tax code the user provided.
  4. Public search — only if a tool exists.
  5. Industry patterns, always labelled as guesses.

Vietnamese SME, or the user gave a tax code → check references/vietnam-business-sources.md before concluding there is no data.

Output

### Kết quả
[2–3 sentences: what they do, rough size, whether they look like a fit]

### Góc tiếp cận
- [Problem they may have — say if it is a guess]
- [Who to target: title or persona]

### Việc tiếp theo
- [One concrete action]

Add a "what's missing" section of at most 2 lines, only when it genuinely matters. Headings follow the user's language.

When nothing can be found

Very common. Ask one question, then write:

Mình chưa rõ ABC làm ngành gì. Nên nhắm chủ doanh nghiệp, người vận hành, hay kế toán?
Chưa rõ thì mình viết bản trung tính cho chủ doanh nghiệp.

If the user has nothing more → write the neutral persona version. Do not stall, do not over-apologise.

Never

  • Invent names, titles, headcount, revenue, funding, or the tools they use.
  • Say "this company doesn't have X" when the truth is "X could not be looked up".
  • Promote a search snippet into a verified fact.

References

Load at most one:

  • references/icp-profiles.md — assessing fit
  • references/pain-signal-patterns.md — finding an angle
  • references/vietnam-business-sources.md — Vietnamese SME, thin data

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free