agentleFS
Sign inStart free
Duckz289Duckz289/Pipeline-to-proposal-Plugin-STANDARD/skills/suggest-next-step/SKILL.md

suggest-next-step

Skill2 starsChanged 4 months agoMITView on GitHub

Advises what to do next with a stalled deal or an unresponsive prospect. Triggered by "deal này giờ sao", "khách chưa trả lời phải làm gì", "bước tiếp theo cho [công ty]", "gửi báo giá lâu rồi chưa thấy gì", "what should I do next with", "this deal is stuck".

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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 needs advice on one deal.

    line 11
  2. Distinctive:

    Only ask when timing genuinely changes the advice and cannot be inferred.

    line 26
  3. Distinctive:

    If a deal file exists, do not make them repeat the history — read it.

    line 28
  4. Distinctive:

    Only mention it if the user says so.

    line 50

≈ “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

Suggest next step

Use when the user needs advice on one deal. Research, email, or proposal too → run-pipeline.

Diagnosis logic: ${CLAUDE_PLUGIN_ROOT}/playbooks/deal-coach.md.

Principle

Return one action, not a list of options. The salesperson is busy — five options pushes the decision back onto them.

And write the message out, do not tell them to write it.

Where timing comes from

  1. The user's own words: "5 days ago", "last week", "after the demo".
  2. The deal file in <DATA>/deals/.
  3. Only ask when timing genuinely changes the advice and cannot be inferred.

If a deal file exists, do not make them repeat the history — read it.

Output

### Kết quả
[Where the deal stands — one sentence. Why it is stuck — one sentence.]

### Việc tiếp theo
- Làm gì: [specific]
- Khi nào: [date]
- Nếu vẫn im lặng: [fallback]

### Nội dung gửi
[The message, written out in full]

Headings follow the user's language.

Never

  • Claim the buyer opened an email, clicked a link, or viewed a proposal — there is no tracking. Only mention it if the user says so.
  • Infer interest from silence.
  • Give vague advice like "keep nurturing the relationship".

Saving

Dated follow-ups go to <DATA>/follow-ups.md per ${CLAUDE_PLUGIN_ROOT}/policies/state-management.md.

References

  • references/follow-up-timing.md — cadence by stage

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