Duckz289Duckz289/Pipeline-to-proposal-Plugin-STANDARD/skills/draft-outreach-email/SKILL.md

draft-outreach-email

Skill2 starsChanged 4 months agoMITView on GitHub

Writes cold outreach emails, follow-ups, LinkedIn/Zalo messages, and call openers. Triggered by "viết email cho [công ty]", "soạn email chào hàng", "follow-up", "khách chưa trả lời viết gì", "tin nhắn LinkedIn", "write an email to", "break-up email".

In this repository9 other files it gives its agents.
- crm-noteSkill
- draft-proposalSkill
- getting-startedSkill
- research-prospectSkill
- run-pipelineSkill
- setup-product-contextSkill
- suggest-next-stepSkill
- update-deal-feedbackSkill
- weekly-summarySkill

The file

We split this skill into the rules it gives an agent

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

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Use when the user only needs buyer-facing copy.
line 11
Distinctive:
Do not ask for: recipient name, exact job title, preferred tone, which case study to use.
line 20
Very specific:
Run ${CLAUDE_PLUGIN_ROOT}/workflows/verification.md.
line 77
Very specific:
Update the deal file per ${CLAUDE_PLUGIN_ROOT}/policies/state-management.md.
line 79

≈ “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

Draft outreach email

Use when the user only needs buyer-facing copy. If they also want research, a proposal, or a next step → run-pipeline.

Writing guidance: ${CLAUDE_PLUGIN_ROOT}/playbooks/messaging.md.

Required

Company name and what the user sells. Missing either → ask exactly one question.

Do not ask for: recipient name, exact job title, preferred tone, which case study to use. All of these have safe defaults.

The most important rule

The email returned must be complete, with no blanks.

Fill every gap with a reasonable assumption and list what to check below. Keep [[EDIT: ...]] in the body only for prices and numbers.

Reason: the user came here to do less work. An email with six holes in it makes the plugin feel worse than using nothing. See ${CLAUDE_PLUGIN_ROOT}/policies/safety-core.md section 3.

Message types

Situation	Type	Length
Never contacted	Cold first touch	60–110 words
Silent 4–7 days	Follow-up #1	40–80
Silent after two touches	Follow-up #2, new angle	40–80
Silent after three	Break-up	40–60
Went cold after interest	Re-engagement	50–80
Just had a call	Recap	60–90
Proposal sent, no reply	Proposal follow-up	40–80
LinkedIn / Zalo	Short message	under 45

Subject under 50 characters.

Output

### Nội dung gửi
Tiêu đề:
- [Option 1]
- [Option 2]

[Complete email]

### Việc tiếp theo
- [What to check — max 2 lines]
- Gửi xong nhắn mình "khách trả lời..." hoặc "chưa thấy hồi âm" để mình cập nhật deal.

Headings follow the user's language.

When data is missing

Missing	Do this
Recipient name	Use "anh/chị" (or a persona in English), note one line
Nothing known about the company	General problem angle, no forced personalisation
No case study	Talk about method, not results
No clear CTA	15-minute call
Weak research	Write the cautious version anyway — do not stall

After writing

Run ${CLAUDE_PLUGIN_ROOT}/workflows/verification.md. If numbers, results, or past customers are mentioned → call ${CLAUDE_PLUGIN_ROOT}/agents/sales-reviewer.md.
Update the deal file per ${CLAUDE_PLUGIN_ROOT}/policies/state-management.md.

References

Load one, never both:

references/email-templates.md — templates by stage
references/objection-responses.md — only when handling an objection

Writing Vietnamese for a buyer → ${CLAUDE_PLUGIN_ROOT}/knowledge/vietnamese-sales-language.md.

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