Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Getting Started

ASecurity

Introduces the plugin with copy-paste examples, for new users or vague requests. Triggered by "plugin này làm được gì", "hướng dẫn", "bắt đầu sao", "dùng thế nào", "chào", "hello", "help", "what can you do", or any sales request with no clear output.

2 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgoapidatabase

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add Duckz289/Pipeline-to-proposal-Plugin-STANDARD --skill getting-started --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Getting Started?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Getting Started
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/duckz289-getting-started/badge)](https://www.skillsdirectory.com/skills/duckz289-getting-started)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: getting-started
description: >
  Introduces the plugin with copy-paste examples, for new users or vague requests.
  Triggered by "plugin này làm được gì", "hướng dẫn", "bắt đầu sao", "dùng thế nào",
  "chào", "hello", "help", "what can you do", or any sales request with no clear output.
---

# Getting started

Use when the user does not know what to type, or the request is too general to guess which artifact
they need.

**Give copy-paste examples, not an abstract menu.** A newcomer does not know what "research" or
"pipeline" means in this context.

## Standard response

Return this structure, in the user's language.

**The middle example must never default to software.** A first-time user reads it as "who this
plugin is for" — if it always says "phần mềm quản lý kho", anyone selling something else quietly
concludes this is a dev tool and leaves. Two rules, in order:

1. If the user already said what they sell anywhere in this conversation, use **that** — real
   product, real rough price if known.
2. Otherwise, **pick one non-software example and vary it between conversations** rather than
   defaulting to the same one every time — rotate through a physical good, a service, and a
   professional service, not three variations of software:

   - "mình bán dịch vụ vệ sinh văn phòng, từ 3 triệu/tháng"
   - "mình bán vật liệu xây dựng, báo giá theo đơn hàng"
   - "mình bán dịch vụ kế toán thuê ngoài, từ 5 triệu/tháng"
   - "mình bán máy móc công nghiệp cho nhà xưởng"

Vietnamese:

~~~
Mình giúp bạn ba việc. Copy một dòng dưới đây rồi sửa cho đúng khách của bạn:

**Tìm hiểu một công ty trước khi liên hệ**
    Tìm hiểu công ty ABC giúp mình

**Viết email chào hàng hoặc follow-up**
    Viết email cho ABC, mình bán dịch vụ vệ sinh văn phòng từ 3 triệu/tháng

**Khách im lặng, không biết làm gì tiếp**
    Gửi proposal cho ABC 5 ngày rồi chưa thấy trả lời

Sau khi gửi cho khách, cứ nhắn mình kết quả — "khách trả lời rồi" hoặc "chưa thấy hồi âm" —
mình sẽ nhớ giúp deal đó đang tới đâu.
~~~

(Swap the second example's product/price for one of the rotation above, or the user's own stated
offer, each time this screen is shown — do not let it ossify into a fixed script.)

English:

~~~
I can help with three things. Copy a line below and change it to fit your prospect:

**Look into a company before reaching out**
    Tell me about ABC Logistics

**Write a cold email or a follow-up**
    Write an email to ABC, I sell office cleaning services from $150/month

**They've gone quiet and you're not sure what to do**
    Sent ABC a proposal 5 days ago, no response

After you send something, just tell me what happened — "they replied" or "still nothing" —
and I'll keep track of where each deal stands.
~~~

## If they ask something specific

**"Where is my data stored?"**
→ Give the real path (see `${CLAUDE_PLUGIN_ROOT}/policies/state-management.md`), and be clear: deal memory stays on their
machine and the plugin author receives nothing, but chat content still goes to Claude like any other
conversation.

**"Does it send emails for me?"**
→ No. It drafts, they send. It does not write to a CRM either.

**"Do I need to install anything else?"**
→ No. No server, no database, no API key.

**"I sell [X] — will this work?"**
→ Yes if it is B2B, selling to companies or organisations. Less useful for consumer retail.

## Routing

| They say | Go to |
|---|---|
| research, "tell me about this company" | `${CLAUDE_PLUGIN_ROOT}/skills/research-prospect/SKILL.md` |
| email, follow-up, message | `${CLAUDE_PLUGIN_ROOT}/skills/draft-outreach-email/SKILL.md` |
| proposal, quote | `${CLAUDE_PLUGIN_ROOT}/skills/draft-proposal/SKILL.md` |
| stuck deal, no response, what next | `${CLAUDE_PLUGIN_ROOT}/skills/suggest-next-step/SKILL.md` |
| several things at once | `${CLAUDE_PLUGIN_ROOT}/skills/run-pipeline/SKILL.md` |
| remember my offer | `${CLAUDE_PLUGIN_ROOT}/skills/setup-product-context/SKILL.md` |

**Never show this screen when the user already made a clear request.** It is only for when they are
stuck.

Attribution

Duckz289Duckz289
View sourceMore from Duckz289 →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →