tool-use-no-code

Synthesize multiple campaign files and documents to extract insights. Use when the user has multiple campaign briefs, reports, or data files and needs to find patterns, compare results, or answer questions across them. No code required. Works by uploading files to Claude directly. Input: campaign documents, question or context. Output: summary per document, common patterns, anomalies, key insights, recommended actions.

跳到安装

仓库: thaolst/ai-growth-agents-for-marketers
最近来源活动: 2026年5月30日 15:41
检测到的 SKILL.md 语言: 英语
星标: 5
分支: 4

安装方式

默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

直接命令不会经过审查 Prompt；运行前请先检查来源。

npx skills add https://github.com/thaolst/ai-growth-agents-for-marketers --skill tool-use-no-code

命令会保持在同一行。复制前请横向滚动并检查完整内容。

想先保存到本地？可下载 SkillsMP 当前能够提供的文件。

检查来源文件

决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。

SKILL.md

来源说明 · 只读预览

返回搜索返回安装

ab-test-analyzer

Analyze A/B test results and recommend next actions. Use when the user has A/B test data and needs to know: which variant won, whether the result is statistically reliable, and what to do next. Works for conversion rate tests, copy tests, mechanic tests, UI tests. Input: user counts and conversions for control and variant. Output: winner, confidence level, segment breakdown, recommended action. Includes effect size, p-value, and confidence intervals.

2026-06-01

agent-pre-deploy-review

Review an AI agent prompt and setup before deploying it in real work. Use when the user has built or customized an agent and wants a thorough review before depending on it for real campaign work. Input: agent description, system prompt, example input, example output. Output: prompt weaknesses, edge cases, improvement suggestions, monitoring plan, deploy/no-deploy recommendation.

2026-06-01

ai-agent-consultant

Help marketers choose the right type of AI agent for their workflow. Use when a marketer wants to automate a repetitive task but doesn't know what kind of agent to build, or what's even possible with AI agents. Input: task description, frequency, input format, output needed, coding ability. Output: recommended agent type, simplest starting point, full-automation path, risks.

2026-06-01

查看这个仓库的全部 Skills

name	tool-use-no-code
description	Synthesize multiple campaign files and documents to extract insights. Use when the user has multiple campaign briefs, reports, or data files and needs to find patterns, compare results, or answer questions across them. No code required. Works by uploading files to Claude directly. Input: campaign documents, question or context. Output: summary per document, common patterns, anomalies, key insights, recommended actions.
metadata	{"author":"thaolst","version":"1.0","license":"MIT"}

Tool Use — No Code

Bạn là analyst. Đọc toàn bộ tài liệu được cung cấp và trả lời câu hỏi cụ thể.

Cách dùng

Upload file hoặc paste nội dung vào Claude. Hỏi câu hỏi cụ thể về nội dung đó.

Output format

Tóm tắt từng tài liệu trong 2-3 câu. Pattern chung xuất hiện lặp lại. Điểm mâu thuẫn hoặc bất thường. 3 insight quan trọng nhất. 2-3 hành động đề xuất.

Nguyên tắc

Dẫn nguồn cụ thể khi trả lời. Nếu không tìm thấy thông tin liên quan, nói rõ thay vì đoán. Ưu tiên insight có thể dẫn đến hành động cụ thể.

English

You are an analyst. Read all provided documents and answer specific questions about them.

Cite sources when answering. If information is not found in the documents, say so rather than guessing. Prioritize insights that lead to specific actions.

tool-use-no-code

来源信息

安装方式

检查来源文件

同仓库更多 Skills

同仓库更多 Skills

Tool Use — No Code

Cách dùng

Output format

Nguyên tắc

English

Tool Use — No Code

Cách dùng

Output format

Nguyên tắc

English