ai-prompt-generator

Generate and optimize precise AI prompts using templates and styles for models like GPT-4, Claude, Gemini, and Qwen.

Security Scan

This skill is internally coherent and does not request credentials or perform network/file I/O, but its README/SKILL.md overstates features that the included code does not implement.

Purpose & Capability

The name/description promise multi-model adaptation, quality scoring, A/B testing and continuous optimization. The included index.js only parses CLI args and prints template-related messages — it does not call any models, perform scoring, run A/B tests, or handle optimization logic. This is an overstatement of capability, but not a security mismatch.

Instruction Scope

SKILL.md documents actions like --action optimize and --input <file>, plus paid-usage behavior. index.js does not read input files or implement optimization/testing features; it only prints outputs and a fixed price. The runtime instructions therefore promise behavior the code doesn't perform (functional inconsistency), but they do not instruct the agent to access unrelated system files, env vars, or external endpoints.

Install Mechanism

There is no install specification and no downloads. The skill is instruction-only with a small included CLI script; nothing will be written to disk by an installer and no external packages are pulled in by an install step.

Credentials

The skill declares no required environment variables, no credentials, and no config paths. The code likewise does not read env vars or credentials. Requested permissions are proportional (minimal).

Persistence & Privilege

always is false and the skill does not request persistent or system-wide privileges. It does not modify other skills or agent configuration. Autonomous invocation is allowed by default but is not combined with any broad credential access.

Assessment

This skill appears safe from a security perspective: it doesn't access network, files, or credentials. However, its documentation and README promise features (model calls, scoring, A/B testing, optimization, billing flow) that the included code does not implement — the CLI only prints templates and a fixed price. Before relying on it: (1) confirm where and how billing is enforced (the skill mentions a ¥3 fee but contains no payment integration), (2) don't expect real model integration or optimization unless the author supplies additional code, and (3) if you need the promised features, request an implementation or run the skill in a sandbox. The author/source is unknown and there's no homepage; if provenance matters, seek a verified source or more details from the publisher.

AI Prompt Generator - AI 提示词生成器

Description

专业 AI 提示词生成工具，帮助用户创建高效、精准的 AI 提示词。内置多种框架和模板，让 AI 输出质量提升 10 倍。

Usage

# 生成提示词
/ai-prompt-generator --task "写博客" --model "gpt-4" --style "detailed"

# 使用模板
/ai-prompt-generator --template "cot" --topic "数据分析"

# 优化已有提示词
/ai-prompt-generator --action "optimize" --input "your-prompt.txt"

参数说明

• --task: 任务描述
• --model: 目标 AI 模型 (gpt-4, claude, gemini, qwen)
• --style: 提示词风格 (detailed, concise, creative, analytical)
• --template: 使用模板 (cot, role, few-shot, chain)
• --action: 操作类型 (generate, optimize, test)

Pricing

• 价格: ¥3/次
• 计费方式: 按次收费
• 免费试用: 前 5 次免费

Features

• ✅ 多模型适配
• ✅ 框架模板库
• ✅ 质量评分
• ✅ A/B 测试
• ✅ 持续优化