Auto Workflow 1.0.0

Builds automation workflows from repetitive tasks. Use when user mentions "automate", "save time", "reduce manual work", or has repeated tasks.

Security Scan

The skill's purpose (build automations) is plausible, but the runtime instructions encourage the agent to act proactively (build/execute scripts and collect 'system state') without declaring what access is needed or requiring user consent — an incoherent and risky instruction boundary.

Purpose & Capability

The name/description match the instruction content: the skill is an instruction template for turning repeated tasks into workflows and scripts. However, the SKILL.md implies generating and executing scripts and collecting 'system state' while the skill declares no required binaries, config paths, or environment access — a mismatch between suggested capabilities and declared requirements.

Instruction Scope

The instructions explicitly tell the agent to '直接做，不等用户要求' ('do it directly, don't wait for the user') and to 'collect data (system state)' in examples. That gives the agent broad discretion to build and run automations and to read system state without explicit user approval or defined limits. It lacks any requirement to obtain user consent, minimize scope, or avoid sensitive data.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest risk from installation because nothing is written to disk by the skill itself.

Credentials

No environment variables, credentials, or config paths are requested (proportionate on paper). But the documented behavior (generating/executing scripts, reading 'system state') would typically require file or system access; those accesses are not declared or constrained, creating ambiguity about what permissions are actually needed/used.

Persistence & Privilege

The skill is not forced-always and is user-invocable; model invocation is allowed (the platform default). The main concern is the SKILL.md's directive to act proactively — combined with agent autonomy this increases risk, but the skill itself does not request persistent presence or cross-skill configuration changes.

What to consider before installing

This skill is an instruction template that tells the agent to detect repetition and immediately build/execute automations and to 'collect system state.' Before installing, confirm how your agent/platform enforces user consent and execution permissions: ensure the agent cannot run scripts or read files without explicit authorization, and require the skill to document exactly what data it will access and to ask for user approval before executing any automation. Ask the author to add explicit consent/confirmation steps, scope limits (what paths or systems it may read), and a safe sandbox for test runs. Because the SKILL.md encourages proactive action, treat it as higher-risk unless you control the agent's runtime permissions.

Auto Workflow

把重复任务自动化的能力。

能力轮廓

• 输入：重复性任务/手动操作
• 输出：自动化工作流 + 执行脚本
• 核心逻辑：识别 → 抽象 → 自动化 → 测试

工作流

1. 观察 - 用户在重复做什么？
2. 抽象 - 这个任务的模式是什么？
3. 设计 - 怎么自动完成？
4. 实现 - 写脚本/配置
5. 测试 - 小范围验证
6. 优化 - 迭代改进

示例

用户每周手动发周报：

1. 收集数据（系统状态）
2. 整理成模板
3. 发送邮件

自动化后：

• 每周五自动执行
• 收集本周数据
• 生成报告
• 自动发送

思维模式

不是"回答问题"，而是"看到重复→立刻构建自动化"

遇到重复操作时：

• 问自己：能否写成脚本？
• 问自己：下次能否自动跑？
• 直接做，不等用户要求