← 返回 Skills 市场
AI Task Router Auto-Route Prompts by Complexity (Local/Cloud)
作者
Shadow Rose
· GitHub ↗
· v1.0.0
· MIT-0
489
总下载
0
收藏
4
当前安装
1
版本数
在 OpenClaw 中安装
/install task-complexity-router
功能描述
Regex-based routing sends simple tasks to local AI, medium to mid-tier, complex to premium — saving 60%+ on API costs.
安全使用建议
This skill appears to do what it claims: local regex-based routing with no external calls or credential requests. Before installing, consider: 1) The author/source is unknown and there's no homepage — verify the source or run in a sandbox. 2) If you accept customRules from untrusted users, malicious or poorly written regexes can crash the process or cause ReDoS; validate or sandbox user-supplied patterns. 3) Test routing behavior on representative prompts so sensitive requests aren't accidentally sent to cheaper models; tune rules and overrides (context.forceModel) accordingly. 4) Keep backups of any config you persist and run in a controlled environment if you rely on it for production routing.
功能分析
Type: OpenClaw Skill
Name: task-complexity-router
Version: 1.0.0
The skill bundle provides a straightforward regex-based utility for routing AI prompts to different models based on task complexity. Analysis of src/task-router.js reveals no network activity, file system access, or data exfiltration logic, and the SKILL.md documentation contains no prompt-injection attempts or instructions to bypass security controls.
能力评估
Purpose & Capability
The name/description say regex routing by complexity and the code implements that: pattern table, route(message) logic, add/remove/export rules. There are no unrelated environment variables, binaries, or install steps requested.
Instruction Scope
SKILL.md and src/task-router.js confine behavior to local routing decisions. The only scope risk is that config.customRules are accepted and compiled into RegExp at construction time (new RegExp(rule.pattern,...)) — loading untrusted pattern strings can cause runtime exceptions or ReDoS (catastrophic backtracking) if patterns are malicious or poorly written. Otherwise the instructions do not read OS files, env vars, or transmit data.
Install Mechanism
No install spec (instruction-only plus a small JS module). Nothing is downloaded or written to disk by an installer; risk from install mechanism is minimal.
Credentials
The skill declares no required env vars, no primary credential, and the code does not reference process.env or other credentials. Requested privileges are proportionate to a routing library.
Persistence & Privilege
always is false and the skill does not modify other skills or system-wide settings. It exposes exportRules/getRules for local config management only.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install task-complexity-router - 安装完成后，直接呼叫该 Skill 的名称或使用
/task-complexity-router触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial upload
元数据
常见问题
AI Task Router Auto-Route Prompts by Complexity (Local/Cloud) 是什么？
Regex-based routing sends simple tasks to local AI, medium to mid-tier, complex to premium — saving 60%+ on API costs. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 489 次。
如何安装 AI Task Router Auto-Route Prompts by Complexity (Local/Cloud)？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install task-complexity-router」即可一键安装，无需额外配置。
AI Task Router Auto-Route Prompts by Complexity (Local/Cloud) 是免费的吗？
是的，AI Task Router Auto-Route Prompts by Complexity (Local/Cloud) 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
AI Task Router Auto-Route Prompts by Complexity (Local/Cloud) 支持哪些平台？
AI Task Router Auto-Route Prompts by Complexity (Local/Cloud) 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 AI Task Router Auto-Route Prompts by Complexity (Local/Cloud)？
由 Shadow Rose（@theshadowrose）开发并维护，当前版本 v1.0.0。
推荐 Skills