getpaseo/paseo

paseo-advisor

Spin up a single agent as an advisor — second opinion on the current task.

查看源码

使用方法

  1. 复制安装命令,在自己的智能体环境安装前先检查源码包。
  2. 从原始文档核对所需工具、凭据和支持的宿主。
  3. 说明输入材料与期望交付物,并对照来源检查输出。
npx skills add https://github.com/getpaseo/paseo --skill paseo-advisor

开始前需了解

  • 安装不包含模型订阅、API 额度或访问文件的权限。
  • 仓库星数和安装量反映活跃情况,不等于独立质量或安全测试。
仓库原始内容

按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。

Paseo Advisor

Single agent. Reads the situation you're in. Gives a judgment. You decide what to do — the advisor doesn't drive the work.

Use the user's request and current conversation as input, including any arguments supplied with the skill invocation. Optional syntax: [--profile <name>] <question or topic>.

Prerequisites

Read the paseo skill. Call list_profiles before choosing the advisor. Do not create the advisor until you have read the configured profiles and their notes.

Picking the advisor

  1. User named a profile (--profile UI Work) → select it by name.
  2. Otherwise choose the profile whose notes best fit the question. Match the actual work: design and approach, audit and review, or research and root-cause analysis.
  3. Contrast helps. When several profiles fit, prefer a different provider family from your own so the second opinion is genuinely fresh.

Materialize the selected profile into create_agent as described by the paseo skill. If no profile fits, use Paseo's provider discovery fallback.

The briefing

The advisor has zero context. Make it self-contained:

  • The question, sharply.
  • What you've considered and what you've ruled out.
  • Relevant files by path (don't paste — let the agent read).
  • Explicit ask: "give me a recommendation, with reasoning."

End with the no-edits suffix:

This is analysis only. Do NOT edit, create, or delete any files. Do NOT write code.

Forwarded skills

If the user's request contains another skill reference, such as /unslop, /skill:unslop, or $unslop, the user is asking the advisor to run that skill against the current task. Examples:

  • /paseo-advisor /unslop → advisor runs /unslop on the current diff.
  • /paseo-advisor /unslop-risk → advisor does an unslop-risk review.
  • /paseo-advisor $diagnose this build failure → advisor invokes /diagnose.
  • /skill:paseo-advisor /skill:unslop → advisor runs the unslop skill on the current diff in Pi.
  • $paseo-advisor $unslop → advisor runs the unslop skill on the current diff in Codex.

Parse the forwarded skill name from the user's request (/<name>, /skill:<name>, or $<name>), excluding this skill's own invocation. In the briefing, tell the advisor explicitly:

Invoke the `<name>` skill against this task. Load it via the Skill tool before doing anything else.

Pass through any remaining arguments after the skill name as the skill's own input. The advisor — not you — runs the skill; you're still just the orchestrator handing it the work.

Launch and synthesize

Create the advisor agent via Paseo with a [Advisor] <topic> title and the briefing as the initial prompt. Wait for it to finish. Read its response. Synthesize for the user — the advisor's verdict + your recommendation.

Persistent advisor

If the user wants ongoing input ("keep this advisor for the next few decisions"), don't archive after the first reply. Send follow-ups when you need another take. Archive when the user says they're done, or when the topic shifts and a fresh context would serve better.

来自同一仓库

更多 Skills

全部 Skills