Skip to content
Development
Skill

/pudo-plan

PUDO Plan phase: turn a request into a short plan card (goal, scope, out of scope, success criteria, risks, steps) before any code is written. Use when the user says "plan this", "/pudo-plan", or starts a non-trivial feature, fix or refactor.

BOOST
From plugin
pudo-code-system
538 skills1 agent
Install
$ npx -y skills add DongDuong2001/pudo-code-system --skill pudo-plan --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/pudo-plan

Context preview

The summary Claude sees to decide when to auto-load this skill.

PUDO Plan phase: turn a request into a short plan card (goal, scope, out of scope, success criteria, risks, steps) before any code is written. Use when the user says "plan this", "/pudo-plan", or starts a non-trivial feature, fix or refactor.

SKILL.md

pudo-plan.SKILL.md
name: pudo-plan
description: >
  PUDO Plan phase: turn a request into a short plan card (goal, scope, out of
  scope, success criteria, risks, steps) before any code is written. Use when
  the user says "plan this", "/pudo-plan", or starts a non-trivial feature, fix
  or refactor.

PUDO Plan

Read the request and the files it touches first. Then reply with this card and stop for approval when the work is risky or unclear:

Goal:              one sentence, in the user's terms
Scope:             files and behaviour that change
Out of scope:      what you will not touch
Success criteria:  checks that prove it works (tests, commands, observable result)
Risks:             data loss, breaking callers, security, unknowns
Steps:             3-7 small steps, each verifiable

Rules:

  • Every success criterion must be checkable by a command or an observable result. "Works well" is not one.
  • Name the smallest version that does the core job. List anything bigger as a follow-up, not a step.
  • If a step deletes or overwrites data, say so in Risks and ask first.
Ships withpudo-code-system

Modular, scalable, automated development intelligence.

Get the whole plugin

Other skills on pudo-code-system.