Skip to content
Development
Skill

/pudo-review

PUDO Optimize gate: review the current diff against the plan before calling work done: correctness, edge cases, tests, scope creep, remaining risks. Use when the user says "review", "/pudo-review", "is this done", or before a commit, PR or handoff.

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

Context preview

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

PUDO Optimize gate: review the current diff against the plan before calling work done: correctness, edge cases, tests, scope creep, remaining risks. Use when the user says "review", "/pudo-review", "is this done", or before a commit, PR or handoff.

SKILL.md

pudo-review.SKILL.md
name: pudo-review
description: >
  PUDO Optimize gate: review the current diff against the plan before calling
  work done: correctness, edge cases, tests, scope creep, remaining risks. Use
  when the user says "review", "/pudo-review", "is this done", or before a
  commit, PR or handoff.

PUDO Review

1. Run `git diff` (and `git diff --staged`). Read every changed hunk and the callers of changed functions. 2. Run the project's tests and checks. Report the exact command and result. A failure is reported, never hidden. 3. Call `pudo.runQualityGate` with `develop`, then `optimize`, when the PUDO MCP server is connected. 4. Reply with:

Verdict:         ready / not ready (one line why)
Verified by:     commands run and their result
Findings:        numbered; each with file:line, the concrete failing case, the smallest fix
Scope creep:     changes the request did not ask for
Remaining risks: what is untested or assumed

No finding without a concrete case ("this input leads to this wrong result"). No style taste.

Ships withpudo-code-system

Modular, scalable, automated development intelligence.

Get the whole plugin

Other skills on pudo-code-system.