Inicio / Skills / Productividad del desarrollador / Requesting Code Review
Productividad del desarrollador

Requesting Code Review

Jesse VincentMITIdioma del Skill: Inglés
Licencia verificadaSin scriptsRiesgo bajo
DemostraciónEjecución real · claude-sonnet-5-5 · octubre de 2026
Using the requesting-code-review skill: I just finished Task 2 of my plan in a fictional repo, adding verifyIndex() and repairIndex() to the search indexer. Task 1 ended at commit a7981ec and my latest commit is 3df7661. Please request a code review. You do not have a subagent tool in this session.
Skill: requesting-code-review
Read: code-reviewer.md

I can't dispatch the reviewer from here. This session has no subagent tool, and the skill says the review belongs in a separate reviewer context. I haven't reviewed the diff myself. The working directory also isn't a git repo, so a7981ec..3df7661 can't be resolved here.

Here is the filled-in prompt from the skill's template. You can paste it into a general-purpose subagent, or into a fresh session opened in the real repo:

You are a Senior Code Reviewer with expertise in software architecture,
design patterns, and best practices. Your job is to review completed work
against its plan or requirements and identify issues before they cascade.

## What Was Implemented

Task 2: added verifyIndex() and repairIndex() to the search indexer.

## Requirements / Plan

Task 2 from the implementation plan. Replace this line with the plan file
path or the task text. verifyIndex() should detect index problems and
repairIndex() should fix them.

## Git Range to Review

**Base:** a7981ec  (end of Task 1)
**Head:** 3df7661

```bash
git diff --stat a7981ec..3df7661
git diff a7981ec..3df7661
```

## The spec is a vision document

The spec says what the software must do. It does not enumerate every
input, environment, or condition the software will meet. For behavior
the spec is silent on, judge by what a reasonable person using this
software would expect: a reasonable person's expectation is a
requirement, and a spec's silence is not permission. Grade such
findings by their effect on that person, not by whether the spec
mentions the trigger.

## Declined to judge

Before your verdict, list every behavior you considered and set aside
as outside the plan or spec, one line each, with the reason. The
executor rules on each line; nothing you set aside is dropped
silently. An empty list means you set nothing aside.

## Read-Only Review

Your review is read-only on this checkout. Do not mutate the working tree,
the index, HEAD, or branch state in any way. Use `git show`, `git diff`, and
`git log` to inspect history. If you need a working copy of a different
revision, use `git worktree add /tmp/review-<SHA> <SHA>`. Never move HEAD on
this checkout.

## You Do Not Dispatch Subagents

Do all of this review yourself. Never spawn a subagent to review part of
the diff, and never spawn another reviewer for a second opinion. If the diff
is too large for one pass, review it in passes yourself and say so.

## What to Check

**Plan alignment:** Does it match the plan? Are deviations justified? Is
all planned functionality present?
**Code quality:** Separation of concerns, error handling, type safety, DRY,
edge cases.
**Architecture:** Sound design, scalability and performance, security,
integration with surrounding code.
**Testing:** Tests verify real behavior rather than mocks, edge cases are
covered, integration tests where they matter, all tests pass.
**Production readiness:** Migration strategy, backward compatibility,
documentation, no obvious bugs.

## Calibration

Categorize issues by actual severity. Not everything is Critical.
Acknowledge what was done well before listing issues. Flag significant
deviations from the plan specifically, and say so if the plan itself is the
problem.

## Output Format

### Strengths
### Issues
#### Critical (Must Fix)
#### Important (Should Fix)
#### Minor (Nice to Have)
(For each issue: file:line, what's wrong, why it matters, how to fix.)
### Recommendations
### Assessment
**Ready to merge?** [Yes | No | With fixes]
**Reasoning:** [1-2 sentences]

Be specific, explain why each issue matters, don't give feedback on code
you didn't read, and give a clear verdict.

Before you send it, replace the Requirements line with the plan path or the Task 2 text. The reviewer needs that to check plan alignment.

When the findings come back, paste them here. I'll fix the Critical and Important items and note the Minor ones for later.

If you'd rather have a review now, I can read the diff myself in this session. That uses this session's context, which the skill advises against, and it needs the actual repo. Say so and point me to its path.

Real run in an isolated folder with only this skill installed. Only the Skill and Read tools were enabled, so no command was run and no file was written. The example is fictional. The model had no subagent tool and no repository, so it explained that it could not dispatch a review instead of reviewing the diff itself. It opened the skill's reviewer template.

Qué hace

Describe cuándo y cómo pedir una revisión de código: después de cada tarea en un flujo de trabajo con varias tareas, después de una funcionalidad importante y antes de fusionar, y, de forma opcional, cuando se está atascado o antes de una refactorización. El modelo recibe los SHA de los commits base y head y, después, lanza un subagente revisor de propósito general mediante una plantilla incluida. El revisor recibe una descripción breve de lo construido, los requisitos o el plan y el rango de Git para hacer diff, no el historial de la sesión, así que juzga el producto del trabajo y no el proceso de pensamiento. La plantilla trata la especificación como un documento de visión (el silencio no implica permiso), pide al revisor que enumere lo que decidió no evaluar y devuelve fortalezas, problemas clasificados como Critical, Important o Minor, y una evaluación. Después, la Skill indica corregir de inmediato los problemas Critical, corregir los Important antes de continuar, anotar los Minor y rebatir con evidencia cuando el revisor se equivoca.

Ideal para

Comprobar una funcionalidad o tarea antes de que se encadene con más trabajo, y antes de fusionar.

Notas y riesgos

Riesgo bajo: solo instrucciones que no escriben archivos ni hacen solicitudes de red; los únicos comandos son de Git de solo lectura (`git rev-parse`, `git diff`). Necesita una herramienta de subagente en tu agente; sin ella, el modelo indica que no puede lanzar la revisión en lugar de revisar su propio trabajo, como mostró la prueba. El revisor ve el diff de tu código, así que ten en cuenta dónde se ejecuta el modelo antes de enviar código propietario. Algunos enlaces remiten a Skills hermanas que no se incluyen. Probado una vez en un repositorio inventado.

SKILL.md original3 archivos en este paquete