Run any Skill in Manus with one click

code-review

Stars2

Forks0

UpdatedJune 19, 2026 at 01:54

Use after implement-and-evaluate confirms acceptance criteria and gates are green, for a final pre-merge review against the constitution and the checklist template.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

CaioWF

CaioWF/keel

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software Quality Assurance Analysts and TestersComputer and Mathematical Occupations·SOC 15-1253

SKILL.md

readonly

name	code-review
description	Use after implement-and-evaluate confirms acceptance criteria and gates are green, for a final pre-merge review against the constitution and the checklist template.

code-review

This is one lens orchestrated by review-and-simplify (dispatched in parallel alongside security-review as part of the mandatory pre-commit step) — it is also usable standalone for an ad-hoc review.

When: implement-and-evaluate has finished — all tasks.md boxes checked, all Critérios de Aceitação passing, gates green — and the feature is otherwise ready to propose for commit.

Template: .specify/templates/checklist-template.md.

Output: the checklist filled out against the actual diff, reported inline (and optionally saved alongside the feature's specs if the user wants a persistent record) — plus a list of any findings that must be fixed before merge.

Steps:

Resolve the active feature from .specify/state (fallback: newest dir under specs/).
Read .specify/memory/constitution.md (principles, code patterns, SDD process) and hold the diff against it — flag any violation of a stated principle or code pattern.
Read .specify/templates/checklist-template.md and walk every item (Testes, Quality Gates, Documentação, Code Review, Deploy) against the actual state of the repo — do not assume an item is satisfied just because gates passed; verify (e.g. check for stray console.log/debug statements, confirm spec.md reflects the final implementation).
Report each checklist item as done/not-done with evidence, plus any constitution violations found.
Make no code edits — this skill reviews, it does not fix. If a finding is blocking, hand it back to implement-and-evaluate (or fix-runner directly for a small gate-level fix) rather than patching it here.
Only once the checklist is clean and no constitution violations remain should you propose the commit message(s) to the user and wait for approval — per the project's commit-at-milestone convention, do not commit yourself.

Next: human review and approval, then commit (proposed by you, executed only after explicit approval).

More from this repository

same repository

okf-enrich

CaioWF/keel

Ingest a raw source into the project's OKF knowledge bundle — distill it into concept pages, refresh the index, and log the change. keel's compounding "LLM wiki" loop.

2026-07-112

finishing-a-development-branch

CaioWF/keel

Use when implementation is complete, gates pass, and you need to decide how to integrate the work — presents structured options (merge, PR, keep, discard) and handles the chosen workflow, including worktree cleanup. Closes the SDD cycle after review-and-simplify.

2026-07-102

subagent-driven-development

CaioWF/keel

Use when executing implementation plans with independent tasks in the current session

2026-07-102

implement-and-evaluate

CaioWF/keel

Orchestrates the implement-feature, evaluator, fix-runner loop for the active feature until all Criterios de Aceitacao are met and quality gates are green.

2026-07-102

tasks-writer

CaioWF/keel

Use after the plan is approved to break the active feature's plan into a concrete task checklist, written into specs/<feature>/tasks.md from the tasks template.

2026-07-102

observability-and-instrumentation

CaioWF/keel

Use while implementing a feature that has retries, queues, background jobs, external calls, or any critical path an on-call engineer will need to reason about in production. Invoke when adding a new endpoint, dependency, or async flow, and before considering such a feature done — instrumentation is developed alongside the code, like tests, not bolted on after.

2026-07-082

code-review

When: implement-and-evaluate has finished — all tasks.md boxes checked, all Critérios de Aceitação passing, gates green — and the feature is otherwise ready to propose for commit.

Template: .specify/templates/checklist-template.md.

Steps:

Resolve the active feature from .specify/state (fallback: newest dir under specs/).

Read .specify/memory/constitution.md (principles, code patterns, SDD process) and hold the diff against it — flag any violation of a stated principle or code pattern.

Read .specify/templates/checklist-template.md and walk every item (Testes, Quality Gates, Documentação, Code Review, Deploy) against the actual state of the repo — do not assume an item is satisfied just because gates passed; verify (e.g. check for stray console.log/debug statements, confirm spec.md reflects the final implementation).

Report each checklist item as done/not-done with evidence, plus any constitution violations found.

Make no code edits — this skill reviews, it does not fix. If a finding is blocking, hand it back to implement-and-evaluate (or fix-runner directly for a small gate-level fix) rather than patching it here.

Only once the checklist is clean and no constitution violations remain should you propose the commit message(s) to the user and wait for approval — per the project's commit-at-milestone convention, do not commit yourself.

Next: human review and approval, then commit (proposed by you, executed only after explicit approval).