Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

requesting-code-review

Étoiles48

Forks3

Mis à jour12 juillet 2026 à 19:55

Independently review a defined change before integration when requested or when material security, data, concurrency, migration, contract, or cross-module risk warrants it; exclude incoming feedback.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

eagleagentic

eagleagentic/superpowers-gpt-5.6

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Analystes en assurance qualité des logiciels et testeursProfessions informatiques et mathématiques·SOC 15-1253

SKILL.md

readonly

name	requesting-code-review
description	Independently review a defined change before integration when requested or when material security, data, concurrency, migration, contract, or cross-module risk warrants it; exclude incoming feedback.

Requesting Code Review

Do not use this workflow merely to evaluate incoming reviewer feedback.

Define the exact change range from a recorded base, merge base, staged diff, or named files. Never assume HEAD~1 covers the work.
Read the requirements and name the specific risks under review.
Inspect the actual diff, affected callers, tests, contracts, and existing evidence only as far as those risks require.
Validate every finding against code and requirements.

Keep the review read-only. Report actionable findings by severity with file and line evidence, impact, and a concrete fix. Omit strengths, generic recommendations, and findings that do not change the decision.

Block integration on supported Critical and Important findings. Re-review only when a substantial correction changes the risk surface; otherwise run the affected verification directly.

Plus depuis ce dépôt

même dépôt

executing-plans

eagleagentic/superpowers-gpt-5.6

Execute an existing plan when implementation is authorized and dependent outcomes need tracking; skip short routine checklists.

2026-07-1548

using-superpowers

eagleagentic/superpowers-gpt-5.6

Mandatory newcomer-safe router for every conversation. Classify by action, impact, and named risk; add workflows only when their descriptions match.

2026-07-1548

writing-plans

eagleagentic/superpowers-gpt-5.6

Create a durable plan when explicitly requested, required by the High-risk tier, or needed for resumable dependency coordination; skip routine native planning.

2026-07-1548

brainstorming

eagleagentic/superpowers-gpt-5.6

Resolve ambiguous product or system work before implementation. Use when materially different interpretations would change scope, architecture, or consequential outcomes; skip precise tasks.

2026-07-1248

finishing-a-development-branch

eagleagentic/superpowers-gpt-5.6

Complete an authorized commit, push, integration, PR, branch, or worktree action while preserving user state. Use after relevant verification when the user or repository requires delivery.

2026-07-1248

receiving-code-review

eagleagentic/superpowers-gpt-5.6

Evaluate incoming code-review feedback against repository evidence. Keep evaluation-only requests read-only; implement supported fixes only when authorized.

2026-07-1248

name	requesting-code-review
description	Independently review a defined change before integration when requested or when material security, data, concurrency, migration, contract, or cross-module risk warrants it; exclude incoming feedback.

Requesting Code Review

Do not use this workflow merely to evaluate incoming reviewer feedback.

Define the exact change range from a recorded base, merge base, staged diff, or named files. Never assume HEAD~1 covers the work.
Read the requirements and name the specific risks under review.
Inspect the actual diff, affected callers, tests, contracts, and existing evidence only as far as those risks require.
Validate every finding against code and requirements.

Block integration on supported Critical and Important findings. Re-review only when a substantial correction changes the risk surface; otherwise run the affected verification directly.