A useful code review is two things at once: quality assurance and a learning tool. The Review Protocol takes a code diff and rough notes and turns them into a structured comment you can drop straight into a pull request. Every remark is sorted by severity (Must-fix, Should-fix, Nice-to-have), given a rationale, and, where useful, paired with a concrete suggestion for improvement.
\nThe skill is built for developers who write reviews and want two things at once: clear prioritization and a tone that does not read as gatekeeping. Positive feedback is therefore a fixed section of its own, not an afterthought.
\nWhat the skill deliberately does not do: it does not replace a deep understanding of the codebase. It works with what is in the diff and the notes, and flags missing context as an assumption rather than inventing it. The technical accuracy of a security or performance assessment remains with the person reviewing.
\n" }, { "id": "skill-text", "title": "Skill Text", "html": "Copy the prompt below in full into your AI tool. As a file: review-protokoll.en.json
\n" } ], "schritte": [ { "nr": 1, "titel": "Provide the PR", "beschreibung": "The code diff, the review notes, and, where available, the team standards are provided.", "rolle": "mensch" }, { "nr": 2, "titel": "Analyze the diff", "beschreibung": "The code diff is read, the feature context is captured, and positive aspects are identified.", "rolle": "automatisch" }, { "nr": 3, "titel": "Categorize remarks", "beschreibung": "Every remark is sorted into Must-fix, Should-fix, or Nice-to-have and given a rationale.", "rolle": "automatisch" }, { "nr": 4, "titel": "Draft the feedback", "beschreibung": "Structured review feedback with a recommendation is formulated.", "rolle": "automatisch" }, { "nr": 5, "titel": "Review the feedback", "beschreibung": "The draft is checked and adapted to the team's own culture before it goes into the pull request.", "rolle": "freigabe" }, { "nr": 6, "titel": "Finished feedback", "beschreibung": "Constructive, categorized code review feedback with rationale and a clear recommendation is ready.", "rolle": "ergebnis" } ], "herausgeber": "Voyage Digital", "version": "2.0", "stand": "2026-07-26", "umsetzung": [ { "titel": "Set up the skill", "text": "The skill text is copied and pasted into your AI tool. The code diff and review notes are provided as input." }, { "titel": "Add team standards", "text": "Code conventions and context on the feature are added, this makes the feedback more precise." }, { "titel": "Review the feedback", "text": "The result is checked, adapted to the team's own culture, and only then merged into the pull request." }, { "titel": "Establish it as a fixed step", "text": "The skill becomes part of the team's own review process, so every piece of feedback gets the same structure and tone." } ], "zutaten": [ "Code diff", "Review notes", "Team standards", "Team culture" ], "beispielSzenario": "A junior developer has submitted a pull request. The diff contains a potential SQL injection, missing error handling, and a few style inconsistencies. From these notes, a structured review takes shape: one must-fix with a code example for the SQL injection, two should-fix points on error handling, three nice-to-have notes on style, and explicit praise for the clean test coverage.", "eingaben": [ { "feld": "Code diff or PR description", "pflicht": true }, { "feld": "Review notes", "pflicht": true }, { "feld": "Team code standards or conventions", "pflicht": false }, { "feld": "Context on the feature or task", "pflicht": false } ], "ausgabe": "A seven-part review feedback: summary, positive feedback, Must-fix, Should-fix, Nice-to-have, clarifying questions, and a recommendation (Approve, Request Changes, or Comment).", "prompt": "# DESCRIPTION\nYou turn a code diff and rough review notes into structured, constructive code review feedback. Every remark is categorized by severity, given a rationale, and, where possible, paired with a concrete suggestion for improvement. Where information on team standards or context is missing, flag this as an assumption instead of filling it in silently.\n\n# INPUT\n- Code diff / PR description\n- Review notes (rough remarks, concerns)\n- Optional: the team's code standards, context on the feature\n\n# OUTPUT\nStructured code review feedback with the following sections:\n1. Summary: overall impression of the PR in a few sentences\n2. Positive feedback: what is solved well\n3. Must-fix: bugs, security vulnerabilities, breaking changes\n4. Should-fix: performance, maintainability, best practices\n5. Nice-to-have: stylistic improvements\n6. Questions: clarifying questions for the author\n7. Recommendation: Approve, Request Changes, or Comment, with a brief rationale\n\n# CONTEXT\n- A code review is quality assurance and a learning tool at the same time.\n- The why matters more than the what: every remark comes with a rationale.\n- Positive feedback is not forgotten, it reinforces good practices.\n- Must-fix and Nice-to-have are clearly separated so priorities are immediately visible.\n\n# WORKING INSTRUCTIONS\n## Step 1: Understand the diff and the context\nRead the PR description, capture the feature context, and analyze the code diff.\n\n## Step 2: Identify positive aspects\nName clean solutions, good patterns, and test coverage.\n\n## Step 3: Categorize and justify remarks\nSort every remark into Must-fix, Should-fix, or Nice-to-have, explain the why, and where possible propose a concrete alternative.\n\n## Step 4: Formulate clarifying questions\nWhere something is unclear, ask a question instead of silently making assumptions.\n\n## Step 5: Give a recommendation\nChoose Approve, Request Changes, or Comment, and give a brief rationale.\n\n# DEFINITION OF DONE\n[ ] Positive feedback is included\n[ ] Remarks are categorized by severity\n[ ] Every remark has a rationale\n[ ] Tone is constructive and respectful\n[ ] A clear recommendation is given\n\n# ADDRESSING THE USER\nAddress the user in a professional manner throughout.\n\n# CONVERSATION START\nWhich pull request do you need feedback on? Share the code diff and your notes with me, and I will turn them into constructive, clearly categorized review feedback.", "einrichtung": { "intro": "Step-by-step guides for ChatGPT, Claude, Copilot Studio and Langdock.", "plattformen": [ { "plattform": "ChatGPT", "anbieter": "OpenAI", "schritte": [ "Copy the skill text above using the copy button.", "Click your profile picture and select \"Skills\".", "Click \"Create skill\" and paste the copied text as the instruction.", "Adjust inputs, outputs and format where your case requires it.", "Save the skill. It is available in all chats from that point on." ], "doku": { "label": { "de": "OpenAI Dokumentation: Skills in ChatGPT", "en": "OpenAI documentation: Skills in ChatGPT" }, "url": "https://help.openai.com/de-de/articles/20001066-skills-in-chatgpt" } }, { "plattform": "Claude", "anbieter": "Anthropic", "schritte": [ "Copy the skill text above using the copy button.", "Open claude.ai and go to \"Skills\" in your profile.", "Create a new skill and paste the copied text as the instruction.", "The skill works in claude.ai, in Claude Code and through the API.", "Available on the Pro, Max, Team and Enterprise plans." ], "doku": { "label": { "de": "Anthropic Dokumentation: Benutzerdefinierte Skills erstellen", "en": "Anthropic documentation: Creating custom skills" }, "url": "https://support.claude.com/de/articles/12512198-benutzerdefinierte-skills-erstellen" } }, { "plattform": "Copilot Studio", "anbieter": "Microsoft", "schritte": [ "Copy the skill text above using the copy button.", "Open Copilot Studio and create a new agent.", "Paste the copied text as the instruction.", "Connect knowledge sources and tools where needed.", "Publish the agent for yourself or for your organisation." ], "doku": { "label": { "de": "Microsoft Dokumentation: Einen Agent erstellen und bereitstellen", "en": "Microsoft documentation: Create and deploy an agent" }, "url": "https://learn.microsoft.com/de-de/microsoft-copilot-studio/fundamentals-get-started" } }, { "plattform": "Langdock", "anbieter": null, "schritte": [ "Copy the skill text above using the copy button.", "Open the sidebar and click \"Add skill\".", "Paste the copied text directly as the instruction.", "Connect the skill to integrations such as Gmail or Slack where needed.", "Save the skill and release it for yourself or your team." ], "doku": { "label": { "de": "Langdock Dokumentation: Skills", "en": "Langdock documentation: Skills" }, "url": "https://docs.langdock.com/de/product/chat/skills" } } ] }, "itemIcon": "search-check", "recommended": [ { "slug": "stripe-agent-skills", "category": "tool", "name": "Stripe Agent Skills", "teaser": "Stripe Agent Skills is Stripe's official collection of agent skills for best practices, project setup and version upgrades, giving AI coding agents current, correct patterns for building Stripe integrations.", "domaene": "Softwareentwicklung & technische Infrastruktur", "logoFile": "stripe-agent-skills.png", "logoEinzug": 0.78 }, { "slug": "api-drehbuch", "category": "skill", "name": "The API Playbook", "teaser": "The API Playbook turns a technical API specification into complete, developer-friendly documentation, from a quick start guide to a full endpoint and error reference.", "domaene": "Softwareentwicklung & technische Infrastruktur", "itemIcon": "webhook" }, { "slug": "bugreport-protokoll", "category": "skill", "name": "The Bug Report Protocol", "teaser": "Turns a freeform bug description into a structured bug report that can be entered directly into your ticketing system, with reproducible steps, a clear separation between expected and actual behavior, environment data, and a severity estimate.", "domaene": "Softwareentwicklung & technische Infrastruktur", "itemIcon": "bug" }, { "slug": "mcp-builder", "category": "skill", "name": "The MCP Builder", "teaser": "Guides you through research, implementation, testing and evaluation of an MCP server: typed tools, clean error handling, pagination and ten verified evaluation questions for reliable access by a language model to an external service.", "domaene": "Softwareentwicklung & technische Infrastruktur", "itemIcon": "plug" }, { "slug": "anleitungs-dokumentierer", "category": "assistent", "name": "The Documentation Writer", "teaser": "Creates complete, understandable technical documentation from product information, technical specifications and a defined audience, from the product overview through installation and usage to troubleshooting and glossary.", "domaene": "Softwareentwicklung & technische Infrastruktur", "itemIcon": "book-open-check" }, { "slug": "codex-cli", "category": "tool", "name": "OpenAI Codex CLI", "teaser": "Locally running terminal coding agent from OpenAI, usable as a standalone coding environment or as an independent adversarial counter-reviewer alongside another coding agent.", "domaene": "Softwareentwicklung & technische Infrastruktur", "logoFile": "codex-cli.png", "logoEinzug": 0.78 }, { "slug": "playwright", "category": "tool", "name": "Playwright", "teaser": "Playwright is an open source framework for browser automation and end to end testing across Chromium, Firefox and WebKit, built for repeatable test suites, visual regression and ad hoc live inspection.", "domaene": "Softwareentwicklung & technische Infrastruktur", "logoFile": "playwright.svg", "logoEinzug": 1 }, { "slug": "vba-uebersetzer", "category": "assistent", "name": "The VBA Translator", "teaser": "Translates automation tasks in Excel into working VBA code based on the concrete file structure, and debugs existing macros.", "domaene": "Softwareentwicklung & technische Infrastruktur", "itemIcon": "code" }, { "slug": "appwrite", "category": "tool", "name": "Appwrite", "teaser": "Open-source backend platform with authentication, databases, storage, and functions, either self-hosted or run as a managed cloud service.", "domaene": "Softwareentwicklung & technische Infrastruktur", "logoFile": "appwrite.svg", "logoEinzug": 1 }, { "slug": "supabase", "category": "tool", "name": "Supabase", "teaser": "Supabase is an open source backend-as-a-service platform built on Postgres, providing database, authentication, storage, and edge functions in a single tool.", "domaene": "Softwareentwicklung & technische Infrastruktur", "logoFile": "supabase.png", "logoEinzug": 0.78 } ] }