This is a comprehensive reference for working with Protocol Buffers and the buf toolchain. It enforces a strict workflow: match existing project style, write proto code with mandatory protovalidate constraints on every field, then verify with buf format and lint. The skill includes templates for common service patterns (CRUD with pagination, batch operations), language-specific buf.gen.yaml configs for Go, TypeScript, Python, and Java, and practical guidance on schema evolution and breaking changes. The insistence on validation for production APIs is opinionated but sensible. If you're building gRPC or Connect services and want to avoid the usual proto pitfalls around versioning and validation, the troubleshooting guide and review checklist alone make this worth having.

skills.sh installs
562
GitHub stars
20
last updated
Jun 3, 2026

Install

$ npx -y skills add bufbuild/claude-plugins --skill protobuf --agent claude-code

Installs into .claude/skills of the current project.

Files

Protocol Buffers

When You Need This Skill

  • Creating or editing .proto files
  • Setting up buf.yaml or buf.gen.yaml
  • Designing gRPC or Connect services
  • Adding protovalidate constraints
  • Troubleshooting buf lint or breaking change errors

Core Workflow

1. Match Project Style

Before writing proto code, review existing .proto files in the project. Match conventions for naming, field ordering, structural patterns, validation, and documentation style. If none exists, ask the user what style should be used or an existing library to emulate.

2. Write Proto Code

3. Verify Changes

Always run after making changes:

buf format -w && buf lint

Check for a Makefile first—many projects use make lint or make format.

Fix all errors before considering the change complete.

Quick Reference

Sponsors

Details

Repository
github.com/bufbuild/claude-plugins
First seen
Jun 3, 2026

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs