New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Use Buf

by moeru-ai in moeru-ai/auv

Configure, inspect, update, validate, and troubleshoot Buf workspaces and modules.

Apache-2.0Auto-check passedDevelopment

Install Use Buf

skills CLI
$ npx skills add moeru-ai/auv --skill use-buf -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install moeru-ai/auv use-buf --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/moeru-ai/auv.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/use-buf .claude/skills/use-buf && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
use-buf
GitHub stars
100
Token cost
~1k tokens
SKILL.md length
471 words
Files
4 (incl. references)
Repo updated
First seen
Licence
Apache-2.0

At a glance

Configure, inspect, update, validate, and troubleshoot Buf workspaces and modules.

  • Works in 5 steps: Read repository instructions. → Search the repository root and likely… → Inspect the configuration version,… → …
  • Working with buf.yaml
  • SKILL.md covers Inspect Before Changing, Keep Configuration…, Manage Dependencies Deliberately and Required Validation, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Use Buf is an agent skill from moeru-ai/auv. Configure, inspect, update, validate, and troubleshoot Buf workspaces and modules. Use when working with buf.yaml, buf.lock, buf.gen.yaml or domain-specific Buf generation templates; managing BSR dependencies; formatting, linting, generating, detecting breaking Protobuf changes; locating dependency schemas; or diagnosing missing types and generation failures.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/commands-and-troubleshooting.md` and `references/configuration.md`).

It sits in Development, covering Linting and formatting and gRPC and Protobuf. It works with gRPC. The repository describes itself as: 📱🐭 No we are not computer use, it's Application Use Via... a unified orchestration layer of OS automation, 0 token cost. The licence is Apache-2.0.

When your agent uses it

  • Working with buf.yaml
  • Domain-specific Buf generation templates
  • Managing BSR dependencies
  • Detecting breaking Protobuf changes

Example prompts

  • “/use-buf”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read repository instructions.
  2. Search the repository root and likely API directories for buf.yaml, buf.lock, buf.gen.yaml, and buf.gen..yaml files.
  3. Inspect the configuration version, module paths, dependency declarations, lint policy, breaking policy, inputs, plugin pins, output paths…
  4. Run buf --version and check repository/CI tool pins before using features from a newer configuration schema.
  5. Diagnose configuration or dependency problems before changing .proto files to work around them.

What it can do on your machine

Read from SKILL.md and the folder at commit 4042350. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Use Buf loads about 1k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 92 tokens; SKILL.md has 471 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from moeru-ai/auv at commit 4042350, republished under its Apache-2.0 licence (© moeru-ai). 471 words, ~1,034 tokens.

Download SKILL.mdSave it as .claude/skills/use-buf/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
use-buf
description
Configure, inspect, update, validate, and troubleshoot Buf workspaces and modules. Use when working with buf.yaml, buf.lock, buf.gen.yaml or domain-specific Buf generation templates; managing BSR dependencies; formatting, linting, generating, detecting breaking Protobuf changes; locating dependency schemas; or diagnosing missing types and generation failures.

Use Buf

Use the Buf CLI as the source of truth for Protobuf compilation, dependency resolution, linting, breaking-change detection, and code generation.

Inspect Before Changing

  1. Read repository instructions.
  2. Search the repository root and likely API directories for buf.yaml, buf.lock, buf.gen.yaml, and buf.gen.<domain>.yaml files.
  3. Inspect the configuration version, module paths, dependency declarations, lint policy, breaking policy, inputs, plugin pins, output paths, and existing generation scripts.
  4. Run buf --version and check repository/CI tool pins before using features from a newer configuration schema.
  5. Diagnose configuration or dependency problems before changing .proto files to work around them.

Use one default buf.gen.yaml. Introduce buf.gen.<domain>.yaml only when generation products genuinely require isolated plugin sets, inputs, or outputs. Pass non-default templates explicitly with buf generate --template <file>.

Keep Configuration Responsibilities Clear

  • Use buf.yaml for workspaces/modules, BSR dependencies, lint rules, breaking rules, policies, and Buf check plugins.
  • Use buf.gen.yaml or buf.gen.<domain>.yaml for protoc-gen-* code-generation plugins, inputs, output directories, options, and managed mode.
  • Use buf.lock as generated dependency resolution state. Do not edit it manually.
  • Keep configuration in the repository root or the established API workspace directory unless repository structure requires otherwise.

Read references/configuration.md before adding modules, dependencies, check plugins, generation templates, or output paths.

Manage Dependencies Deliberately

  • Prefer BSR modules for maintained dependencies, including Google APIs, well-known types, Protovalidate, and grpc-gateway annotations.
  • Add or remove dependencies in buf.yaml, then run buf dep update and inspect the buf.lock diff.
  • Use buf dep graph --format json to identify the resolved dependency chain.
  • Use buf dep prune only after confirming an import is genuinely unused.
  • When a type appears missing, inspect configuration and the lockfile, run buf dep update, then run buf build or buf generate to obtain the compiler's concrete import/type error.
  • Never hardcode an operating system's Buf cache location. Export the pinned module with buf export when source inspection is required.
Show full SKILL.md (164 more words)Show less

Required Validation

After changing first-party Protobuf or Buf configuration, MUST run:

sh
buf lint
buf generate
buf breaking --against '.git#branch=main'

Also run buf format --diff or the repository's format check and all language-specific tests/type checks for generated outputs.

Do not skip the breaking check merely because a break is intentional. Run it, capture the violations, and report that the change is an approved experimental/unreleased break. If the repository does not have a main branch, report that exact baseline failure and resolve the intended integration baseline rather than silently omitting compatibility validation.

Diagnose in Dependency Order

  1. Confirm the current directory and discovered buf.yaml.
  2. Confirm module paths and import paths.
  3. Confirm dependencies and buf.lock with buf dep graph.
  4. Compile with buf build.
  5. Lint with buf lint.
  6. Generate with the selected template.
  7. Inspect plugin stderr, output collisions, and generated diffs.
  8. Run the breaking check against main.

Use $use-buf-plugins for remote/local plugin selection, offline generation, rate limits, or plugin wrappers. Read references/commands-and-troubleshooting.md for precise inspection commands and failure handling.

© moeru-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in .agents/skills/use-buf of moeru-ai/auv.

  • SKILL.md
  • agents/openai.yaml
  • references/commands-and-troubleshooting.md
  • references/configuration.md

Open the folder on GitHubat commit 4042350

Compare with similar skills

Use Buf next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Use Buf compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Use Buf this skillmoeru-ai/auv100—~1kAutomated safety check: PassApache-2.0
Golang Proantoniopaya22/go-rest-template1723 repos~1.2kAutomated safety check: PassMIT
Intrinsic Core Debuggingintrinsic-ai/intrinsic-core562—~3.8kAutomated safety check: NotesApache-2.0
Dev Rulesrust-dd/tako162—~810Automated safety check: PassMIT
Using Dotnetnovotnyllc/dotnet-artisan232—~2.3kAutomated safety check: WarnMIT
Profile Trainingmarin-community/marin3.9k—~2.5kAutomated safety check: PassApache-2.0

Similar skills

  • Golang Pro

    antoniopaya22/go-rest-template

    Implements concurrent Go patterns using goroutines and channels, designs and builds microservices with gRPC or REST, optimizes Go application performance with pprof, and enforces idiomatic Go with…

    172 GitHub starsUsed in 3 repos~1.2k tokens
    Backend & APIsAuto-check passed

  • Intrinsic Core Debugging

    intrinsic-ai/intrinsic-core

    Meta-level debugging workflows, architectural layer isolation, and progressive disclosure routing across Envoy ingress, Kubernetes pods, Behavior Trees, ObjectWorld synchronization, ICON real-time…

    562 GitHub stars~3.8k tokensUpdated today
    DevOps & CloudAuto-check: notes

  • Dev Rules

    rust-dd/tako

    General coding-style rules to apply to every project. An agent skill from rust-dd/tako.

    162 GitHub stars~810 tokensUpdated 10 days ago
    Backend & APIsAuto-check passed

  • Using Dotnet

    novotnyllc/dotnet-artisan

    Detects .NET intent for any C, ASP.NET Core, EF Core, Blazor, MAUI, Uno Platform, WPF, WinUI, SignalR, gRPC, xUnit, NuGet, or MSBuild request from prompt keywords and repository signals (.sln…

    232 GitHub stars~2.3k tokensUpdated 3 days ago
    Backend & APIsAuto-check: warnings

  • Profile Training

    marin-community/marin

    Profile a named JAX, Levanter, or Marin run, or investigate a measured startup, compilation, initialization, or throughput bottleneck.

    3.9k GitHub stars~2.5k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Doca Rdma

    NVIDIA/skills

    Official

    A skill your agent uses when the user is doing hands-on DOCA RDMA programming on a BlueField DPU, ConnectX NIC, or DOCA host — bringing up an RDMA context on a docadev, picking a connection method…

    3.6k GitHub stars~3.5k tokensUpdated 2 days ago
    Backend & APIsAuto-check passed

More from moeru-ai/auv

All 8 skills in this repo

  • Auv Wayland Rendering

    moeru-ai/auv

    Prepare, diagnose, and validate Linux GPU and Wayland environments for AUV rendering and capture through XDG Desktop Portal and PipeWire.

    100 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Domain CLI

    moeru-ai/auv

    A skill your agent uses when building CLI tools. An agent skill from moeru-ai/auv.

    100 GitHub starsUsed in 1 repo~988 tokens
    Auto-check passed

  • Use Protobuf

    moeru-ai/auv

    Design, change, and review Protobuf schemas used as gRPC contracts, streaming protocols, typed data models, grpc-gateway REST APIs, OpenAPI specifications, or generated SDK inputs.

    100 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Domain Cloud Native

    moeru-ai/auv

    A skill your agent uses when building cloud-native apps. An agent skill from moeru-ai/auv.

    100 GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed

  • Domain ML

    moeru-ai/auv

    A skill your agent uses when building ML/AI apps in Rust. An agent skill from moeru-ai/auv.

    100 GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed

  • Use Pixi

    moeru-ai/auv

    A skill your agent uses when explaining, creating, or changing a Pixi workspace, including manifests, dependencies, platforms, targets, features, environments, tasks, lockfiles, editable Python…

    100 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Use Buf

What does Use Buf do?

Configure, inspect, update, validate, and troubleshoot Buf workspaces and modules. Use Buf is an agent skill from moeru-ai/auv. Configure, inspect, update, validate, and troubleshoot Buf workspaces and modules.

When should I use Use Buf?

Use Buf fits situations like: working with buf.yaml; domain-specific Buf generation templates; managing BSR dependencies; detecting breaking Protobuf changes.

How do I install Use Buf in Claude Code?

Run `npx skills add moeru-ai/auv --skill use-buf -a claude-code`. Or copy the skill folder (.agents/skills/use-buf in moeru-ai/auv) into .claude/skills/use-buf in your project. Claude Code loads it when a task matches its description.

How do I install Use Buf in Codex?

Run `npx skills add moeru-ai/auv --skill use-buf -a codex`. Or copy the skill folder (.agents/skills/use-buf in moeru-ai/auv) into .agents/skills/use-buf in your project. Codex loads it when a task matches its description.

Can I use Use Buf in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add moeru-ai/auv --skill use-buf -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/use-buf, .gemini/skills/use-buf, .github/skills/use-buf and .opencode/skills/use-buf in your project.

What does Use Buf need to run?

SKILL.md names no scripts, command-line tools or credentials: Use Buf is instructions for the agent only.

Does Use Buf access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Use Buf safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Use Buf use?

Use Buf is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Use Buf use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.3k tokens, read only when the agent opens those files.

What are the alternatives to Use Buf?

Skills that share tags, products or a category with Use Buf: Golang Pro (antoniopaya22/go-rest-template, 172 stars), Intrinsic Core Debugging (intrinsic-ai/intrinsic-core, 562 stars), Dev Rules (rust-dd/tako, 162 stars) and Using Dotnet (novotnyllc/dotnet-artisan, 232 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Use Buf?

moeru-ai (a GitHub organization) maintains it in moeru-ai/auv, which has 100 GitHub stars. The repository was last updated on October 11, 2026.

Source: moeru-ai/auv on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.