Bruno 工作流程中的代理技能
概览
一套用于使用 Bruno — 开源 API 客户端的代理技能集合。每个技能都是自包含的目录，AI 编码代理可以加载它以执行 Bruno 的专注任务：生成集合、编写测试或设置配置配置。 SKILL.md 是进入点。它的 YAML 前言（名称、描述）是代理决定何时加载技能的方式;主体是代理遵循的指令。 这些技能针对支持代理技能模式的代理（Claude Code、Anthropic API 技能特性及兼容运行时）。使用其中一个： 1. 将技能目录（例如 bruno-collection-generator/）复制到你的代理技能文件夹，或指向该仓库。2. 通过自然语言描述任务来触发技能——例如，“从此 OpenAPI 文件生成 Bruno 集合”或“为此 Bruno 请求写烟雾测试”。3. 代理加载 SKILL.md，遵循其指令，并可能调用 scripts/ 下的辅助脚本。 代理人/OpenAI。
概述（AI 翻译）
一套用于使用 Bruno — 开源 API 客户端的代理技能集合。每个技能都是自包含的目录，AI 编码代理可以加载它以执行 Bruno 的专注任务：生成集合、编写测试或设置配置配置。
技能
| 技能 | 目的 |
|---|---|
bruno-collection-generator |
生成 Bruno 集合、请求文件、环境和请求文档，来源于后端源代码、OpenAPI 片段、curl 命令或端点列表。 |
bruno-test-writer |
编写并改进 Bruno API 测试、断言、响应前后脚本、请求链和模式检查。 |
bruno-ci-setup |
创建能够通过 Bruno CLI 运行 Bruno 集合的 CI 工作流——GitHub Actions、GitLab CI、Jenkins、Azure Pipelines——并支持报告和秘密处理。 |
每个技能的布局相同：
SKILL.md 是进入点。其 YAML 前置内容（name， description）是智能体决定何时加载技能的方式;主体是智能体遵循的指令。
使用一项技能
这些技能针对支持代理技能模式的代理（Claude Code、Anthropic API 技能特性及兼容运行时）。使用其中一个：
- 复制技能目录（例如：
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
Bruno Agent Skills
A collection of agent skills for working with Bruno — the open-source API client. Each skill is a self-contained directory an AI coding agent can load to perform a focused Bruno task: generating collections, writing tests, or setting up CI.
Skills
| Skill | Purpose |
|---|---|
bruno-collection-generator |
Generate Bruno collections, request files, environments, and request docs from backend source, OpenAPI snippets, curl commands, or endpoint lists. |
bruno-test-writer |
Write and improve Bruno API tests, assertions, pre-/post-response scripts, request chaining, and schema checks. |
bruno-ci-setup |
Create CI workflows that run Bruno collections with the Bruno CLI — GitHub Actions, GitLab CI, Jenkins, Azure Pipelines — with reports and secret handling. |
Each skill follows the same layout:
/
├── SKILL.md # Skill front-matter + instructions the agent loads
├── agents/ # Agent-specific manifests (e.g. openai.yaml)
├── references/ # Quick-reference docs the skill cites
├── scripts/ # Helper scripts + tests
└── assets/ # Example inputs (where applicable)
SKILL.md is the entry point. Its YAML front-matter (name, description) is how an agent decides when to load the skill; the body is the instructions the agent follows.
Using a skill
These skills target agents that support the Agent Skills pattern (Claude Code, the Anthropic API skills feature, and compatible runtimes). To use one:
- Copy the skill directory (e.g.
bruno-collection-generator/) into your agent’s skills folder, or point your agent at this repo. - Trigger the skill by describing the task in natural language — for example, “generate a Bruno collection from this OpenAPI file” or “write smoke tests for this Bruno request.”
- The agent loads
SKILL.md, follows its instructions, and may call into the helper scripts underscripts/.
The agents/openai.yaml file in each skill provides an OpenAI-compatible manifest for runtimes that prefer that format.
Running the tests
The helper scripts under each skill have pytest tests. To run them locally:
python -m pip install --upgrade pip pytest pyyaml
python -m pytest -v
CI runs the same tests against Python 3.9 and 3.12 — see .github/workflows/tests.yml.
Repository layout
bruno-agent-skills/
├── bruno-ci-setup/
├── bruno-collection-generator/
├── bruno-test-writer/
└── .github/workflows/tests.yml
Contributing
Issues and pull requests are welcome. When adding or changing a skill:
- Keep
SKILL.mdfocused — the front-matterdescriptiondrives skill selection, so it should clearly describe when to use the skill.
推荐工具
换一个关键词，或者移除筛选条件。
安装
npx skillfish add bruno-collections/bruno-agent-skills