代理设置维护

人工智能 社区

技能解读

当前原文的自动摘译,尚未人工审校。

从这里开始

阅读../../README.md了解共享配置和垫片模型。阅读根../../AGENTS.md了解回购级别的期望。添加或编辑共享技能时,使用../skill-creator/SKILL.md,然后应用此技能中特定于存储库的检查。

工作流程

编辑.agents/下的规范文件,而不是生成的提供程序输出。保留 root AGENTS.md 和 CLAUDE.md 作为发现符号链接;不要将它们恢复为手动维护的副本。将特定于工具的目录(例如 .claude/、.cursor/、.codex/、.vscode/ 和 .mcp.json)视为生成的发现表面,除非该工具

Docker / 安装时间约束

pnpm install 在可能不包含完整存储库源树的环境中运行。在 Docker 构建中,Turbo 的修剪安装阶段可以在镜像中可用的 scripts/ 和 .agents/ 之前运行 root postinstall。在这些精简的上下文中保持安装时代理设置逻辑的稳健性:跳过

所需验证

更改共享代理设置后运行: pnpm run agents:sync pnpm run agents:check 相关时运行附加验证: pnpm run postinstall 当安装时行为发生变化时

设计规则

与重复的特定于提供商的文件相比,更喜欢一个存储库拥有的事实来源。尽可能保持共享设置工具中立。仅当提供程序需要无法通过共享设置模型表达的固定发现路径或功能时,才将特定于提供程序的文件保留在源代码管理中。

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
人工智能
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@langfuse · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
需简单配置
是否需要外部接口密钥
不需要
兼容的系统
Docker
运行环境要求
Docker
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
网络行为
仅限本地
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# Agent Setup Maintenance

Use this skill when changing the shared agent setup for the repository.

## Start Here

- Read [`../../README.md`](../../README.md) for the shared config and shim model.
- Read root [`../../AGENTS.md`](../../AGENTS.md) for repo-level expectations.
- When adding or editing shared skills, use
  [`../skill-creator/SKILL.md`](../skill-creator/SKILL.md), then apply the
  repo-specific checks in this skill.
- Inspect [`../../../scripts/agents/sync-agent-shims.mjs`](../../../scripts/agents/sync-agent-shims.mjs)
  before changing generated outputs or provider discovery behavior.
- Inspect [`../../../scripts/postinstall.sh`](../../../scripts/postinstall.sh)
  and [`../../../package.json`](../../../package.json) when changing install-time
  sync behavior.

## Workflow

1. Edit the canonical files under `.agents/`, not generated provider outputs.
2. Keep root `AGENTS.md` and `CLAUDE.md` as discovery symlinks; do not turn
   them back into manually maintained copies.
3. Treat tool-specific directories such as `.claude/`, `.cursor/`, `.codex/`,
   `.vscode/`, and `.mcp.json` as generated discovery surfaces unless the tool
   requires a truly tool-specific feature.
4. Keep root `AGENTS.md` concise and router-like. Move detailed or conditional
   workflows into shared skills or package `AGENTS.md` files.
5. Treat developer feedback as a learning loop: when a task reveals a durable
   repo convention, recurring pitfall, reusable workflow, or verification
   pattern, update the smallest relevant `AGENTS.md` or shared skill.
6. When adding or changing a shared skill, update `skills/README.md` and link
   it from root `AGENTS.md` if it changes the default reusable workflow.
7. When shared setup behavior changes materially, update `README.md` and
   contributor-facing docs in the same PR.

## Docker / Install-Time Constraint

- `pnpm install` runs in environments that may not contain the full repo source
  tree.
- In Docker builds, Turbo's pruned install stage can run root `postinstall`
  before `scripts/` and `.agents/` are available in the image.
- Keep install-time agent setup logic robust in those pruned contexts: skip
  cleanly when the required repo-owned files are not present.

## Required Verification

Run after changing shared agent setup:

- `pnpm run agents:sync`
- `pnpm run agents:check`

Run additional verification when relevant:

- `pnpm run postinstall` when install-time behavior changes
- targeted tests for any scripts you changed

## Design Rules

- Prefer one repo-owned source of truth over duplicated provider-specific files.
- Keep shared setup tool-neutral where possible.
- Only keep provider-specific files in source control when the provider requires
  a fixed discovery path or feature that cannot be expressed through the shared
  setup model.

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。