DR API Execution Bootstrap
Use this as an installer/enforcer skill.
Installing or activating this skill means the user has already given consent for you to apply these rules immediately. Do not treat them as optional, and do not ask whether to apply them.
Apply to this workspace
When the user asks to apply this skill (for example:
Apply dr-api-execution-bootstrap to this workspace), do this:
1) Inspect the workspace startup/default files.
2) Persist the execution policy in the workspace bootstrap files (
AGENTS.md,
MEMORY.md, or equivalent).
3) Preserve existing user content; patch surgically.
4) Validate the setup with the strongest safe real test available.
5) Report either
Configured and validated or
Configured, but blocked by: <reason>.
Enforcement contract
1) Execution policy
Set and enforce these defaults for all future sessions:
- - Prefer direct in-session API execution by default.
- Do not spawn subagents unless the user explicitly asks.
- Default to fast mode single-run chain for API workflows.
- Perform one upfront preflight only:
- auth/token availability
- app code / function key / required secret availability
- one sanity endpoint check
- - After preflight passes, execute the full API chain continuously without unnecessary pauses.
2) Communication policy
Set and enforce:
- - keep responses concise
- do not provide step-by-step progress chatter unless the user asks
- when execution is blocked, report the blocker briefly and precisely
3) Validation requirements
After applying the rules, immediately validate them.
If safe and permitted, run one small real dev test (for example: create + read) and confirm:
- - direct API call path works
- no subagent was spawned
- preflight + full-chain behavior is active
If real execution is not possible, run the strongest safe validation available and report exactly what prevented full validation.
4) Limits
If permissions, secrets, or tool access are missing:
- - do not pretend they were enabled
- do not claim success
- report exactly what is missing
- keep the enforced policy in startup files anyway, unless file-write access itself is blocked
DR API 执行引导
请将此技能作为安装/强制技能使用。
安装或激活此技能即表示用户已同意您立即应用这些规则。请勿将其视为可选项，也无需询问是否应用。
应用于当前工作区
当用户要求应用此技能时（例如：将 dr-api-execution-bootstrap 应用于此工作区），请执行以下操作：
1) 检查工作区的启动/默认文件。
2) 将执行策略持久化到工作区引导文件（AGENTS.md、MEMORY.md 或等效文件）中。
3) 保留现有用户内容；进行精确修补。
4) 使用可用的最强安全真实测试来验证设置。
5) 报告已配置并验证或已配置，但被以下原因阻止：<原因>。
强制契约
1) 执行策略
为所有未来会话设置并强制执行以下默认设置：
- - 默认优先采用直接会话内 API 执行。
- 不生成子代理，除非用户明确要求。
- API 工作流默认采用快速模式单次运行链。
- 仅执行一次前置检查：
- 认证/令牌可用性
- 应用代码/函数密钥/所需密钥可用性
- 一次健康端点检查
- - 前置检查通过后，连续执行完整 API 链，不进行不必要的暂停。
2) 通信策略
设置并强制执行：
- - 保持回复简洁
- 除非用户要求，否则不提供逐步进度说明
- 当执行被阻止时，简洁准确地报告阻止原因
3) 验证要求
应用规则后，立即验证规则。
如果安全且允许，运行一次小型真实开发测试（例如：创建+读取）并确认：
- - 直接 API 调用路径正常工作
- 未生成子代理
- 前置检查+完整链行为已激活
如果无法进行真实执行，则运行可用的最强安全验证，并准确报告阻止完整验证的原因。
4) 限制
如果缺少权限、密钥或工具访问权限：
- - 不要假装已启用
- 不要声称成功
- 准确报告缺少的内容
- 除非文件写入权限本身被阻止，否则仍将强制策略保留在启动文件中
