Back to Details

scout

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

scout — Real-System Best Practices & Production Archetype Engine

scout — 真实系统最佳实践与生产架构范式引擎

Domain Rubric

领域评估准则

1. Source Authority Hierarchy

1. 来源权威性层级

Triangulate technical inquiries against authoritative production evidence:
  • Tier 1 (Canonical Standards & Official Specs): RFCs, language specifications, cloud vendor reference architectures, and formal technical papers.
  • Tier 2 (High-Scale Production Engineering): Tech blogs and architecture disclosures from proven high-scale engineering organizations (e.g., Stripe, Netflix, Cloudflare, Discord, Uber, Meta).
  • Tier 3 (Battle Scars & Postmortems): Documented production outages, postmortems, and root-cause analyses revealing edge cases, operational bottlenecks, and failure modes.
  • Exclusion Filter: Exclude SEO-optimized content farms, unverified personal blog posts, vendor marketing collateral, and unvetted AI summaries.
针对技术查询，利用权威的生产证据进行三角验证：
  • 第 1 层（权威标准与官方规范）：RFC、语言规范、云厂商参考架构和正式技术论文。
  • 第 2 层（高规模生产实践）：来自成熟高规模工程组织的技术博客和架构披露，例如 Stripe、Netflix、Cloudflare、Discord、Uber、Meta。
  • 第 3 层（实战教训与事后复盘）：记录在案的生产故障、事后复盘和根因分析，用于揭示边缘情况、运营瓶颈和故障模式。
  • 排除条件：排除为 SEO 优化而生产的内容农场、未经验证的个人博客、厂商营销材料以及未经核实的 AI 摘要。

2. Search & Inclusion Budget

2. 搜索与纳入预算

  • Exploration Ceiling: Maximum 8 search queries and 10 fetched pages per scouting run.
  • Inclusion Budget: Synthesize from 3 to 5 premier, high-signal sources.
  • Short-Circuit Stop: Terminate search as soon as the canonical pattern and known failure modes are triangulated with primary evidence.
  • 探索上限：每次调研最多执行 8 个搜索查询并抓取 10 个页面。
  • 纳入预算：综合 3 至 5 个一流、高信噪比的来源。
  • 短路终止：一旦使用一手证据完成标准模式与已知故障模式的三角验证，立即终止搜索。

Canonical Output Contract

标准输出契约

markdown
undefined
markdown
undefined

Scout Report: <Topic / Inquiry>

Scout 报告：<主题 / 调研问题>

1. Executive Summary

1. 执行摘要

  • Canonical Production Archetype: <Boring, battle-tested standard approach adopted by industry leaders>
  • Operational Reality: <Key complexity, maintenance overhead, or scaling bottleneck in practice>
  • 标准生产架构范式：<行业领先者采用的稳健、久经考验的标准方案>
  • 实际运行情况：<实践中的关键复杂性、维护开销或扩展瓶颈>

2. Industry Precedents & Battle Scars

2. 行业先例与实战教训

Source / OrganizationPattern DeployedProduction Scale / ContextKnown Failure Mode / Trade-off
<Org / Paper><Architecture / Tool><Traffic, Data Volume, SLA><Failure point, latency spike, cost trap>
来源 / 组织已部署的模式生产规模 / 上下文已知故障模式 / 权衡取舍
<组织 / 论文><架构 / 工具><流量、数据量、SLA><故障点、延迟峰值、成本陷阱>

3. Recommended Baseline vs. Traps

3. 推荐基线与应避免的陷阱

  • Recommended Baseline: <Simplest robust architecture meeting requirements without premature optimization>
  • Premature Traps to Avoid: <Over-engineered patterns or hype-driven tools that introduce unnecessary failure modes>
  • 推荐基线：<满足需求且无需过早优化的最简单稳健架构>
  • 应避免的过早工程陷阱：<引入不必要故障模式的过度工程模式或受炒作驱动的工具>

4. Primary Citations

4. 一手引用

  • <Source Title> — <Core insight or concrete data point extracted>
undefined
  • <来源标题> — <提取的核心洞察或具体数据点>
undefined

Routing

路由

  • Deliberate trade-offs or evaluate architectural fit for the project → (via /clarify).
  • Baseline is accepted, adequately supported, and the caller requests change planning → (via /changeset).
  • 需要进行权衡取舍或评估架构与项目的适配性 →（通过 /clarify）。
  • 基线方案已获接受、证据充分，且调用方要求制定变更计划 →（通过 /changeset）。

Execution Protocol

执行协议

  1. Query Triangulation & Dispatch:
    • Formulate 2 to 3 targeted search queries crossing: canonical standards/RFCs, high-scale engineering cases, and failure postmortems.
    • Launch 
      research
      subagent(s) dynamically scaled to inquiry complexity or caller-declared budget (Role: 
      Real-System Research Scout
      ) supplying:
      • The triangulated queries and Search Budget (max 8 queries, 10 fetched pages).
      • The Canonical Output Contract above as the required output contract (offload deep comparative dossiers to 
        .agents/scratch/scout-dossier.md
        when extensive).
    • Mandate the subagent to inspect full page bodies via URL tools before synthesizing; cite strictly verified URLs and never synthesize from search snippets alone.
  2. Synthesis & Halt:
    • Emit the completed report into the conversation stream (with pointers to any offloaded dossiers) and halt turn immediately.
  1. 查询三角验证与分派：
    • 制定 2 至 3 个有针对性的搜索查询，交叉覆盖：权威标准/RFC、高规模工程案例以及故障事后复盘。
    • 根据调研复杂度或调用方指定的预算，动态扩展 
      research
      subagent（角色：
      Real-System Research Scout
      ），并提供：
      • 三角验证后的查询和搜索预算（最多 8 个查询、抓取 10 个页面）。
      • 上面的标准输出契约作为必需输出契约；如果需要提供内容繁复的比较性档案，则将其卸载到 
        .agents/scratch/scout-dossier.md
        。
    • 要求 subagent 在综合之前使用 URL 工具检查完整页面正文；严格引用已验证的 URL，绝不只根据搜索摘要进行综合。
  2. 综合与停止：
    • 将完成的报告输出到对话流中（同时提供任何已卸载档案的指针），然后立即结束本轮。