Back to Details

capture

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

MANDATORY PREPARATION

强制准备

Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first.
Capture the current session's work into a persistent summary. This creates a record that survives session boundaries — future commands can reference what happened here.
调用 /agent-workflow —— 它包含工作流原则、反模式以及上下文收集协议。在继续操作前请遵循该协议——如果尚不存在工作流上下文，你必须先运行 /teach-maestro。
将当前会话的工作内容整理为持久化摘要。这会创建一条跨会话保留的记录——后续命令可以引用本次会话中发生的内容。

What to Capture

需捕获的内容

Read the conversation history and identify:
  1. Commands run — which Maestro commands were invoked and in what order
  2. Decisions made — architectural choices, trade-offs accepted, patterns adopted
  3. Files changed — what was created, modified, or deleted
  4. Issues found — bugs, gaps, or risks identified
  5. Next steps — what should happen next (be specific)
阅读对话历史并识别以下内容：
  1. 已运行命令 —— 调用了哪些Maestro命令以及调用顺序
  2. 已做决策 —— 架构选择、接受的权衡方案、采用的模式
  3. 变更文件 —— 新建、修改或删除的内容
  4. 发现的问题 —— 识别出的bug、缺口或风险
  5. 后续步骤 —— 接下来的工作内容（请具体说明）

Output Format

输出格式

Generate a session summary file at 
.maestro/sessions/{date}_{topic}.md
:
markdown
undefined
在 
.maestro/sessions/{date}_{topic}.md
路径生成会话摘要文件：
markdown
undefined

Session: {topic}

Session: {topic}

Date: {YYYY-MM-DD}
Date: {YYYY-MM-DD}

Commands Run

Commands Run

  • /diagnose → Score: 18/25
  • /fortify → Added retry logic to API handlers
  • /evaluate → Verified with 3 test scenarios
  • /diagnose → Score: 18/25
  • /fortify → Added retry logic to API handlers
  • /evaluate → Verified with 3 test scenarios

Decisions

Decisions

  • Chose retry-with-backoff over circuit breaker (simpler, sufficient for current load)
  • Kept synchronous error handling (async not justified yet)
  • Chose retry-with-backoff over circuit breaker (simpler, sufficient for current load)
  • Kept synchronous error handling (async not justified yet)

Files Changed

Files Changed

  • src/api/handler.ts
    — added retry wrapper
  • src/middleware/auth.ts
    — added input validation
  • tests/api.test.ts
    — new test file
  • src/api/handler.ts
    — added retry wrapper
  • src/middleware/auth.ts
    — added input validation
  • tests/api.test.ts
    — new test file

Open Issues

Open Issues

  • Rate limiting not yet implemented (deferred to next session)
  • Rate limiting not yet implemented (deferred to next session)

Next Steps

Next Steps

  1. Run 
    /guard
    to add rate limiting
  2. Run 
    /evaluate
    with adversarial test cases

Also append a decision entry to `.maestro/decisions.jsonl` recording this capture.
  1. Run 
    /guard
    to add rate limiting
  2. Run 
    /evaluate
    with adversarial test cases

同时向 `.maestro/decisions.jsonl` 追加一条决策条目，记录本次捕获操作。

Session Capture Checklist

会话捕获检查清单

  • All commands from this session listed
  • Key decisions documented with rationale
  • Files changed listed with brief descriptions
  • Open issues captured (nothing lost)
  • Next steps are specific and actionable
  • Summary saved to 
    .maestro/sessions/
  • 已列出本次会话的所有命令
  • 关键决策已记录并说明理由
  • 已列出变更文件并附简要说明
  • 未解决问题已捕获（无遗漏）
  • 后续步骤具体且可执行
  • 摘要已保存至 
    .maestro/sessions/
    目录

Recommended Next Step

推荐后续步骤

After capturing, your next session should start with 
/recap
to restore context, then proceed with the next steps listed above.
NEVER:
  • Store raw prompts or full LLM outputs in the session file
  • Overwrite an existing session file — create a new one
  • Skip the "Next Steps" section — this is what makes capture valuable
  • Capture without reading the conversation history first
  • Auto-capture without the user invoking this command
完成捕获后，下一次会话应先运行 
/recap
恢复上下文，再继续执行上述后续步骤。
绝对禁止：
  • 在会话文件中存储原始提示词或完整的LLM输出
  • 覆盖已有的会话文件——请创建新文件
  • 省略“后续步骤”部分——这是捕获的价值所在
  • 未先阅读对话历史就进行捕获
  • 用户未调用本命令就自动捕获