autoresearch

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

<Purpose> Autoresearch is a stateful skill for bounded, evaluator-driven iterative improvement. It owns one mission at a time, keeps iterating through non-passing results, records each evaluation and decision as durable artifacts, and stops only when an explicit max-runtime ceiling or another explicit terminal condition is reached. </Purpose>

<Use_When>

You already have a mission and evaluator from
```
/deep-interview --autoresearch
```
You want persistent single-mission improvement with strict evaluation
You need durable experiment logs under
```
.omc/autoresearch/
```
You want a supported path for periodic reruns via Claude Code native cron </Use_When>

<Do_Not_Use_When>

You need evaluator generation at runtime — use
```
/deep-interview --autoresearch
```
first
You need multiple missions orchestrated together — v1 forbids that
You want the deprecated
```
omc autoresearch
```
CLI flow — it is no longer authoritative </Do_Not_Use_When>

<Contract> - Single-mission only in v1 - Mission setup/evaluator generation stays in `deep-interview --autoresearch` - Evaluator output must be structured JSON with required boolean `pass` and optional numeric `score` - Non-passing iterations do **not** stop the run - Stop conditions are explicit and bounded, with max-runtime as the primary strict stop hook </Contract>

<Required_Artifacts> Canonical persistent storage lives under

.omc/autoresearch/<mission-slug>/

and/or

.omc/logs/autoresearch/<run-id>/

Minimum required artifacts:

mission spec
evaluator script or command reference
per-iteration evaluation JSON
markdown decision logs

Recommended canonical shape:

text

.omc/autoresearch/<mission-slug>/
  mission.md
  evaluator.json
  runs/<run-id>/
    evaluations/
      iteration-0001.json
      iteration-0002.json
    decision-log.md

Reuse existing runtime artifacts when available rather than duplicating them unnecessarily. </Required_Artifacts>

<Workflow> 1. Confirm a single mission exists and evaluator setup is already available. 2. Ensure mode/state is active for `autoresearch` and records: - mission slug/dir - evaluator reference - iteration count - started/updated timestamps - explicit max-runtime or deadline 3. On every iteration: - run exactly one experiment/change cycle - run the evaluator - persist machine-readable evaluation JSON - append a human-readable markdown decision log entry - continue even when evaluation does not pass 4. Stop when: - max-runtime ceiling is reached - user explicitly cancels - another explicit terminal condition is recorded by the runtime </Workflow>

<Cron_Integration> Claude Code native cron is a supported integration point for periodic mission enhancement. In v1, prefer documenting/configuring cron inputs over building a large scheduler UI.

If cron is used:

keep one mission per scheduled job
preserve the same mission/evaluator contract
append new run artifacts rather than overwriting prior experiments </Cron_Integration>

<Execution_Policy>

Do not hand execution back to
```
omc autoresearch
```
Do not create multi-mission orchestration
Prefer reusing
```
src/autoresearch/*
```
runtime/schema helpers where they already match the stricter contract
Keep logs useful to humans, not only machines </Execution_Policy>

<Purpose> Autoresearch是一种由评估器驱动的、用于有限范围迭代改进的有状态skill。它一次仅处理一个任务，针对未通过的结果持续迭代，将每次评估和决策记录为持久化工件，仅当达到明确的最长运行时上限或其他明确终止条件时才停止。 </Purpose>

<Use_When>

您已通过
```
/deep-interview --autoresearch
```
获取任务和评估器
您需要带有严格评估的持久化单任务改进
您需要存储在
```
.omc/autoresearch/
```
下的持久化实验日志
您希望通过Claude Code原生cron实现定期重运行的支持路径 </Use_When>

<Do_Not_Use_When>

您需要在运行时生成评估器——请先使用
```
/deep-interview --autoresearch
```
您需要编排多个任务——v1版本不支持此功能
您想要使用已弃用的
```
omc autoresearch
```
CLI流程——该流程已不再是权威方案 </Do_Not_Use_When>

<Contract> - v1版本仅支持单任务 - 任务设置/评估器生成需通过`deep-interview --autoresearch`完成 - 评估器输出必须为结构化JSON，包含必填布尔值`pass`和可选数值`score` - 未通过的迭代不会终止运行 - 停止条件明确且受限，最长运行时是主要的严格停止钩子 </Contract>

<Required_Artifacts> 标准持久化存储位于

.omc/autoresearch/<mission-slug>/

和/或

.omc/logs/autoresearch/<run-id>/

下。

最低要求的工件：

任务规格
评估器脚本或命令引用
每次迭代的评估JSON
Markdown决策日志

推荐的标准结构：

text

.omc/autoresearch/<mission-slug>/
  mission.md
  evaluator.json
  runs/<run-id>/
    evaluations/
      iteration-0001.json
      iteration-0002.json
    decision-log.md

在可用时重用现有运行时工件，避免不必要的重复。 </Required_Artifacts>

<Workflow> 1. 确认存在单个任务且评估器设置已就绪。 2. 确保`autoresearch`的模式/状态已激活，并记录： - 任务标识/目录 - 评估器引用 - 迭代次数 - 启动/更新时间戳 - 明确的最长运行时或截止时间 3. 在每次迭代中： - 运行恰好一个实验/变更周期 - 运行评估器 - 持久化机器可读的评估JSON - 添加一条人类可读的Markdown决策日志条目 - 即使评估未通过也继续执行 4. 在以下情况时停止： - 达到最长运行时上限 - 用户明确取消 - 运行时记录了其他明确的终止条件 </Workflow>

<Cron_Integration> Claude Code原生cron是支持定期任务增强的集成点。在v1版本中，优先记录/配置cron输入，而非构建大型调度器UI。

如果使用cron：

每个调度任务对应一个任务
保留相同的任务/评估器契约
添加新的运行工件，而非覆盖之前的实验 </Cron_Integration>

<Execution_Policy>

不要将执行权交回给
```
omc autoresearch
```
不要创建多任务编排
在现有
```
src/autoresearch/*
```
运行时/模式助手符合更严格契约的情况下，优先重用它们
确保日志对人类有用，而非仅适用于机器 </Execution_Policy>