sciomc

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Research Skill

研究技能

Orchestrate parallel scientist agents for comprehensive research workflows with optional AUTO mode for fully autonomous execution.

编排并行科学家Agent以实现完整的研究工作流，支持可选的AUTO模式进行完全自主执行。

Overview

概述

Research is a multi-stage workflow that decomposes complex research goals into parallel investigations:

Decomposition - Break research goal into independent stages/hypotheses
Execution - Run parallel scientist agents on each stage
Verification - Cross-validate findings, check consistency
Synthesis - Aggregate results into comprehensive report

研究是一个多阶段工作流，会将复杂的研究目标拆解为并行的调查任务：

分解 - 将研究目标拆分为独立的阶段/假设
执行 - 为每个阶段启动并行的科学家Agent运行
验证 - 交叉验证发现结果，检查一致性
合成 - 将结果汇总为完整的报告

Usage Examples

使用示例

/oh-my-claudecode:sciomc <goal>                    # Standard research with user checkpoints
/oh-my-claudecode:sciomc AUTO: <goal>              # Fully autonomous until complete
/oh-my-claudecode:sciomc status                    # Check current research session status
/oh-my-claudecode:sciomc resume                    # Resume interrupted research session
/oh-my-claudecode:sciomc list                      # List all research sessions
/oh-my-claudecode:sciomc report <session-id>       # Generate report for session

/oh-my-claudecode:sciomc <goal>                    # 带用户检查点的标准研究模式
/oh-my-claudecode:sciomc AUTO: <goal>              # 完全自主执行直至完成
/oh-my-claudecode:sciomc status                    # 查看当前研究会话状态
/oh-my-claudecode:sciomc resume                    # 恢复被中断的研究会话
/oh-my-claudecode:sciomc list                      # 列出所有研究会话
/oh-my-claudecode:sciomc report <session-id>       # 生成指定会话的报告

Quick Examples

快速示例

/oh-my-claudecode:sciomc What are the performance characteristics of different sorting algorithms?
/oh-my-claudecode:sciomc AUTO: Analyze authentication patterns in this codebase
/oh-my-claudecode:sciomc How does the error handling work across the API layer?

/oh-my-claudecode:sciomc 不同排序算法的性能特征是什么？
/oh-my-claudecode:sciomc AUTO: 分析这个代码库中的认证模式
/oh-my-claudecode:sciomc API层的错误处理是如何工作的？

Research Protocol

研究协议

Stage Decomposition Pattern

阶段分解模式

When given a research goal, decompose into 3-7 independent stages:

markdown

undefined

收到研究目标时，将其拆解为3-7个独立阶段：

markdown

undefined

Research Decomposition

研究分解

Goal: <original research goal>

目标： <原始研究目标>

Stage 1: <stage-name>

阶段1：<阶段名称>

Focus: What this stage investigates
Hypothesis: Expected finding (if applicable)
Scope: Files/areas to examine
Tier: LOW | MEDIUM | HIGH

聚焦点： 本阶段的调查内容
假设： 预期发现（如适用）
范围： 需要检查的文件/领域
等级： LOW | MEDIUM | HIGH

Stage 2: <stage-name>

阶段2：<阶段名称>

...

undefined

...

undefined

Parallel Scientist Invocation

并行科学家调用

Fire independent stages in parallel via Task tool:

// Stage 1 - Simple data gathering
Task(subagent_type="oh-my-claudecode:scientist", model="haiku", prompt="[RESEARCH_STAGE:1] Investigate...")

// Stage 2 - Standard analysis
Task(subagent_type="oh-my-claudecode:scientist", model="sonnet", prompt="[RESEARCH_STAGE:2] Analyze...")

// Stage 3 - Complex reasoning
Task(subagent_type="oh-my-claudecode:scientist", model="opus", prompt="[RESEARCH_STAGE:3] Deep analysis of...")

通过Task工具并行启动独立阶段任务：

// 阶段1 - 简单数据收集
Task(subagent_type="oh-my-claudecode:scientist", model="haiku", prompt="[RESEARCH_STAGE:1] 调查...")

// 阶段2 - 标准分析
Task(subagent_type="oh-my-claudecode:scientist", model="sonnet", prompt="[RESEARCH_STAGE:2] 分析...")

// 阶段3 - 复杂推理
Task(subagent_type="oh-my-claudecode:scientist", model="opus", prompt="[RESEARCH_STAGE:3] 深度分析...")

Smart Model Routing

智能模型路由

CRITICAL: Always pass
model
parameter explicitly!

Task Complexity	Agent	Model	Use For
Data gathering	`scientist` (model=haiku)	haiku	File enumeration, pattern counting, simple lookups
Standard analysis	`scientist`	sonnet	Code analysis, pattern detection, documentation review
Complex reasoning	`scientist`	opus	Architecture analysis, cross-cutting concerns, hypothesis validation

关键：必须显式传入
model
参数！

任务复杂度	Agent	模型	适用场景
数据收集	`scientist` (model=haiku)	haiku	文件枚举、模式统计、简单查询
标准分析	`scientist`	sonnet	代码分析、模式检测、文档审查
复杂推理	`scientist`	opus	架构分析、跨领域问题、假设验证

Routing Decision Guide

路由决策指南

Research Task	Tier	Example Prompt
"Count occurrences of X"	LOW	"Count all usages of useState hook"
"Find all files matching Y"	LOW	"List all test files in the project"
"Analyze pattern Z"	MEDIUM	"Analyze error handling patterns in API routes"
"Document how W works"	MEDIUM	"Document the authentication flow"
"Explain why X happens"	HIGH	"Explain why race conditions occur in the cache layer"
"Compare approaches A vs B"	HIGH	"Compare Redux vs Context for state management here"

研究任务	等级	示例提示
"统计X的出现次数"	LOW	"统计useState hook的所有使用次数"
"查找所有匹配Y的文件"	LOW	"列出项目中所有测试文件"
"分析Z模式"	MEDIUM	"分析API路由中的错误处理模式"
"记录W的工作原理"	MEDIUM	"记录认证流程"
"解释X发生的原因"	HIGH	"解释缓存层出现竞态条件的原因"
"比较A和B两种方案"	HIGH	"对比Redux和Context在此处做状态管理的优劣"

Verification Loop

验证循环

After parallel execution completes, verify findings:

// Cross-validation stage
Task(subagent_type="oh-my-claudecode:scientist", model="sonnet", prompt="
[RESEARCH_VERIFICATION]
Cross-validate these findings for consistency:

Stage 1 findings: <summary>
Stage 2 findings: <summary>
Stage 3 findings: <summary>

Check for:
1. Contradictions between stages
2. Missing connections
3. Gaps in coverage
4. Evidence quality

Output: [VERIFIED] or [CONFLICTS:<list>]
")

并行执行完成后，验证发现结果：

// 交叉验证阶段
Task(subagent_type="oh-my-claudecode:scientist", model="sonnet", prompt="
[RESEARCH_VERIFICATION]
交叉验证以下发现的一致性：

阶段1发现：<摘要>
阶段2发现：<摘要>
阶段3发现：<摘要>

检查项：
1. 各阶段之间的矛盾
2. 缺失的关联关系
3. 覆盖范围缺口
4. 证据质量

输出：[VERIFIED] 或 [CONFLICTS:<冲突列表>]
")

AUTO Mode

AUTO模式

AUTO mode runs the complete research workflow autonomously with loop control.

AUTO模式通过循环控制自主运行完整的研究工作流。

Loop Control Protocol

循环控制协议

[RESEARCH + AUTO - ITERATION {{ITERATION}}/{{MAX}}]

Your previous attempt did not output the completion promise. Continue working.

Current state: {{STATE}}
Completed stages: {{COMPLETED_STAGES}}
Pending stages: {{PENDING_STAGES}}

[RESEARCH + AUTO - 迭代 {{ITERATION}}/{{MAX}}]

你上一次尝试未输出完成承诺标识，请继续工作。

当前状态：{{STATE}}
已完成阶段：{{COMPLETED_STAGES}}
待处理阶段：{{PENDING_STAGES}}

Promise Tags

承诺标签

Tag	Meaning	When to Use
`[PROMISE:RESEARCH_COMPLETE]`	Research finished successfully	All stages done, verified, report generated
`[PROMISE:RESEARCH_BLOCKED]`	Cannot proceed	Missing data, access issues, circular dependency

标签	含义	使用时机
`[PROMISE:RESEARCH_COMPLETE]`	研究成功完成	所有阶段完成、已验证、报告已生成
`[PROMISE:RESEARCH_BLOCKED]`	无法继续推进	数据缺失、访问问题、循环依赖

AUTO Mode Rules

AUTO模式规则

Max Iterations: 10 (configurable)
Continue until: Promise tag emitted OR max iterations
State tracking: Persist after each stage completion
Cancellation:
```
/oh-my-claudecode:cancel
```
or "stop", "cancel"

最大迭代次数： 10（可配置）
运行终止条件： 输出承诺标签或达到最大迭代次数
状态追踪： 每个阶段完成后持久化状态
取消方式：
```
/oh-my-claudecode:cancel
```
或输入 "stop", "cancel"

AUTO Mode Example

AUTO模式示例

/oh-my-claudecode:sciomc AUTO: Comprehensive security analysis of the authentication system

[Decomposition]
- Stage 1 (LOW): Enumerate auth-related files
- Stage 2 (MEDIUM): Analyze token handling
- Stage 3 (MEDIUM): Review session management
- Stage 4 (HIGH): Identify vulnerability patterns
- Stage 5 (MEDIUM): Document security controls

[Execution - Parallel]
Firing stages 1-3 in parallel...
Firing stages 4-5 after dependencies complete...

[Verification]
Cross-validating findings...

[Synthesis]
Generating report...

[PROMISE:RESEARCH_COMPLETE]

/oh-my-claudecode:sciomc AUTO: 对认证系统进行全面安全分析

[分解]
- 阶段1（LOW）：枚举与认证相关的文件
- 阶段2（MEDIUM）：分析Token处理逻辑
- 阶段3（MEDIUM）：审查会话管理机制
- 阶段4（HIGH）：识别漏洞模式
- 阶段5（MEDIUM）：记录安全控制措施

[执行 - 并行]
并行启动阶段1-3...
依赖完成后启动阶段4-5...

[验证]
交叉验证发现结果...

[合成]
生成报告...

[PROMISE:RESEARCH_COMPLETE]

Parallel Execution Patterns

并行执行模式

Independent Dataset Analysis (Parallel)

独立数据集分析（并行）

When stages analyze different data sources:

// All fire simultaneously
Task(subagent_type="oh-my-claudecode:scientist", model="haiku", prompt="[STAGE:1] Analyze src/api/...")
Task(subagent_type="oh-my-claudecode:scientist", model="haiku", prompt="[STAGE:2] Analyze src/utils/...")
Task(subagent_type="oh-my-claudecode:scientist", model="haiku", prompt="[STAGE:3] Analyze src/components/...")

当各阶段分析不同数据源时使用：

// 全部同时启动
Task(subagent_type="oh-my-claudecode:scientist", model="haiku", prompt="[STAGE:1] 分析 src/api/...")
Task(subagent_type="oh-my-claudecode:scientist", model="haiku", prompt="[STAGE:2] 分析 src/utils/...")
Task(subagent_type="oh-my-claudecode:scientist", model="haiku", prompt="[STAGE:3] 分析 src/components/...")

Hypothesis Battery (Parallel)

假设组测试（并行）

When testing multiple hypotheses:

// Test hypotheses simultaneously
Task(subagent_type="oh-my-claudecode:scientist", model="sonnet", prompt="[HYPOTHESIS:A] Test if caching improves...")
Task(subagent_type="oh-my-claudecode:scientist", model="sonnet", prompt="[HYPOTHESIS:B] Test if batching reduces...")
Task(subagent_type="oh-my-claudecode:scientist", model="sonnet", prompt="[HYPOTHESIS:C] Test if lazy loading helps...")

当需要测试多个假设时使用：

// 同时测试多个假设
Task(subagent_type="oh-my-claudecode:scientist", model="sonnet", prompt="[HYPOTHESIS:A] 测试缓存是否提升...")
Task(subagent_type="oh-my-claudecode:scientist", model="sonnet", prompt="[HYPOTHESIS:B] 测试批处理是否减少...")
Task(subagent_type="oh-my-claudecode:scientist", model="sonnet", prompt="[HYPOTHESIS:C] 测试懒加载是否有助于...")

Cross-Validation (Sequential)

交叉验证（串行）

When verification depends on all findings:

// Wait for all parallel stages
[stages complete]

// Then sequential verification
Task(subagent_type="oh-my-claudecode:scientist", model="opus", prompt="
[CROSS_VALIDATION]
Validate consistency across all findings:
- Finding 1: ...
- Finding 2: ...
- Finding 3: ...
")

当验证依赖所有阶段的发现结果时使用：

// 等待所有并行阶段完成
[阶段完成]

// 随后串行执行验证
Task(subagent_type="oh-my-claudecode:scientist", model="opus", prompt="
[CROSS_VALIDATION]
验证所有发现的一致性：
- 发现1：...
- 发现2：...
- 发现3：...
")

Concurrency Limit

并发限制

Maximum 20 concurrent scientist agents to prevent resource exhaustion.

If more than 20 stages, batch them:

Batch 1: Stages 1-5 (parallel)
[wait for completion]
Batch 2: Stages 6-7 (parallel)

最多同时运行20个科学家Agent以避免资源耗尽。

如果阶段数量超过20，分批执行：

批次1：阶段1-5（并行）
[等待完成]
批次2：阶段6-7（并行）

Session Management

会话管理

Directory Structure

目录结构

.omc/research/{session-id}/
  state.json              # Session state and progress
  stages/
    stage-1.md            # Stage 1 findings
    stage-2.md            # Stage 2 findings
    ...
  findings/
    raw/                  # Raw findings from scientists
    verified/             # Post-verification findings
  figures/
    figure-1.png          # Generated visualizations
    ...
  report.md               # Final synthesized report

.omc/research/{session-id}/
  state.json              # 会话状态与进度
  stages/
    stage-1.md            # 阶段1发现结果
    stage-2.md            # 阶段2发现结果
    ...
  findings/
    raw/                  # 科学家返回的原始发现
    verified/             # 验证后的发现
  figures/
    figure-1.png          # 生成的可视化图表
    ...
  report.md               # 最终合成的报告

State File Format

状态文件格式

json

{
  "id": "research-20240115-abc123",
  "goal": "Original research goal",
  "status": "in_progress | complete | blocked | cancelled",
  "mode": "standard | auto",
  "iteration": 3,
  "maxIterations": 10,
  "stages": [
    {
      "id": 1,
      "name": "Stage name",
      "tier": "LOW | MEDIUM | HIGH",
      "status": "pending | running | complete | failed",
      "startedAt": "ISO timestamp",
      "completedAt": "ISO timestamp",
      "findingsFile": "stages/stage-1.md"
    }
  ],
  "verification": {
    "status": "pending | passed | failed",
    "conflicts": [],
    "completedAt": "ISO timestamp"
  },
  "createdAt": "ISO timestamp",
  "updatedAt": "ISO timestamp"
}

json

{
  "id": "research-20240115-abc123",
  "goal": "原始研究目标",
  "status": "in_progress | complete | blocked | cancelled",
  "mode": "standard | auto",
  "iteration": 3,
  "maxIterations": 10,
  "stages": [
    {
      "id": 1,
      "name": "阶段名称",
      "tier": "LOW | MEDIUM | HIGH",
      "status": "pending | running | complete | failed",
      "startedAt": "ISO时间戳",
      "completedAt": "ISO时间戳",
      "findingsFile": "stages/stage-1.md"
    }
  ],
  "verification": {
    "status": "pending | passed | failed",
    "conflicts": [],
    "completedAt": "ISO时间戳"
  },
  "createdAt": "ISO时间戳",
  "updatedAt": "ISO时间戳"
}

Session Commands

会话命令

Command	Action
`/oh-my-claudecode:sciomc status`	Show current session progress
`/oh-my-claudecode:sciomc resume`	Resume most recent interrupted session
`/oh-my-claudecode:sciomc resume <session-id>`	Resume specific session
`/oh-my-claudecode:sciomc list`	List all sessions with status
`/oh-my-claudecode:sciomc report <session-id>`	Generate/regenerate report
`/oh-my-claudecode:sciomc cancel`	Cancel current session (preserves state)

命令	作用
`/oh-my-claudecode:sciomc status`	显示当前会话进度
`/oh-my-claudecode:sciomc resume`	恢复最近被中断的会话
`/oh-my-claudecode:sciomc resume <session-id>`	恢复指定会话
`/oh-my-claudecode:sciomc list`	列出所有会话及状态
`/oh-my-claudecode:sciomc report <session-id>`	生成/重新生成报告
`/oh-my-claudecode:sciomc cancel`	取消当前会话（保留状态）

Tag Extraction

标签提取

Scientists use structured tags for findings. Extract them with these patterns:

科学家使用结构化标签标记发现结果，通过以下模式提取：

Finding Tags

发现标签

[FINDING:<id>] <title>
<evidence and analysis>
[/FINDING]

[EVIDENCE:<finding-id>]
- File: <path>
- Lines: <range>
- Content: <relevant code/text>
[/EVIDENCE]

[CONFIDENCE:<level>] # HIGH | MEDIUM | LOW
<reasoning for confidence level>

[FINDING:<id>] <标题>
<证据与分析>
[/FINDING]

[EVIDENCE:<finding-id>]
- 文件：<路径>
- 行号：<范围>
- 内容：<相关代码/文本>
[/EVIDENCE]

[CONFIDENCE:<level>] # HIGH | MEDIUM | LOW
<置信度等级的判定理由>

Extraction Regex Patterns

提取正则表达式模式

javascript

// Finding extraction
const findingPattern = /\[FINDING:(\w+)\]\s*(.*?)\n([\s\S]*?)\[\/FINDING\]/g;

// Evidence extraction
const evidencePattern = /\[EVIDENCE:(\w+)\]([\s\S]*?)\[\/EVIDENCE\]/g;

// Confidence extraction
const confidencePattern = /\[CONFIDENCE:(HIGH|MEDIUM|LOW)\]\s*(.*)/g;

// Stage completion
const stageCompletePattern = /\[STAGE_COMPLETE:(\d+)\]/;

// Verification result
const verificationPattern = /\[(VERIFIED|CONFLICTS):?(.*?)\]/;

javascript

// 发现结果提取
const findingPattern = /\[FINDING:(\w+)\]\s*(.*?)\n([\s\S]*?)\[\/FINDING\]/g;

// 证据提取
const evidencePattern = /\[EVIDENCE:(\w+)\]([\s\S]*?)\[\/EVIDENCE\]/g;

// 置信度提取
const confidencePattern = /\[CONFIDENCE:(HIGH|MEDIUM|LOW)\]\s*(.*)/g;

// 阶段完成标识
const stageCompletePattern = /\[STAGE_COMPLETE:(\d+)\]/;

// 验证结果提取
const verificationPattern = /\[(VERIFIED|CONFLICTS):?(.*?)\]/;

Evidence Window

证据上下文

When extracting evidence, include context window:

[EVIDENCE:F1]
- File: /src/auth/login.ts
- Lines: 45-52 (context: 40-57)
- Content:
  ```typescript
  // Lines 45-52 with 5 lines context above/below

[/EVIDENCE]

undefined

提取证据时，包含上下文窗口：

[EVIDENCE:F1]
- 文件：/src/auth/login.ts
- 行号：45-52（上下文：40-57）
- 内容：
  ```typescript
  // 行45-52，上下各带5行上下文

[/EVIDENCE]

undefined

Quality Validation

质量验证

Findings must meet quality threshold:

Quality Check	Requirement
Evidence present	At least 1 [EVIDENCE] per [FINDING]
Confidence stated	Each finding has [CONFIDENCE]
Source cited	File paths are absolute and valid
Reproducible	Another agent could verify

发现结果必须满足质量门槛：

质量检查	要求
存在证据	每个[FINDING]至少对应1个[EVIDENCE]
声明置信度	每个发现都带有[CONFIDENCE]
标注来源	文件路径为绝对路径且有效
可复现	其他Agent可以验证结果

Report Generation

报告生成

Report Template

报告模板

markdown

undefined

markdown

undefined

Research Report: {{GOAL}}

研究报告：{{GOAL}}

Session ID: {{SESSION_ID}} Date: {{DATE}} Status: {{STATUS}}

会话ID： {{SESSION_ID}} 日期： {{DATE}} 状态： {{STATUS}}

Executive Summary

执行摘要

Methodology

方法论

Research Stages

研究阶段

Stage	Focus	Tier	Status
{{STAGES_TABLE}}

阶段	聚焦点	等级	状态
{{STAGES_TABLE}}

Approach

实现方案

{{Description of decomposition rationale and execution strategy}}

Key Findings

核心发现

Finding 1: {{TITLE}}

发现1：{{TITLE}}

Confidence: {{HIGH|MEDIUM|LOW}}

置信度： {{HIGH|MEDIUM|LOW}}

Evidence

证据

Finding 2: {{TITLE}}

发现2：{{TITLE}}

...

Visualizations

可视化图表

Cross-Validation Results

交叉验证结果

Limitations

局限性

{{Limitation 1}}
{{Limitation 2}}
{{Areas not covered and why}}

{{局限性1}}
{{局限性2}}
{{未覆盖的领域及原因}}

Recommendations

建议

{{Actionable recommendation}}
{{Actionable recommendation}}

{{可执行的建议}}
{{可执行的建议}}

Appendix

附录

Raw Data

原始数据

Session State

会话状态

undefined

undefined

Figure Embedding Protocol

图表嵌入协议

Scientists generate visualizations using this marker:

[FIGURE:path/to/figure.png]
Caption: Description of what the figure shows
Alt: Accessibility description
[/FIGURE]

Report generator embeds figures:

markdown

undefined

科学家使用以下标记生成可视化图表：

[FIGURE:path/to/figure.png]
Caption: 图表内容说明
Alt: 无障碍描述
[/FIGURE]

报告生成器嵌入图表：

markdown

undefined

Visualizations

可视化图表

Caption: Description of what the figure shows

Caption: Description of what the figure shows

undefined

Caption：图表内容说明

Caption：图表内容说明

undefined

Figure Types

图表类型

Type	Use For	Generated By
Architecture diagram	System structure	scientist
Flow chart	Process flows	scientist
Dependency graph	Module relationships	scientist
Timeline	Sequence of events	scientist
Comparison table	A vs B analysis	scientist

类型	适用场景	生成方
架构图	系统结构	scientist
流程图	流程逻辑	scientist
依赖图	模块关系	scientist
时间线	事件序列	scientist
对比表	A vs B分析	scientist

Configuration

配置

Optional settings in

.claude/settings.json

json

{
  "omc": {
    "research": {
      "maxIterations": 10,
      "maxConcurrentScientists": 5,
      "defaultTier": "MEDIUM",
      "autoVerify": true,
      "generateFigures": true,
      "evidenceContextLines": 5
    }
  }
}

.claude/settings.json

中的可选配置：

json

{
  "omc": {
    "research": {
      "maxIterations": 10,
      "maxConcurrentScientists": 5,
      "defaultTier": "MEDIUM",
      "autoVerify": true,
      "generateFigures": true,
      "evidenceContextLines": 5
    }
  }
}

Cancellation

取消

/oh-my-claudecode:cancel

Or say: "stop research", "cancel research", "abort"

Progress is preserved in

.omc/research/{session-id}/

for resume.

/oh-my-claudecode:cancel

或输入："停止研究", "取消研究", "中止"

进度会保存在

.omc/research/{session-id}/

中，可后续恢复。

Troubleshooting

故障排查

Stuck in verification loop?

Check for conflicting findings between stages
Review state.json for specific conflicts
May need to re-run specific stages with different approach

Scientists returning low-quality findings?

Check tier assignment - complex analysis needs HIGH tier
Ensure prompts include clear scope and expected output format
Review if research goal is too broad

AUTO mode exhausted iterations?

Review state to see where it's stuck
Check if goal is achievable with available data
Consider breaking into smaller research sessions

Missing figures in report?

Verify figures/ directory exists
Check [FIGURE:] tags in findings
Ensure paths are relative to session directory

卡在验证循环？

检查各阶段发现结果之间的冲突
查看state.json了解具体冲突
可能需要用不同方案重新运行特定阶段

科学家返回低质量发现？

检查等级分配 - 复杂分析需要HIGH等级
确保提示中包含明确的范围和预期输出格式
检查研究目标是否过于宽泛

AUTO模式耗尽迭代次数？

查看状态了解卡住的位置
检查现有数据是否可以实现目标
考虑拆分为更小的研究会话

报告中缺少图表？

确认figures/目录存在
检查发现结果中的[FIGURE:]标签
确保路径是相对于会话目录的相对路径