survey

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

survey - Cross-Platform Problem-Space Scan

survey - 跨平台问题域扫描

Keyword:
survey
| Platforms: OMC / OMX / OHMG / Claude Code / Codex CLI / Gemini CLI / OpenCode
Survey the landscape before planning, coding, or committing to a direction.

关键词：
survey
| 支持平台：OMC / OMX / OHMG / Claude Code / Codex CLI / Gemini CLI / OpenCode
在规划、编码或敲定方向前完成态势扫描。

When to use this skill

何时使用此技能

Before building a new feature, tool, workflow, or agent capability
When the user asks "what exists?", "scan the landscape", "research this space", or "survey solutions"
When you need problem context, current workarounds, and solution gaps before
```
/plan
```
,
```
jeo
```
,
```
ralph
```
, or implementation
When the topic spans multiple agent platforms and you need a single vendor-neutral picture

在构建新功能、工具、工作流或Agent能力前
当用户询问“现有哪些方案？”、“扫描行业态势”、“调研该领域”或“调研解决方案”时
当你在执行
```
/plan
```
、
```
jeo
```
、
```
ralph
```
或落地前需要了解问题上下文、当前临时方案、解决方案缺口时
当主题覆盖多个Agent平台，你需要一份中立的统一梳理结果时

Do not use this skill when

请勿在以下场景使用此技能

The user already knows the solution and wants implementation now
The task is a small bug fix or narrow code change
The user needs a feasibility study, architecture plan, or execution roadmap rather than discovery

用户已经明确解决方案，现在需要落地
任务是小型bug修复或范围狭窄的代码变更
用户需要可行性研究、架构方案或执行路线图，而非探索性调研

Output Package

输出包

Save research in a platform-neutral directory so Claude / Codex / Gemini can all reuse it:

text

.survey/{slug}/
├── triage.md
├── context.md
├── solutions.md
└── platform-map.md    # optional; required for agent/tooling/platform topics

```
triage.md
```
: problem / audience / why now
```
context.md
```
: workflows, affected users, workarounds, adjacent problems, user voices
```
solutions.md
```
: solution inventory, categories, frequency, gaps, contradictions, key insight
```
platform-map.md
```
: normalize platform-specific findings into
```
settings
```
,
```
rules
```
,
```
hooks
```

将调研结果存储在平台无关的目录下，以便Claude / Codex / Gemini都可以复用：

text

.survey/{slug}/
├── triage.md
├── context.md
├── solutions.md
└── platform-map.md    # 可选；Agent/工具/平台相关主题必填

```
triage.md
```
：问题/受众/立项原因
```
context.md
```
：工作流、受影响用户、临时解决方案、关联问题、用户反馈
```
solutions.md
```
：解决方案盘点、分类、出现频率、缺口、矛盾点、核心洞察
```
platform-map.md
```
：将平台特定的发现统一规整为
```
settings
```
、
```
rules
```
、
```
hooks
```
三类

Core Abstraction Layer

核心抽象层

When the topic involves agent tooling, model orchestration, hooks, permissions, or vendor APIs, normalize findings into three layers:

```
settings
```
: model, safety, temperature, max tokens, system prompt, provider parameters
```
rules
```
: allow/deny/modify policy, guardrails, action constraints, approval logic
```
hooks
```
: pre/post/error callbacks, notify handlers, lifecycle automation, event triggers

Use this abstraction when comparing Claude, Codex, Gemini, OMC, OMX, or OHMG. Do not describe vendor features as unrelated one-off concepts if they map cleanly into one of these three layers.

Recommended internal profile:

yaml

survey_profile:
  settings:
    search_language: English
    output_language: user-language
    max_searches_per_lane: 8-10
    save_root: .survey
  rules:
    - facts_only
    - no_code_generation
    - ask_max_2_triage_questions
    - dedupe_solution_names
    - include_source_links
  hooks:
    pre_research:
      - normalize_topic
      - choose_platform_adapter
    post_lane:
      - merge_notes
      - record_sources
    post_run:
      - write_summary
      - suggest_next_skill

当主题涉及Agent工具、模型编排、hooks、权限或厂商API时，将调研结果统一规整为三层：

```
settings
```
：模型、安全规则、temperature、最大token数、系统提示词、服务商参数
```
rules
```
：允许/拒绝/修改策略、护栏、操作约束、审批逻辑
```
hooks
```
：前置/后置/错误回调、通知处理器、生命周期自动化、事件触发器

在对比Claude、Codex、Gemini、OMC、OMX或OHMG时使用该抽象层。如果厂商功能可以清晰归入上述三层，请勿将其描述为无关的独立概念。

推荐内部配置：

yaml

survey_profile:
  settings:
    search_language: English
    output_language: user-language
    max_searches_per_lane: 8-10
    save_root: .survey
  rules:
    - facts_only
    - no_code_generation
    - ask_max_2_triage_questions
    - dedupe_solution_names
    - include_source_links
  hooks:
    pre_research:
      - normalize_topic
      - choose_platform_adapter
    post_lane:
      - merge_notes
      - record_sources
    post_run:
      - write_summary
      - suggest_next_skill

Platform Adapter

平台适配器

Select the closest available orchestration surface, but keep the output format identical.

Platform	Preferred execution shape	Notes
OMC / Claude Code	4 parallel research agents. Prefer research-oriented specialist agents when available; otherwise use general-purpose agents with web search.	Keep artifacts in `.survey/` , not `.omc/` , so other platforms can reuse them.
OMX / Codex CLI	Use `$research` , explorer/planner-style agents, or parallel workers with web access.	Translate vendor config into `settings/rules/hooks` in `platform-map.md` when relevant.
OHMG / Gemini / Antigravity	Use Workflow Guide + PM/research-capable agents or equivalent parallel lanes.	Preserve the same 4-lane structure and shared artifact names.
OpenCode / fallback	Use generic web-capable agents in parallel.	Do not block on missing specialized agent names.

If a platform-specific specialist does not exist, fall back to a general-purpose web-enabled agent and keep going.

选择最接近的可用编排载体，但保持输出格式完全一致。

平台	推荐执行模式	说明
OMC / Claude Code	4个并行调研Agent。优先使用研究导向的专业Agent，否则使用具备网页搜索能力的通用Agent。	将产出物存储在 `.survey/` 而非 `.omc/` 目录下，以便其他平台复用。
OMX / Codex CLI	使用 `$research` 、探索/规划类Agent或具备网页访问能力的并行工作节点。	相关场景下将厂商配置转换为 `platform-map.md` 中的 `settings/rules/hooks` 格式。
OHMG / Gemini / Antigravity	使用工作流指南 + 具备PM/调研能力的Agent或等效并行链路。	保留相同的4链路结构和统一的产出物命名。
OpenCode / fallback	使用具备通用网页访问能力的并行Agent。	不要因缺少特定专业Agent而阻塞流程。

如果不存在平台专属的专业Agent，降级使用具备网页访问能力的通用Agent继续执行即可。

Execution Policy

执行规则

Never write product code in this skill. This is a research-only skill.
Search broadly in English for coverage, unless the user explicitly requires another search language.
Save files in the user's language unless the repository has a stronger convention.
Ask at most 2 triage questions, one at a time, only if
```
what
```
,
```
who
```
, or
```
why
```
is unclear.
Run all 4 research lanes in parallel whenever possible.
Keep claims source-backed. Include links for quotes, rankings, and non-obvious claims.
Deduplicate tools that appear under multiple names or product tiers.
Do not recommend build/kill/adopt by default. Present the landscape and gaps.

请勿在此技能中编写产品代码，这是仅用于调研的技能。
优先使用英文做广泛搜索以覆盖更多内容，除非用户明确要求使用其他搜索语言。
使用用户的语言存储文件，除非仓库有更明确的规范要求。
最多仅询问2个分诊问题，一次问一个，仅在
```
what
```
、
```
who
```
或
```
why
```
不明确时提问。
尽可能并行执行全部4条调研链路。
所有结论都要有来源支撑，引用、排名和非显而易见的结论需要附上链接。
对不同名称或产品层级下出现的相同工具做去重处理。
不要默认推荐构建/停用/采纳某方案，仅呈现态势和缺口即可。

Workflow

工作流

Step 0: Triage

步骤0：分诊

Parse the request into:

```
what
```
: the pain point, idea, or capability to survey
```
who
```
: who feels the pain or uses the workflow
```
why
```
: why it matters now

Before proceeding, check whether

.survey/{slug}/triage.md

already exists.

If it exists, ask whether to reuse or overwrite.
If the user keeps the existing survey, skip to Step 3 and summarize the saved files.

Save:

markdown

undefined

Parse the request into:

```
what
```
：要调研的痛点、想法或能力
```
who
```
：受痛点影响或使用该工作流的人群
```
why
```
：当前需要调研的原因

继续执行前，检查

.survey/{slug}/triage.md

是否已存在。

如果存在，询问用户是复用还是覆盖。
如果用户选择保留现有调研，跳转到步骤3并汇总已存储的文件内容。

存储内容：

markdown

undefined

Triage

Problem: {what}
Audience: {who}
Why now: {why}

undefined

Problem: {what}
Audience: {who}
Why now: {why}

undefined

Step 1: Run 4 Parallel Lanes

步骤1：并行执行4条调研链路

Launch all lanes together.

同时启动所有链路。

Lane A: Context

链路A：上下文

Research:

where the problem appears in real workflows
who is affected
how people currently work around it
adjacent problems and downstream consequences
direct user voices from communities

Return sections:

```
## Workflow Context
```
```
## Affected Users
```
```
## Current Workarounds
```
```
## Adjacent Problems
```
```
## User Voices
```

调研内容：

问题在实际工作流中的出现场景
受影响的人群
用户当前的临时解决方案
关联问题和下游影响
来自社区的直接用户反馈

返回章节：

```
## 工作流上下文
```
```
## 受影响用户
```
```
## 当前临时解决方案
```
```
## 关联问题
```
```
## 用户反馈
```

Lane B: Solutions

链路B：解决方案

Research:

products, plugins, libraries, SaaS, GitHub projects, services
curated lists and comparison pages
common pricing and packaging
limitations and repeated complaints

Return sections:

```
## Solutions
```
```
## Frequency Ranking
```
```
## Categories
```
```
## Curated Sources
```

调研内容：

产品、插件、库、SaaS、GitHub项目、服务
精选列表和对比页面
通用定价和打包模式
局限性和高频投诉

返回章节：

```
## 解决方案
```
```
## 出现频率排名
```
```
## 分类
```
```
## 精选来源
```

Lane C: Actual Behavior

链路C：实际使用行为

Research:

what people actually use in practice
which manual workflows persist despite vendor claims
common frustration patterns
where users drop back to spreadsheets, scripts, copy-paste, or multi-tool workflows

Return sections:

```
## What People Actually Use
```
```
## Common Workarounds
```
```
## Pain Points With Current Solutions
```
```
## Sources
```

调研内容：

用户实际在使用的方案
尽管厂商有相关宣传但仍然存在的手动工作流
高频痛点模式
用户退回到使用表格、脚本、复制粘贴或多工具组合工作流的场景

返回章节：

```
## 用户实际使用的方案
```
```
## 通用临时解决方案
```
```
## 现有方案的痛点
```
```
## 来源
```

Lane D: Alternatives / Platform Map

链路D：替代方案 / 平台映射

Default mode:

JTBD alternatives
cross-industry substitutes
indirect competitors

For agent / model / orchestration topics, this lane must instead normalize the space into:

```
## Settings
```
```
## Rules
```
```
## Hooks
```
```
## Platform Gaps
```

Use a comparison table for Claude / Codex / Gemini when applicable.

默认模式：

JTBD替代方案
跨行业替代方案
间接竞品

针对Agent/模型/编排相关主题，该链路需要将领域内容统一规整为：

```
## Settings
```
```
## Rules
```
```
## Hooks
```
```
## 平台缺口
```

适用场景下使用表格对比Claude / Codex / Gemini。

Step 2: Synthesize and Save

步骤2：汇总并存储

Write

context.md

markdown

undefined

编写

context.md

：

markdown

undefined

Context: {project name}

Workflow Context

{when and where the problem shows up}

Affected Users

Role	Responsibility	Skill Level
{rows}

Role	Responsibility	Skill Level
{rows}

Current Workarounds

{numbered list with limitations}

Adjacent Problems

{lettered or bulleted list}

User Voices

{quotes with source links}


Write `solutions.md`:

```markdown

{quotes with source links}


编写`solutions.md`：

```markdown

Solution Landscape: {project name}

Solution List

Name	Approach	Strengths	Weaknesses	Notes
{deduplicated list}

Name	Approach	Strengths	Weaknesses	Notes
{deduplicated list}

What People Actually Use

{behavior summary}

Frequency Ranking

{most mentioned solutions}

Key Gaps

{structural gaps not covered today}

Contradictions

{marketed claims vs user reality}

Key Insight

{1 paragraph}


When the topic is platform or agent related, write `platform-map.md`:

```markdown

{1 paragraph}


当主题和平台或Agent相关时，编写`platform-map.md`：

```markdown

Platform Map: {project name}

Settings

Concern	Claude	Codex	Gemini	Common Layer
{rows}

Concern	Claude	Codex	Gemini	Common Layer
{rows}

Rules

Concern	Claude / OMC	Codex / OMX	Gemini / OHMG	Common Layer
{rows}

Concern	Claude / OMC	Codex / OMX	Gemini / OHMG	Common Layer
{rows}

Hooks

Lifecycle	Claude	Codex	Gemini	Common Layer
{rows}

Lifecycle	Claude	Codex	Gemini	Common Layer
{rows}

Platform Gaps

{where abstractions do not align cleanly}

undefined

{where abstractions do not align cleanly}

undefined

Step 3: Summarize for the User

步骤3：为用户生成摘要

Return a short summary:

markdown

undefined

返回简短摘要：

markdown

undefined

Survey complete: {slug}

Context

{1-2 sentence summary}
Main workaround: {most common workaround}

{1-2 sentence summary}
Main workaround: {most common workaround}

Solution Landscape

{N} solutions across {M} categories
Key insight: {one sentence}
Key gap: {one sentence}

{N} solutions across {M} categories
Key insight: {one sentence}
Key gap: {one sentence}

Files

```
.survey/{slug}/triage.md
```
```
.survey/{slug}/context.md
```
```
.survey/{slug}/solutions.md
```
```
.survey/{slug}/platform-map.md
```
# if created


Do not move into planning or implementation unless the user asks.

---

```
.survey/{slug}/triage.md
```
```
.survey/{slug}/context.md
```
```
.survey/{slug}/solutions.md
```
```
.survey/{slug}/platform-map.md
```
# if created


除非用户要求，否则不要进入规划或落地环节。

---

Quick Reference

快速参考

Action	Instruction
Start a survey	`survey <topic>`
Reuse existing results	Check `.survey/{slug}/` first
Search strategy	Search in English, write in the user's language
Parallel lanes	Context + Solutions + Behavior + Alternatives/Platform Map
Next step after survey	`/plan` , `jeo` , `ralph` , or implementation if the user asks

操作	说明
启动调研	`survey <topic>`
复用已有结果	优先检查 `.survey/{slug}/` 目录
搜索策略	英文搜索，使用用户语言输出
并行链路	上下文 + 解决方案 + 行为 + 替代方案/平台映射
调研后下一步	如用户要求，执行 `/plan` 、 `jeo` 、 `ralph` 或落地

Final Checklist

最终检查清单

```
what / who / why
```
are clear
Existing survey checked before overwrite
4 lanes executed in parallel
Source links included for quotes and non-obvious claims
```
context.md
```
saved
```
solutions.md
```
saved
```
platform-map.md
```
saved for agent/platform topics
Final user summary is factual, short, and recommendation-free

```
what / who / why
```
已明确
覆盖前已检查是否存在现有调研
4条链路已并行执行
引用和非显而易见的结论已附上来源链接
```
context.md
```
已保存
```
solutions.md
```
已保存
Agent/平台相关主题已保存
```
platform-map.md
```
最终用户摘要客观、简洁、无推荐倾向

survey

Original

Translation

survey - Cross-Platform Problem-Space Scan

survey - 跨平台问题域扫描

When to use this skill

何时使用此技能

Do not use this skill when

请勿在以下场景使用此技能

Output Package

输出包

Core Abstraction Layer

核心抽象层

Platform Adapter

平台适配器

Execution Policy

执行规则

Workflow

工作流

Step 0: Triage

步骤0：分诊

Triage

Triage

Step 1: Run 4 Parallel Lanes

步骤1：并行执行4条调研链路

Lane A: Context

链路A：上下文

Lane B: Solutions

链路B：解决方案

Lane C: Actual Behavior

链路C：实际使用行为

Lane D: Alternatives / Platform Map

链路D：替代方案 / 平台映射

Step 2: Synthesize and Save

步骤2：汇总并存储

Context: {project name}

Context: {project name}

Workflow Context

Workflow Context

Affected Users

Affected Users

Current Workarounds

Current Workarounds

Adjacent Problems

Adjacent Problems

User Voices

User Voices

Solution Landscape: {project name}

Solution Landscape: {project name}

Solution List

Solution List

Categories

Categories

What People Actually Use

What People Actually Use

Frequency Ranking

Frequency Ranking

Key Gaps

Key Gaps

Contradictions

Contradictions

Key Insight

Key Insight

Platform Map: {project name}

Platform Map: {project name}

Settings

Settings

Rules

Rules

Hooks

Hooks

Platform Gaps

Platform Gaps

Step 3: Summarize for the User

步骤3：为用户生成摘要

Survey complete: {slug}

Survey complete: {slug}

Context

Context

Solution Landscape