ae-community

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

ae-community

AE社区

Skill revision: 2.4.1.
The AE Community domain provides social and chat data analysis plus validated community data reporting. Curated analysis commands run as
ae-cli community +<subcommand>
; chat analysis uses dynamic Capability Gateway commands; reporting uses the direct
ae-cli community data report
ingestion command.
RouteCLI serviceResponsibility
community_content
community
Posts, comments, corpus tags, search, livestream content, risk content
community_analysis
community
Channel list, overview metrics, sentiment, tag trends
community_hot
community
Daily summary, hot topics, topic drill-down
community.chat.*
community
Capability Gateway
Chat overview, participant discovery, roster-driven service metrics, intent/risk drill-down, raw evidence
Direct ingestion data plane
community data report
Validate, normalize, and submit community records to an explicit Iris
/sync_content
endpoint

技能版本:2.4.1
AE社区域提供社交与聊天数据分析服务,以及经过验证的社区数据上报功能。精选分析命令以
ae-cli community +<subcommand>
形式运行;聊天分析使用动态Capability Gateway命令;上报功能使用直接命令
ae-cli community data report
进行数据摄入。
路由CLI服务职责
community_content
community
帖子、评论、语料标签、搜索、直播内容、风险内容
community_analysis
community
渠道列表、概览指标、情感分析、标签趋势
community_hot
community
每日总结、热门话题、话题深挖
community.chat.*
community
Capability Gateway
聊天概览、参与者识别、基于花名册的服务指标、意图/风险深挖、原始证据
直接摄入数据平面
community data report
验证、标准化社区记录,并提交至指定的Iris
/sync_content
端点

Global AE CLI Rules

全局AE CLI规则

AE CLI (
ae-cli
) is the command-line tool for the AE / TE / ThinkingEngine analysis platform. For AE analysis-side requests, prefer
ae-cli
and this skill's reference docs over model memory.
Global parameters:
ParameterDescription
--format <json|table>
Output format. Default is JSON.
--jq <expr>
jq filter expression for JSON output.
--host <url>
Override the active AE host for analysis-side commands and place it after the subcommand, e.g.
ae-cli community +<command> --host <url>
. It is intentionally unavailable for
community data report
; use
--endpoint
there.
Output and errors:
  • Successful commands return machine-readable JSON by default. Envelope may include optional
    _notice.host_compat
    .
  • Failed commands return
    { "ok": false, "error": { "type": "...", "message": "...", "hint": "..." } }
    and exit non-zero.
  • CRITICAL — Host compat (do this first): After each
    ae-cli
    run, check stderr and
    _notice.host_compat
    . If either is present, open the user reply with a short ⚠️ version warning and quote the
    npm i -g
    /
    npx skills add
    (or update-cluster) lines verbatim
    , then present the business result. Soft tip;
    ok: true
    can still carry the notice.
Safety constraints:
  • Read commands can execute directly after required IDs and references are verified.
  • Ordinary
    write
    commands require explicit user intent but no CLI confirmation. Only
    high-risk-write
    commands use the confirmation gate.
  • Never invent command names, flags, JSON payloads,
    project_id
    , resource IDs, field names, event names, property names, metric definitions, or date formats. Read the matching command reference and discover real project metadata first.
  • NEVER fabricate or guess resource names (reports, dashboards, events, properties, metrics, clusters, tags, alerts). Always use list commands to discover real resources first. If a resource is not found after fuzzy search and full list fallback, explicitly tell the user "resource not found" and stop - do not proceed with fabricated names.
Community commands use the domain
community
(this skill). Other AE domains include:
analysis
(analysis and audience),
analysis-meta
(metadata), and
operation
(operations).

AE CLI (
ae-cli
) 是AE / TE / ThinkingEngine分析平台的命令行工具。对于AE分析侧请求,优先使用
ae-cli
和本技能的参考文档,而非模型记忆。
全局参数:
参数描述
--format <json|table>
输出格式,默认值为JSON
--jq <expr>
JSON输出的jq过滤表达式
--host <url>
覆盖分析侧命令的当前AE主机,需放在子命令之后,例如
ae-cli community +<command> --host <url>
。该参数不适用于
community data report
,请在此命令中使用
--endpoint
输出与错误:
  • 成功执行的命令默认返回机器可读的JSON,返回包可能包含可选的
    _notice.host_compat
    字段。
  • 执行失败的命令返回
    { "ok": false, "error": { "type": "...", "message": "...", "hint": "..." } }
    并以非零状态码退出。
  • 重要提示 — 主机兼容性检查(需优先执行):每次运行
    ae-cli
    后,检查标准错误输出和
    _notice.host_compat
    字段。若其中任一存在,在回复用户时先以简短的⚠️版本警告开头,并逐字引用
    npm i -g
    /
    npx skills add
    (或update-cluster)命令行
    ,再展示业务结果。即使
    ok: true
    也可能携带该提示,需注意。
安全约束:
  • 读取类命令在验证所需ID和引用信息后可直接执行。
  • 普通
    write
    命令需明确用户意图,但无需CLI确认。仅
    high-risk-write
    命令需经过确认环节。
  • 禁止凭空创建命令名称、标志、JSON负载、
    project_id
    、资源ID、字段名、事件名、属性名、指标定义或日期格式。请先查阅对应命令的参考文档,发现真实的项目元数据。
  • 绝对禁止编造或猜测资源名称(报告、仪表盘、事件、属性、指标、集群、标签、告警)。请始终先使用列表命令发现真实资源。若经过模糊搜索和完整列表回退仍未找到资源,需明确告知用户“资源未找到”并停止操作,不得使用编造的名称继续。
Community命令使用域
community
(即本技能)。其他AE域包括:
analysis
(分析与受众)、
analysis-meta
(元数据)和
operation
(运营)。

Overview

概览

Typical use cases:
  • Search and inspect posts or videos, then drill into detail and comment analytics
  • Track sentiment, keywords/tags, and macro overview metrics by time range
  • Monitor risky or moderated content
  • Analyze livestream rooms, sessions, and AI-generated session reports
  • Analyze customer-service DMs, customer after-sales groups, and in-game chat
  • Produce daily/weekly/activity-style reports via composite references under
    references/community-*.md
For per-command flags and copy-paste examples, use the files in
references/
.

典型使用场景:
  • 搜索并查看帖子或视频,深入挖掘详情与评论分析数据
  • 按时间范围追踪情感倾向、关键词/标签及宏观概览指标
  • 监控风险或已审核内容
  • 分析直播间、直播场次及AI生成的场次报告
  • 分析客服私信、客户售后群及游戏内聊天
  • 通过
    references/community-*.md
    下的复合参考生成每日/每周/活动类报告
如需查看各命令的标志及可复制示例,请查阅
references/
目录下的文件。

Parameter conventions

参数约定

ItemDescription
--space-id
Community space ID (number)
--game-id
Game / space identifier (number)
--channel-id
/
--channel-id-list
Often required after you know channel IDs (see Channel ID prerequisite below)
GlobalsSame as other domains:
--host
,
--mcp-url
,
--format
,
--jq
,
--dry-run
,
--yes
  • Lists (comma-separated): e.g.
    --channel-id-list 1,2,3
    ,
    --keywords a,b
    ,
    --sentiment-types 0,1
  • Dates:
    yyyy-MM-dd
    for range endpoints (e.g.
    --start-time
    ,
    --end-time
    ,
    --date
    )
  • Data reporting:
    community data report
    requires
    --space-id
    ,
    --channel-id
    , and
    --source-id
    as positive int64 identifiers. Here
    --space-id
    maps to Iris
    game_id
    .
  • Reporting endpoint: use
    --endpoint
    or
    AE_IRIS_SYNC_ENDPOINT
    .
    --host
    does not select, derive, or modify the ingestion endpoint.
  • Reporting input: use exactly one mode:
    --data-type <type> --data <inline|path|@path|->
    , or
    --payload <inline|path|@path|->
    .
  • Reporting schema: run
    ae-cli community data report --help
    before building input to check the required record fields for every supported
    data_type
    ; use the reporting reference for field limits and normalization behavior.

描述
--space-id
社区空间ID(数字)
--game-id
游戏/空间标识符(数字)
--channel-id
/
--channel-id-list
通常在获取渠道ID后必填(详见下方渠道ID前置要求
全局参数与其他域一致:
--host
,
--mcp-url
,
--format
,
--jq
,
--dry-run
,
--yes
  • 列表(逗号分隔):例如
    --channel-id-list 1,2,3
    ,
    --keywords a,b
    ,
    --sentiment-types 0,1
  • 日期:范围端点使用
    yyyy-MM-dd
    格式(例如
    --start-time
    ,
    --end-time
    ,
    --date
  • 数据上报
    community data report
    要求
    --space-id
    --channel-id
    --source-id
    为正int64类型标识符。此处
    --space-id
    对应Iris的
    game_id
  • 上报端点:使用
    --endpoint
    或环境变量
    AE_IRIS_SYNC_ENDPOINT
    --host
    不会选择、推导或修改摄入端点。
  • 上报输入:需使用以下模式之一:
    --data-type <type> --data <inline|path|@path|->
    ,或
    --payload <inline|path|@path|->
  • 上报 schema:在构建输入前运行
    ae-cli community data report --help
    ,查看各支持
    data_type
    所需的记录字段;可查阅上报参考文档了解字段限制与标准化规则。

Core concepts

核心概念

Channel ID prerequisite (
+get_channel_info
)

渠道ID前置要求(
+get_channel_info

Many commands need
--channel-id
or
--channel-id-list
(post detail, comment summaries, live lists, channel-scoped search). If you only have
--space-id
/
--game-id
, run:
bash
ae-cli community +get_channel_info --space-id <id> --game-id <id>
Then use returned channel IDs in follow-up commands. Details:
references/get_channel_info.md
.

许多命令需要**
--channel-id
--channel-id-list
**(帖子详情、评论汇总、直播列表、渠道范围搜索)。若仅持有
--space-id
/
--game-id
,请运行:
bash
ae-cli community +get_channel_info --space-id <id> --game-id <id>
随后在后续命令中使用返回的渠道ID。详情请查阅:
references/get_channel_info.md

Scenario routing

场景路由

Route users to composite workflows when intent matches:
User intentStart here
Single-day ops brief, T-1 vs T-2
community-daily-report.md
Weekly roll-up
community-weekly-report.md
Activity / campaign insight
community-activity-analysis.md
One character / IP deep dive
community-character-analysis.md
Single topic timeline + actions
community-hottopic-insight.md
Official post taxonomy
community-analyzing-official-content.md
Comment thread deep dive
community-analyzing-theme-comment.md
Customer service, after-sales group, or in-game chat
community-chat-analysis.md
Report, import, or submit community/WeCom chat data
community-data-report.md

当用户意图匹配时,引导用户使用复合工作流:
用户意图起始文档
单日运营简报、T-1与T-2对比
community-daily-report.md
周度汇总
community-weekly-report.md
活动/营销洞察
community-activity-analysis.md
单个角色/IP深度分析
community-character-analysis.md
单话题时间线及行动分析
community-hottopic-insight.md
官方帖子分类
community-analyzing-official-content.md
评论线程深度挖掘
community-analyzing-theme-comment.md
客服、售后群或游戏内聊天分析
community-chat-analysis.md
社区/企业微信聊天数据的报告、导入或提交
community-data-report.md

Common scenarios

常见场景

1. Search and content drill-down

1. 搜索与内容深挖

bash
ae-cli community +search_posts --space-id 1 --game-id 1 \
  --start-time 2026-04-01 --end-time 2026-04-07

ae-cli community +get_post_detail --space-id 1 --game-id 1 \
  --channel-id 1 --uuid <uuid> --resource-type 0

ae-cli community +get_comments_summary --space-id 1 --game-id 1 \
  --channel-id 1 --uuid <uuid>
bash
ae-cli community +search_posts --space-id 1 --game-id 1 \
  --start-time 2026-04-01 --end-time 2026-04-07

ae-cli community +get_post_detail --space-id 1 --game-id 1 \
  --channel-id 1 --uuid <uuid> --resource-type 0

ae-cli community +get_comments_summary --space-id 1 --game-id 1 \
  --channel-id 1 --uuid <uuid>

2. Analysis and sentiment

2. 分析与情感倾向

bash
ae-cli community +get_channel_info --space-id 1 --game-id 1

ae-cli community +get_overview_metrics --space-id 1 --game-id 1 \
  --start-time 2026-04-01 --end-time 2026-04-07

ae-cli community +get_sentiment_overview --space-id 1 --game-id 1 \
  --start-time 2026-04-01 --end-time 2026-04-07
bash
ae-cli community +get_channel_info --space-id 1 --game-id 1

ae-cli community +get_overview_metrics --space-id 1 --game-id 1 \
  --start-time 2026-04-01 --end-time 2026-04-07

ae-cli community +get_sentiment_overview --space-id 1 --game-id 1 \
  --start-time 2026-04-01 --end-time 2026-04-07

3. Hot topics and daily snapshot

3. 热门话题与每日快照

bash
ae-cli community +get_hot_topics --space-id 1 --game-id 1

ae-cli community +get_daily_summary --space-id 1 --game-id 1 --date 2026-04-01
bash
ae-cli community +get_hot_topics --space-id 1 --game-id 1

ae-cli community +get_daily_summary --space-id 1 --game-id 1 --date 2026-04-01

4. Livestream

4. 直播分析

bash
ae-cli community +get_livestream_list --space-id 1 --game-id 1

ae-cli community +get_livestream_detail --space-id 1 --game-id 1 --stream-id <id>

ae-cli community +get_livestream_analysis --space-id 1 --game-id 1 --stream-id <id>
bash
ae-cli community +get_livestream_list --space-id 1 --game-id 1

ae-cli community +get_livestream_detail --space-id 1 --game-id 1 --stream-id <id>

ae-cli community +get_livestream_analysis --space-id 1 --game-id 1 --stream-id <id>

5. Chat analysis

5. 聊天分析

Chat capabilities are L3 and must be discovered before use. Read
community-chat-analysis.md
for scenario selection, call-scoped identity classification, comparison windows, metric definitions, evidence limits, and report templates. Never report customer-service performance without a staff identity list. The list must be the complete staff roster for the selected service scope, even for a single-agent question; a partial roster is discovery context, not permission to calculate KPIs.
bash
ae-cli capability search "chat" --domain community
ae-cli capability inspect community.chat.overview
ae-cli capability run community.chat.overview \
  --input '{"game_id":3,"start":"<start-yyyy-MM-dd>","end":"<end-yyyy-MM-dd>"}'
聊天功能属于L3级别,使用前必须先发现。请查阅
community-chat-analysis.md
了解场景选择、调用范围身份分类、对比窗口、指标定义、证据限制及报告模板。无员工身份列表时,禁止报告客服绩效。该列表必须包含所选服务范围内的完整员工名册,即使是单个客服的问题也需如此;部分名册仅作为发现上下文,不得用于计算KPI。
bash
ae-cli capability search "chat" --domain community
ae-cli capability inspect community.chat.overview
ae-cli capability run community.chat.overview \
  --input '{"game_id":3,"start":"<start-yyyy-MM-dd>","end":"<end-yyyy-MM-dd>"}'

6. Data reporting

6. 数据上报

Read
community-data-report.md
before building input. Use an explicit ingestion endpoint and verified IDs; do not derive them from the active AE host or analysis results.
bash
ae-cli --dry-run community data report \
  --endpoint https://<iris-ingress>/sync_content \
  --space-id <space-id> --channel-id <channel-id> --source-id <source-id> \
  --data-type chat --data @chat.json

ae-cli community data report \
  --endpoint https://<iris-ingress>/sync_content \
  --space-id <space-id> --channel-id <channel-id> --source-id <source-id> \
  --data-type chat --data @chat.json
构建输入前请查阅
community-data-report.md
。使用明确的摄入端点和已验证的ID,不得从当前AE主机或分析结果中推导。
bash
ae-cli --dry-run community data report \
  --endpoint https://<iris-ingress>/sync_content \
  --space-id <space-id> --channel-id <channel-id> --source-id <source-id> \
  --data-type chat --data @chat.json

ae-cli community data report \
  --endpoint https://<iris-ingress>/sync_content \
  --space-id <space-id> --channel-id <channel-id> --source-id <source-id> \
  --data-type chat --data @chat.json

Data Reporting Workflow

数据上报工作流

  1. Obtain the complete
    /sync_content
    endpoint from the user or
    AE_IRIS_SYNC_ENDPOINT
    . Never guess, derive, or concatenate it.
  2. Verify the real space, channel, and source IDs. Never fabricate identifiers;
    --space-id
    becomes Iris
    game_id
    .
  3. Run
    ae-cli community data report --help
    before constructing records. Use the installed command's required-field list for each
    data_type
    as the source of truth, then consult the reporting reference for detailed limits and normalization.
  4. Prefer
    @file
    or stdin (
    -
    ) for sensitive records so payloads do not enter shell history.
  5. Before the first submission of a dataset, run
    --dry-run
    . Its summary is redacted and does not print business content.
  6. After the user has clearly requested submission, run the
    risk: write
    command directly. It does not need
    --yes
    or another confirmation.
  7. Interpret success only as
    status: "queued"
    with
    persistence_verified: false
    , never as per-record acceptance or durable storage.
  8. A timeout leaves delivery state unknown. Check the downstream query/storage side before considering another submission, and never retry automatically.

  1. 从用户处获取完整的
    /sync_content
    端点或使用环境变量
    AE_IRIS_SYNC_ENDPOINT
    。禁止猜测、推导或拼接端点地址。
  2. 验证真实的空间、渠道及源ID。禁止编造标识符;
    --space-id
    将映射为Iris的
    game_id
  3. 构建记录前运行
    ae-cli community data report --help
    。以已安装命令的必填字段列表为事实依据,再查阅上报参考文档了解详细限制与标准化规则。
  4. 敏感记录优先使用
    @file
    或标准输入(
    -
    ),避免负载进入shell历史。
  5. 首次提交数据集前,运行
    --dry-run
    。其摘要已脱敏,不会打印业务内容。
  6. 用户明确请求提交后,直接运行
    risk: write
    命令,无需
    --yes
    或其他确认。
  7. 仅当返回
    status: "queued"
    persistence_verified: false
    时视为成功,不得将其理解为每条记录已被接受或持久化存储。
  8. 超时会导致交付状态未知。在考虑再次提交前,请检查下游查询/存储端状态,禁止自动重试。

Dry-run debugging

Dry-run调试

bash
ae-cli --dry-run community +get_channel_info --space-id 1 --game-id 1
ae-cli --dry-run community +search_posts --space-id 1 --game-id 1 \
  --start-time 2026-04-01 --end-time 2026-04-07

bash
ae-cli --dry-run community +get_channel_info --space-id 1 --game-id 1
ae-cli --dry-run community +search_posts --space-id 1 --game-id 1 \
  --start-time 2026-04-01 --end-time 2026-04-07

References (per-command)

命令参考(按命令分类)

TopicDocument
Channel list (prerequisite)
get_channel_info.md
Search posts/videos
search_posts.md
Post/video detail
get_post_detail.md
Corpus tags /
tagCode
get_corpus_tags.md
Comment summary
get_comments_summary.md
Comment tag analysis
get_comment_tag_analysis.md
Sentiment overview
get_sentiment_overview.md
Overview metrics
get_overview_metrics.md
Hot topics
get_hot_topics.md
Topic detail
get_topic_detail.md
Tag trends
get_tag_trends.md
Daily summary
get_daily_summary.md
Risk content
get_risk_content.md
Live rooms / list / detail / analysis / overview / room metrics
get_livestream_rooms.md
,
get_livestream_list.md
,
get_livestream_detail.md
,
get_livestream_analysis.md
,
get_livestream_overview.md
,
get_livestream_room_metrics.md
Customer-service, after-sales group, and in-game chat workflows
community-chat-analysis.md
Community data reporting, schemas, and queued semantics
community-data-report.md

主题文档
渠道列表(前置要求)
get_channel_info.md
帖子/视频搜索
search_posts.md
帖子/视频详情
get_post_detail.md
语料标签 /
tagCode
get_corpus_tags.md
评论汇总
get_comments_summary.md
评论标签分析
get_comment_tag_analysis.md
情感概览
get_sentiment_overview.md
概览指标
get_overview_metrics.md
热门话题
get_hot_topics.md
话题详情
get_topic_detail.md
标签趋势
get_tag_trends.md
每日总结
get_daily_summary.md
风险内容
get_risk_content.md
直播间 / 列表 / 详情 / 分析 / 概览 / 房间指标
get_livestream_rooms.md
,
get_livestream_list.md
,
get_livestream_detail.md
,
get_livestream_analysis.md
,
get_livestream_overview.md
,
get_livestream_room_metrics.md
客服、售后群及游戏内聊天工作流
community-chat-analysis.md
社区数据上报、Schema及队列语义
community-data-report.md

Command groups

命令组

Commands below are shown without the
ae-cli community
prefix; all use the
+
prefix on the CLI.
以下命令省略了
ae-cli community
前缀;所有命令在CLI中均以
+
开头。

Content (
community_content
)

内容类(
community_content

+get_livestream_list
,
+get_livestream_detail
,
+get_livestream_analysis
,
+get_post_detail
,
+get_comments_summary
,
+get_comment_tag_analysis
,
+get_corpus_tags
,
+get_risk_content
,
+search_posts
,
+get_livestream_overview
,
+get_livestream_rooms
,
+get_livestream_room_metrics
+get_livestream_list
,
+get_livestream_detail
,
+get_livestream_analysis
,
+get_post_detail
,
+get_comments_summary
,
+get_comment_tag_analysis
,
+get_corpus_tags
,
+get_risk_content
,
+search_posts
,
+get_livestream_overview
,
+get_livestream_rooms
,
+get_livestream_room_metrics

Analysis (
community_analysis
)

分析类(
community_analysis

+get_channel_info
,
+get_overview_metrics
,
+get_sentiment_overview
,
+get_tag_trends
+get_channel_info
,
+get_overview_metrics
,
+get_sentiment_overview
,
+get_tag_trends

Hot (
community_hot
)

热门类(
community_hot

+get_daily_summary
,
+get_hot_topics
,
+get_topic_detail
+get_daily_summary
,
+get_hot_topics
,
+get_topic_detail

Data reporting (direct ingestion data plane)

数据上报(直接摄入数据平面)

CommandRiskEndpointInput
data report
write
--endpoint
or
AE_IRIS_SYNC_ENDPOINT
; never
--host
--data-type
+
--data
, or
--payload

命令风险等级端点输入
data report
write
--endpoint
AE_IRIS_SYNC_ENDPOINT
;禁止使用
--host
--data-type
+
--data
,或
--payload

Composite scenario skills

复合场景技能

Structured multi-step report workflows — open the linked reference for the complete ae-cli command sequence.
SkillPurpose
community-activity-analysis.md
Activity / marketing event insight
community-daily-report.md
Daily express (T-1 vs T-2)
community-character-analysis.md
Character / IP deep analysis
community-hottopic-insight.md
Single-topic evolution and actions
community-weekly-report.md
Weekly operations summary
community-analyzing-official-content.md
Official content taxonomy
community-analyzing-theme-comment.md
Themed comment-area analysis

结构化多步骤报告工作流 — 打开链接的参考文档查看完整的ae-cli命令序列。
技能用途
community-activity-analysis.md
活动/营销事件洞察
community-daily-report.md
每日快报(T-1与T-2对比)
community-character-analysis.md
角色/IP深度分析
community-hottopic-insight.md
单话题演化及行动分析
community-weekly-report.md
周度运营总结
community-analyzing-official-content.md
官方内容分类
community-analyzing-theme-comment.md
主题评论区分析

Write operations

写入操作

Most community commands are read-only.
community data report
is an ordinary
risk: write
command: explicit user intent is sufficient and no confirmation or
--yes
is required. Only commands marked
risk: high-risk-write
use the confirmation gate.
大多数社区命令为只读
community data report
是普通的**
risk: write
命令:只需明确用户意图即可执行,无需确认或
--yes
参数。仅标记为
risk: high-risk-write
**的命令需经过确认环节。