ae-community
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chineseae-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 ; chat analysis uses dynamic Capability Gateway commands; reporting uses the direct ingestion command.
ae-cli community +<subcommand>ae-cli community data report| Route | CLI service | Responsibility |
|---|---|---|
| | Posts, comments, corpus tags, search, livestream content, risk content |
| | Channel list, overview metrics, sentiment, tag trends |
| | Daily summary, hot topics, topic drill-down |
| | Chat overview, participant discovery, roster-driven service metrics, intent/risk drill-down, raw evidence |
| Direct ingestion data plane | | Validate, normalize, and submit community records to an explicit Iris |
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 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 进行数据摄入。
ae-cli community +<subcommand>ae-cli community data report| 路由 | CLI服务 | 职责 |
|---|---|---|
| | 帖子、评论、语料标签、搜索、直播内容、风险内容 |
| | 渠道列表、概览指标、情感分析、标签趋势 |
| | 每日总结、热门话题、话题深挖 |
| | 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 | | 验证、标准化社区记录,并提交至指定的Iris |
Global AE CLI Rules
全局AE CLI规则
AE CLI () is the command-line tool for the AE / TE / ThinkingEngine analysis platform. For AE analysis-side requests, prefer and this skill's reference docs over model memory.
ae-cliae-cliGlobal parameters:
| Parameter | Description |
|---|---|
| Output format. Default is JSON. |
| jq filter expression for JSON output. |
| Override the active AE host for analysis-side commands and place it after the subcommand, e.g. |
Output and errors:
- Successful commands return machine-readable JSON by default. Envelope may include optional .
_notice.host_compat - Failed commands return and exit non-zero.
{ "ok": false, "error": { "type": "...", "message": "...", "hint": "..." } } - CRITICAL — Host compat (do this first): After each run, check stderr and
ae-cli. If either is present, open the user reply with a short ⚠️ version warning and quote the_notice.host_compat/npm i -g(or update-cluster) lines verbatim, then present the business result. Soft tip;npx skills addcan still carry the notice.ok: true
Safety constraints:
- Read commands can execute directly after required IDs and references are verified.
- Ordinary commands require explicit user intent but no CLI confirmation. Only
writecommands use the confirmation gate.high-risk-write - Never invent command names, flags, JSON payloads, , resource IDs, field names, event names, property names, metric definitions, or date formats. Read the matching command reference and discover real project metadata first.
project_id - 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 (this skill). Other AE domains include: (analysis and audience), (metadata), and (operations).
communityanalysisanalysis-metaoperationAE CLI () 是AE / TE / ThinkingEngine分析平台的命令行工具。对于AE分析侧请求,优先使用和本技能的参考文档,而非模型记忆。
ae-cliae-cli全局参数:
| 参数 | 描述 |
|---|---|
| 输出格式,默认值为JSON |
| JSON输出的jq过滤表达式 |
| 覆盖分析侧命令的当前AE主机,需放在子命令之后,例如 |
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字段。
_notice.host_compat - 执行失败的命令返回 并以非零状态码退出。
{ "ok": false, "error": { "type": "...", "message": "...", "hint": "..." } } - 重要提示 — 主机兼容性检查(需优先执行):每次运行后,检查标准错误输出和
ae-cli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_notice.host_compat/npm i -g(或update-cluster)命令行,再展示业务结果。即使npx skills add也可能携带该提示,需注意。ok: true
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。
- 普通命令需明确用户意图,但无需CLI确认。仅
write命令需经过确认环节。high-risk-write - 禁止凭空创建命令名称、标志、JSON负载、、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。
project_id - 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(即本技能)。其他AE域包括:(分析与受众)、(元数据)和(运营)。
communityanalysisanalysis-metaoperationOverview
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
- 通过下的复合参考生成每日/每周/活动类报告
references/community-*.md
如需查看各命令的标志及可复制示例,请查阅目录下的文件。
references/Parameter conventions
参数约定
| Item | Description |
|---|---|
| Community space ID (number) |
| Game / space identifier (number) |
| Often required after you know channel IDs (see Channel ID prerequisite below) |
| Globals | Same as other domains: |
- Lists (comma-separated): e.g. ,
--channel-id-list 1,2,3,--keywords a,b--sentiment-types 0,1 - Dates: for range endpoints (e.g.
yyyy-MM-dd,--start-time,--end-time)--date - Data reporting: requires
community data report,--space-id, and--channel-idas positive int64 identifiers. Here--source-idmaps to Iris--space-id.game_id - Reporting endpoint: use or
--endpoint.AE_IRIS_SYNC_ENDPOINTdoes not select, derive, or modify the ingestion endpoint.--host - Reporting input: use exactly one mode: , or
--data-type <type> --data <inline|path|@path|->.--payload <inline|path|@path|-> - Reporting schema: run before building input to check the required record fields for every supported
ae-cli community data report --help; use the reporting reference for field limits and normalization behavior.data_type
| 项 | 描述 |
|---|---|
| 社区空间ID(数字) |
| 游戏/空间标识符(数字) |
| 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: |
- 列表(逗号分隔):例如 ,
--channel-id-list 1,2,3,--keywords a,b--sentiment-types 0,1 - 日期:范围端点使用格式(例如
yyyy-MM-dd,--start-time,--end-time)--date - 数据上报:要求
community data report、--space-id和--channel-id为正int64类型标识符。此处--source-id对应Iris的--space-id。game_id - 上报端点:使用或环境变量
--endpoint。AE_IRIS_SYNC_ENDPOINT不会选择、推导或修改摄入端点。--host - 上报输入:需使用以下模式之一:,或
--data-type <type> --data <inline|path|@path|->。--payload <inline|path|@path|-> - 上报 schema:在构建输入前运行,查看各支持
ae-cli community data report --help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。data_type
Core concepts
核心概念
Channel ID prerequisite (+get_channel_info
)
+get_channel_info渠道ID前置要求(+get_channel_info
)
+get_channel_infoMany commands need or (post detail, comment summaries, live lists, channel-scoped search). If you only have / , run:
--channel-id--channel-id-list--space-id--game-idbash
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**或**(帖子详情、评论汇总、直播列表、渠道范围搜索)。若仅持有 / ,请运行:
--channel-id--channel-id-list--space-id--game-idbash
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.mdScenario routing
场景路由
Route users to composite workflows when intent matches:
| User intent | Start here |
|---|---|
| Single-day ops brief, T-1 vs T-2 | |
| Weekly roll-up | |
| Activity / campaign insight | |
| One character / IP deep dive | |
| Single topic timeline + actions | |
| Official post taxonomy | |
| Comment thread deep dive | |
| Customer service, after-sales group, or in-game chat | |
| Report, import, or submit community/WeCom chat data | |
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 | |
| 周度汇总 | |
| 活动/营销洞察 | |
| 单个角色/IP深度分析 | |
| 单话题时间线及行动分析 | |
| 官方帖子分类 | |
| 评论线程深度挖掘 | |
| 客服、售后群或游戏内聊天分析 | |
| 社区/企业微信聊天数据的报告、导入或提交 | |
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 2026-04-07bash
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 2026-04-073. 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 2026-04-01bash
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 2026-04-014. 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
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.
community-chat-analysis.mdbash
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。
community-chat-analysis.mdbash
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 before building input. Use an
explicit ingestion endpoint and verified IDs; do not derive them from the active AE host or analysis
results.
community-data-report.mdbash
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。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。
community-data-report.mdbash
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.jsonData Reporting Workflow
数据上报工作流
- Obtain the complete endpoint from the user or
/sync_content. Never guess, derive, or concatenate it.AE_IRIS_SYNC_ENDPOINT - Verify the real space, channel, and source IDs. Never fabricate identifiers; becomes Iris
--space-id.game_id - Run before constructing records. Use the installed command's required-field list for each
ae-cli community data report --helpas the source of truth, then consult the reporting reference for detailed limits and normalization.data_type - Prefer or stdin (
@file) for sensitive records so payloads do not enter shell history.- - Before the first submission of a dataset, run . Its summary is redacted and does not print business content.
--dry-run - After the user has clearly requested submission, run the command directly. It does not need
risk: writeor another confirmation.--yes - Interpret success only as with
status: "queued", never as per-record acceptance or durable storage.persistence_verified: false - A timeout leaves delivery state unknown. Check the downstream query/storage side before considering another submission, and never retry automatically.
- 从用户处获取完整的端点或使用环境变量
/sync_content。禁止猜测、推导或拼接端点地址。AE_IRIS_SYNC_ENDPOINT - 验证真实的空间、渠道及源ID。禁止编造标识符;将映射为Iris的
--space-id。game_id - 构建记录前运行。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。
ae-cli community data report --help - 敏感记录优先使用或标准输入(
@file),避免负载进入shell历史。- - 首次提交数据集前,运行。其摘要已脱敏,不会打印业务内容。
--dry-run - 用户明确请求提交后,直接运行命令,无需
risk: write或其他确认。--yes - 仅当返回且
status: "queued"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。persistence_verified: false - 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 2026-04-07bash
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 2026-04-07References (per-command)
命令参考(按命令分类)
| Topic | Document |
|---|---|
| Channel list (prerequisite) | |
| Search posts/videos | |
| Post/video detail | |
Corpus tags / | |
| Comment summary | |
| Comment tag analysis | |
| Sentiment overview | |
| Overview metrics | |
| Hot topics | |
| Topic detail | |
| Tag trends | |
| Daily summary | |
| Risk content | |
| Live rooms / list / detail / analysis / overview / room metrics | |
| Customer-service, after-sales group, and in-game chat workflows | |
| Community data reporting, schemas, and queued semantics | |
| 主题 | 文档 |
|---|---|
| 渠道列表(前置要求) | |
| 帖子/视频搜索 | |
| 帖子/视频详情 | |
语料标签 / | |
| 评论汇总 | |
| 评论标签分析 | |
| 情感概览 | |
| 概览指标 | |
| 热门话题 | |
| 话题详情 | |
| 标签趋势 | |
| 每日总结 | |
| 风险内容 | |
| 直播间 / 列表 / 详情 / 分析 / 概览 / 房间指标 | |
| 客服、售后群及游戏内聊天工作流 | |
| 社区数据上报、Schema及队列语义 | |
Command groups
命令组
Commands below are shown without the prefix; all use the prefix on the CLI.
ae-cli community+以下命令省略了前缀;所有命令在CLI中均以开头。
ae-cli community+Content (community_content
)
community_content内容类(community_content
)
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_metricsAnalysis (community_analysis
)
community_analysis分析类(community_analysis
)
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_trendsHot (community_hot
)
community_hot热门类(community_hot
)
community_hot+get_daily_summary+get_hot_topics+get_topic_detail+get_daily_summary+get_hot_topics+get_topic_detailData reporting (direct ingestion data plane)
数据上报(直接摄入数据平面)
| Command | Risk | Endpoint | Input |
|---|---|---|---|
| | | |
| 命令 | 风险等级 | 端点 | 输入 |
|---|---|---|---|
| | | |
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.
| Skill | Purpose |
|---|---|
| Activity / marketing event insight |
| Daily express (T-1 vs T-2) |
| Character / IP deep analysis |
| Single-topic evolution and actions |
| Weekly operations summary |
| Official content taxonomy |
| 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 |
|---|---|
| 活动/营销事件洞察 |
| 每日快报(T-1与T-2对比) |
| 角色/IP深度分析 |
| 单话题演化及行动分析 |
| 周度运营总结 |
| 官方内容分类 |
| 主题评论区分析 |
Write operations
写入操作
Most community commands are read-only. is an ordinary command: explicit user intent is sufficient and no confirmation or is required. Only commands marked use the confirmation gate.
community data reportrisk: write--yesrisk: high-risk-write大多数社区命令为只读。是普通的**命令:只需明确用户意图即可执行,无需确认或参数。仅标记为**的命令需经过确认环节。
community data reportrisk: write--yesrisk: high-risk-write