@thinkingai/ae-cli 1.0.1 → 1.0.15

package/skills/ae-community/references/community-analyzing-official-content.md

@@ -0,0 +1,71 @@
+# ae-community community-analyzing-official-content
+
+
+Official content analysis: Analyze recently published official content for a specified game in the community module, then classify and summarize it using the predefined categories.
+
+Trigger scenario: Use this skill when the user wants to know the official release content of the specified game in the near future.
+
+## Analysis process
+
+1. **Confirm analysis time**: Get the start date and end date (recommended not to exceed 30 days)
+2. **Query official content**: Call `+search_posts` and set the `official: true` parameter
+3. **Content Classification Analysis**: Classified by four categories: game announcements, community activities, linkages, and promotional materials
+4. **Formatted output**: Generate a structured official content analysis report
+
+## Execution process
+
+**Step 1: Confirm analysis time**
+- **If the user has specified the analysis time**: Record the time range (start time, end time) and enter step 2
+- **If the user does not specify the analysis time**: Inform the user to provide the following information before proceeding:
+- Start date of analysis
+- The end date of the analysis
+- ⚠️ The time range is recommended to be no more than 30 days to ensure query efficiency and content readability
+
+**Step 2: Check official content**
+Use the `+search_posts` tool to query official published content within a specified time range.
+- Calling parameters: `gameId`, `startTime`, `endTime`, `official: true`, `pagerHeader`
+- Focus on recording the total number of topics, channel distribution and timestamp of each post
+
+**Step 3: Content Classification and Analysis**
+Classification analysis according to the following four categories
+
+## Content classification criteria
+
+| Category | Definition | Information to be extracted |
+|------|------|----------------|
+| **Game Announcement** | Announcement and introduction of new game content such as new versions and new activities | Activity/version/new card pool content, game elements, duration (resident activities return to "Resident") |
+| **Community Activities** | Activities that promote players to post, reply, and create in the community, usually with physical rewards or community titles | Publishing platform, activity requirements, duration, and reward content |
+| **Linkage** | Announcement of linkage activities outside the game | Linkage brand/IP, linkage time, linkage form (in-game linkage ownership game announcement) |
+| **Promotional Materials** | General promotional materials (pictures, comics, character quotes, etc.) | Related characters/content, material form |
+
+## Cross-platform merge rules
+
+- **Game announcements, linkages, and promotional materials**: If the same content is released on multiple platforms and the content is consistent, merge it into one, and indicate "multi-platform release" in the summary
+- **Community Activities**: Each platform is listed separately and is not merged (because the activity rules of different platforms may be different)
+
+## Output structure
+
+### 1. Analysis summary
+- **Game**: Game name
+- **Analysis time**: start date - end date
+- **TOTAL OFFICIAL CONTENT**: Total quantity
+
+### 2. Game Announcement
+Contents list (sorted by time)
+
+### 3. Community activities
+Content list (sorted by platform and time)
+
+### 4. Linkage
+Contents list (sorted by time)
+
+### 5. Promotional materials
+Contents list (sorted by time)
+
+## Example
+
+```bash
+# User input example
+"Analyze the official releases of the past week"
+"Help me sort out this month's official announcements"
+```

package/skills/ae-community/references/community-analyzing-theme-comment.md

@@ -0,0 +1,123 @@
+# ae-community community-analyzing-theme-comment
+
+
+In-depth analysis of topic comment areas: Conduct in-depth analysis of the comment areas of specified posts or videos, and generate an in-depth analysis report including comment trends, opinion distribution, and summary.
+
+Trigger scenario: Use this skill when users need to conduct in-depth analysis of the comment area of ​​a specified topic (post or video).
+
+## Analysis process
+
+1. **Identify target post/video**: Get UUID, channelId and resourceType, or search via `+search_posts`
+2. **Get comment area data**: Call `+get_post_detail` to obtain the target content details and comment area
+3. **Get the complete comment area in paging**: loop through all comments and eliminate meaningless content such as irrigation and pure expressions.
+4. **In-depth analysis**:
+- Comment trend analysis (time trend, sentiment distribution trend)
+- Opinion analysis (extracting positive/negative opinions and representative comments)
+- Summary analysis (market data, opinion analysis, ecological analysis)
+
+## Execution process
+
+**Step 1: Identify Target Posts/Videos**
+- Check if the user has explicitly specified the post or video to be analyzed (UUID, channelId, resourceType)
+- If the user has provided the above information, jump directly to step 2
+- If the user does not specify a target, the `+search_posts` tool needs to be used to search for suitable posts
+
+**Step 2: Get comment area data**
+- Use the `+get_post_detail` tool to get the details and comments section of the target content
+- Get the complete comment area in pagination (pageSize recommended is 100)
+- Check the number of comments and the hasMore field in the returned results
+- If hasMore is true, continue calling to get the next page
+
+**Comment filtering rules**:
+When obtaining and storing comments, the following content that has no analytical significance needs to be eliminated:
+- **Spoiled comments**: Repeated posting of the same or similar content, content that swipes the screen
+- **Pure emoticons/symbols**: Contains only emoticons and symbol combinations (such as "???", "!!!")
+- **No substance**: Comments with less than 3 characters
+- **System Message**: Official automatically generated message
+
+**Step 3: In-depth analysis**
+
+**3.1 Comment Trend Analysis**
+- Comment time trend: statistics on the time distribution of comments published, summarized by day
+- Sentiment distribution trend: Statistics on changes in the proportion of positive, neutral, and negative comments by day
+
+**3.2 Viewpoint analysis**
+- Text clustering and topic extraction of all valid comments
+- Identify recurring keywords and phrases
+- Merge semantically similar views
+- Differentiate between positive and negative viewpoints
+- Each opinion includes: opinion title, opinion description, number of matching comments, representative comments (up to 10)
+- **Handling Opposing Viewpoints**: Allow diametrically opposed positive and negative views on the same thing to exist, and do not merge opposing views.
+
+**3.3 Summary analysis**
+- Summary of market data: total number of comments, overall sentiment distribution, peak comment time
+- Summary of opinion analysis: main positive opinions, main negative opinions, points of conflict of opinions, core needs of players
+- Ecological analysis of the comment area: overall atmosphere, relevance of comments and content, core user group characteristics, potential risks and opportunities
+
+## Output structure (must be complete)
+
+### 1. Basic information
+- **Post/Video Title**: Title content
+- **Source Channel**: Channel name
+- **Published**: Release date
+- **Analysis Time Range**: The time period for analysis
+- **Number of valid comments**: The number after excluding invalid comments
+
+### 2. Comment trends
+
+**Time Trend**
+
+| Date | Number of comments | Percentage |
+|------|--------|------|
+| YYYY-MM-DD | Quantity | X% |
+
+**Emotion Distribution**
+
+| Date | Positive | Neutral | Negative |
+|------|------|------|------|
+| YYYY-MM-DD | X% | X% | X% |
+
+### 3. Viewpoint analysis
+
+**Positive View**
+
+**Viewpoint 1: [Viewpoint Title]**
+- **Viewpoint Description**: [Detailed Description]
+- **Number of matching comments**: X
+- **Representative comments**:
+- "[Comment 1]"
+- "[Comment 2]"
+
+**Negative opinions (can be multiple)**
+
+**Viewpoint 1: [Viewpoint Title]**
+- **Viewpoint Description**: [Detailed Description]
+- **Number of matching comments**: X
+- **Representative comments**:
+- "[Comment 1]"
+- "[Comment 2]"
+
+### 4. Summary
+
+**Broad market data summary**:
+- Total number of comments, overall sentiment distribution, peak comment time
+
+**Summary of opinion analysis**:
+- Mainly positive points
+- Mainly negative points
+- Points of conflict of opinions
+- Players’ core needs
+
+**Ecological Analysis and Suggestions**:
+- Overall atmosphere
+- Relevance of comments and content
+- Characteristics of core user groups
+-Potential risks and opportunities
+
+## Example
+
+```bash
+# User input example
+"Analyze the comment area of ​​this post"
+"Help me deeply analyze the user feedback of this video"
+```

package/skills/ae-community/references/community-character-analysis.md

@@ -0,0 +1,70 @@
+# ae-community community-character-analysis
+
+
+Role-specific in-depth analysis: In-depth diagnosis for a single role, instead of regular daily/weekly reports, the "Role-specific in-depth analysis report" is output.
+
+Trigger: Use this when the user asks for "in-depth analysis of a certain character", "character sentiment insight", "deep-dive analysis of of a certain character's discussion", and "character analysis".
+
+## Analysis process
+
+1. **`+get_sentiment_overview`**: Get the core word cloud of the character under positive and negative discussions to set the tone of the current overall reputation
+2. **`+get_hot_topics`**: Confirm whether the character has formed a hot topic in the community
+3. **`+search_posts`**: Search for recent hot posts using "character name + core controversial words"
+4. **`+get_post_detail` & `+get_comments_summary`**: Extract the core views of the post and emotional feedback in the comment area
+
+## Entity extraction and deduction rules
+
+- [Core Analysis Role] must be extracted from user input (such as "Role", "Role A")
+- If the user doesn't say anything, please clearly ask "Which character do you want to analyze in depth?"
+- If the user does not specify a time, **automatically push forward 7-14 days from the current system time as the query period**
+
+## Core Constraints
+
+- **Reject fake claims**: Must explain "why" and give evidence of posts/comments.
+- **Strictly distinguish between early warning and risk control**:
+- Alerts: experience risks (mechanics, numerical values, plot, art, performance)
+-Risk Control: risk of violation (causing war, illegal production, leakage, rumors)
+
+## Output structure
+
+### 1. Character’s current ecology and community impression
+Use a very insightful paragraph to summarize the character’s current true position in the player’s mind.
+
+### 2. Discussion popularity and emotional portrait matrix
+
+| Dimensions | Data/Description |
+|------|----------|
+| Emotional fundamentals | Positive/neutral/negative ratio |
+| Main forum for sentiment | Main discussion channel |
+| High frequency word co-occurrence | Core keywords |
+
+### 3. In-depth deep-dive analysis of of players’ core needs and focus
+
+**✨ Core Values ​​and Highlight Experience**
+- **Extraction of player voices**: [Summary]
+- **Typical original voice/support case**: "[Real comments]"
+
+**🧨 Analysis of core pain points**
+- **Dismantling of deep demands**: [Analysis]
+- **Typical original voice/support case**: "[Real comments]"
+
+### 4. Operation strategy
+- **Public Opinion Direction Guidance**: Specific Suggestions
+- **Version/Optimization Forward Planning**: Direction for improvement
+
+### 5. Warning content
+
+**⚠️ Warning content**
+
+| Danger level | Warning triggers | Community spread | Core performance | Suggested follow-up actions |
+|---------|-----------|-----------|---------|-------------|
+| High/medium/low | Specific problems | Scope of impact | Specific performance | Handling suggestions |
+
+## Example
+
+```bash
+# User input example
+"A deep analysis of the role"
+"Help me break down the discussion of character A"
+"Analyze the sentiment of XX character"
+```

package/skills/ae-community/references/community-daily-report.md

@@ -0,0 +1,84 @@
+# ae-community community-daily-report
+
+
+Daily brief: Generate a concise "User Operations Daily Brief" covering daily macro trends, breaking sentiment signals, and safety/compliance risks, with T-1 vs T-2 comparison.
+
+Trigger: Use this when the user asks for "generate daily report", "yesterday's battle report" or "daily sentiment summary".
+
+## Roles and Goals
+
+You are the "User Operations Director + Public Opinion Monitoring Expert". The core task is to quickly answer three things:
+1) Whether the overall trend on the target date rose or fell relative to the previous day; 2) What is the most important focus of sentiment on the day; 3) Are there any risks that need to be dealt with immediately?
+
+## Time deduction and speech rules
+
+1. **The user clearly specifies the date** (for example: "Publish the daily report on March 17"):
+- The target date is the specified date, and the comparison date is automatically calculated as the previous day.
+- **Red line of speech**: In the text of the report, relative time pronouns such as "today", "yesterday" and "the day before yesterday" are absolutely prohibited**, and specific dates or objective pronouns must be used (such as: "Surge in volume on that day", "Compared to the previous day")
+2. **The user did not explicitly specify the date** (such as only saying "generate daily report"):
+- Automatically use yesterday as the target day (T-1) and the day before yesterday as the comparison day (T-2)
+- Allows the use of relative terms such as "yesterday/today's highlights"
+
+## Required tool chain
+
+1. `+get_overview_metrics` (called twice: T-1 and T-2)
+2. `+get_sentiment_overview` (target day sentiment distribution)
+3. `+get_daily_summary` (target day event summary)
+4. `+search_posts` (locating core hot posts)
+5. `+get_post_detail` + `+get_comments_summary` (extract the real original sound)
+6. `+get_risk_content` (compliance risk)
+
+## Core Constraints
+
+- **Minimalism, rejecting long forms**: focus on describing "incremental information" and "sudden anomalies"
+- **Absolute isolation of early warning and risk control**: Product bugs, UI complaints, and event feedback are classified as "Business Experience"; illegal products, politics, pornography, gambling and drugs, and illegal advertising are written into "Compliance Risk Control"
+- **The original voice of the user is absolutely authentic**: it must be 100% derived from real text, **It is absolutely prohibited to fabricate or conjecture what the user said**
+
+## Output structure
+
+### 1. Core Overview
+- **Summary Overview**: Summarize the core events of the day in one sentence
+- **Data Overview**: Month-on-month changes in key indicators
+- **Hot words of the day**: high-frequency keywords
+
+### 2. Single-day core dashboard
+
+| Indicator categories | Data | Month-on-month changes |
+|---------|------|---------|
+| Total sound volume of the market | Specific value | ↑/↓ X% |
+| Sentiment of the day | Positive/neutral/negative proportion | Changing trends |
+| Main volume position | Distribution of various channels | Channel comparison |
+
+### 3. Core Focus and User Insights
+
+**Core Focus**:
+- Focus 1: [Event Description]
+- **User Feedback**: [Feedback Summary]
+- **Typical original voice**: "[Real user comments]"
+
+**User Sentiment Summary**
+
+| Emotional Tendencies | Main Trigger Points | Possible Impact |
+|---------|-----------|-----------|
+| Positive/Negative/Neutral | Specific reasons | Impact analysis |
+
+### 4. Risk control tips and operational suggestions
+
+**Safety Compliance Risk Control**
+
+| Risk control type | Number of findings | Main performance | Disposal suggestions |
+|---------|---------|---------|---------|
+| Specific type | Quantity | Specific performance | Treatment suggestions |
+
+### 5. Operation suggestions and future node suggestions
+- short term advice
+- Mid- to long-term focus
+
+## Example
+
+```bash
+# User input example
+"Generate daily report"
+"Publish the daily report for March 17th"
+"Yesterday's Battle Report"
+```

package/skills/ae-community/references/community-hottopic-insight.md

@@ -0,0 +1,113 @@
+# ae-community community-hottopic-insight
+
+
+Topic analysis: Automatically collect corpus, intelligently identify industry attributes, and output a structured Topic Analysis that includes a core summary, an overview of sentiment and the context of events, core hot discussions, sentiment slices, social media channel insights, and operational recommendations.
+
+Triggering scenario: Triggered when the user requests "Analyze topic", "Generate topic analysis report" or "Topic analysis".
+
+# # Analysis process
+
+1. * * `+get_hot_topics` * *: Get topic information (topicId, startTime, endTime)
+2. * * `+search_posts` * *: Search related posts by topic ID, * * Focus on recording the time, total number and distribution of posts by channel * *
+3. * * `+get_post_detail` * *: Grab high-profile content details (up to 10)
+
+# # Entity and Time Rules
+
+- [Topic name] must be extracted from user input
+- If the user does not provide it, the user must ask the core analysis object
+- If the user does not specify a specific time, * * the current system time is automatically pushed forward by 7-14 days as the query cycle * *
+
+Core Requirements
+
+- * * Dynamic traceability authenticity * *: must be strongly dependent on the post's real publishing time
+- * * Evolutionary chains of "Time - Events - Topics - Emotions" must be clearly identified * *
+- In chronological order, extract "what happened at what time, what was mainly discussed at that time, what was the emotion"
+- If you can't catch the timestamp, please truthfully explain that "due to data limitations, it is impossible to generate an accurate timeline", and it is strictly forbidden to fabricate a false history of development
+
+# # Output structure
+
+* *⚠️ Mandatory: The report must be output in strict accordance with the structure of the following six parts, no parts may be omitted, and the order or format may not be changed. * *
+
+# # # I. Summary of Core Content
+- Event Overview: Summarize what everyone is talking about in one sentence
+- The evolution of sentiment: such as "experienced a sharp reversal from the positive expectation of the previous period to the collapse of the reputation of the factor value problem after the launch"
+
+# # # II. Overview of Public Opinion Data and Dynamic Evolution
+
+* * Quantitative📊 sentiment statistics * *:
+- Total number of current topics
+- Overview of the number of content in each channel
+- Overall Sentiment Ratio
+
+* * Trends in🔥 popularity * *: Describe popularity trends
+
+* * * Dynamic Public Opinion Evolution Vein (🔴Core must be itemized, not omitted) * *:
+- * * `[MM-DD]` | Phase 1: [Phase naming, e.g. prospective warm-up period - expecting to be full] * *
+- * * Trigger Node * *: [What happened at that time, ex: the official release of the live demo PV]
+- * * Core Focus * *: [What players are talking about, e.g., motion fluency, fine art modeling]
+- * * Emotional direction * *: [ex:🟢 extremely positive expectations, players are highly rated]
+- * * `[MM-DD]` | Phase 2: [Phase name, e.g. live/new story launch] * *
+- * * Trigger Node * *: [ex: Core mechanism was tampered with after update]
+- * * Core Focus * *: [ex: Accusation of official misinformation, request for refund of deposit]
+- * * Emotional direction * *🔴: [ex: Negative outburst]
+- * * `[MM-DD]` | Phase 3: [Phase Naming, e.g. Current Status/Official Response] * *
+- * * Trigger Node * *: [ex: official apology blue sticker description]
+- * * Core Focus * *: [ex: Is the compensation plan justified in a tug-of-war?]
+- * * Emotional direction * *: [ex:🟡 Negative emotions ease slightly, turn to wait and see for confirmation]
+
+* Note: The number of stages increases or decreases according to the actual discussion escalation process *
+
+# # # III. Summary of Core Hotspot Discussions
+Objectively distill the 2-3 core specific issues that are currently the loudest and most controversial, regardless of emotions
+
+# # # IV. Emotional Slicing and Opinion Analysis
+
+* *🔴 Negative Emotional Slice * *
+- * * Focus Issue * *: [Specific Issue]
+- * * High frequency word cloud * *: [keyword list]
+- * * Typical Player Soundtrack * *:
+- "[True Comment 1]"
+- "[True Comment 2]"
+
+* *🟡 Neutral Emotion Slice * *
+- * * Focus Issue * *: [Specific Issue]
+- * * High frequency word cloud * *: [keyword list]
+- * * Typical Player Soundtrack * *:
+- "[True Comment 1]"
+- "[True Comment 2]"
+
+* *🟢 Positive Emotional Slice * *
+- * * Focus Issue * *: [Specific Issue]
+- * * High frequency word cloud * *: [keyword list]
+- * * Typical Player Soundtrack * *:
+- "[True Comment 1]"
+- "[True Comment 2]"
+
+* *⚠️ Note: The player's soundtrack must use "" to quote authentic reviews, and fabrication is strictly forbidden. * *
+
+# # # V. Content insights across social media platforms
+Compare of detailed data from different channels and characteristics of sentiment
+
+# # # VI. Suggestions for Operation and Response from an Industry Perspective
+
+* *⚡ Emergency Intervention (Firefighting Strategies for Crisis Response) * *
+- Risk Assessment: [Specific Risks]
+- Suggested action: [Specific action]
+
+* 🚀 * Homeostasis (amplification strategy for operational activation) * *
+- Opportunity Point Identification: [Specific Opportunity]
+- Suggested Tactics: [Specific Tactics]
+
+# # User input example
+
+```bash
+"Analyze the topic of # new UI redesign #"
+"Generate the analysis report for the XX version of the comprehensive review topic"
+"Analyze XX topics for me"
+```
+
+# # Execute Checklist
+
+- Typical soundtracks must be traced back to real posts/comments.
+- Channel insights must reflect platform differences, not just data.
+- Suggestions are divided into “emergency intervention” and “homeopathic guidance”.

package/skills/ae-community/references/community-weekly-report.md

@@ -0,0 +1,84 @@
+# ae-community community-weekly-report
+
+
+Community Operation Weekly Summary: Summarize a week's data, focus on the "Daily Summary" to connect the core escalating discussion events of the week, and output a "Community Operations Weekly Summary Report."
+
+Trigger: Use this when the user asks for "generate weekly report", "community operation weekly report", "weekly summary" and "review of the past week".
+
+## Roles and Goals
+
+You are "Director of Community Operations + Senior Data Analyst". The goal is not to write a chronological narrative, but to restore the weekly evolution chain of "event-emotion-platform" and give executable suggestions.
+
+## Time deduction rules
+
+1. The user clearly gives the date: query strictly according to the user scope.
+2. The user does not provide a date: automatically retrieve the past 7 days (`endTime=yesterday`, `startTime=endTime-7d`).
+3. Don’t interrupt the process due to lack of time.
+
+## Required tool chain
+
+1. `+get_overview_metrics` (weekly total and channel distribution)
+2. `+get_daily_summary` (daily context, weekly report core input)
+3. `+get_sentiment_overview` (sentiment structure)
+4. `+get_comments_summary` (emotion changes on the comment side)
+5. `+get_risk_content` (compliance risk control)
+6. `+get_hot_topics` (hotspot assisted verification)
+
+## Output structure (must be complete)
+
+1. **Core summary of the report**: Setting the tone for this week + hot keywords
+2. **Overview indicator board**: total volume, sentiment distribution, channel matrix (table)
+3. **Core Events**: Extract 2-3 events and write down the escalation path and focus demands.
+4. **Platform Insights**: Discussion styles and core differences across different channels
+5. **Early Warning and Risk Control** (two independent tables)
+- Early warning: Bug/mechanism/plot/experience issues
+- Risk control: black/gray-market activity/advertising/sensitive violations/flamebait/content designed to provoke conflict, etc.
+6. **Action suggestions for next week**: Problem closed loop, distribution strategy, monitoring focus
+
+### 2. Overview of statistical indicators
+
+| Indicator categories | Data | Weekly |
+|---------|------|--------|
+| Total content of the market | Specific values ​​| ↑/↓ X% |
+| Overall sentiment distribution | Positive/neutral/negative proportion | Changing trends |
+| Channel volume distribution matrix | Data of each channel | Channel comparison |
+
+### 3. Insights into this week’s core events and sentiment context
+
+**Tracking of core sentiment events this week**:
+- **Big Event 1**: [Event Name]
+- **Fermentation context**: [Timeline review]
+- **Public Opinion Focus/Demand**: [Core Viewpoint]
+
+**User comments and emotional dynamic evolution**:
+- Sentiment trend analysis
+
+### 4. In-depth insights into each platform
+Horizontally compare the tone differences of different social media platforms
+
+### 5. Community early warning and safety risk control
+
+**⚠️ Early warning information**
+
+| Warning level | Warning trigger items | Community spread | Core performance | Suggested follow-up actions |
+|---------|-----------|-----------|---------|-------------|
+| High/medium/low | Specific problems | Scope of impact | Specific performance | Handling suggestions |
+
+**🛡️ Security compliance and risk control interception**
+
+| Risk control level | Violation type | Discovery channels | Violation facts | Disposal suggestions |
+|---------|---------|---------|-------------|---------|
+| Serious/General | Violation type | Channel name | Specific facts | Handling suggestions |
+
+### 6. Operation suggestions and planning for next week
+- short term advice
+- Focus on next week
+
+## Example
+
+```bash
+# User input example
+"Generate weekly report"
+"Last week's community operations weekly report"
+"Weekly Summary"
+```

package/skills/ae-community/references/get_channel_info.md

@@ -0,0 +1,20 @@
+# ae-community +get_channel_info
+
+
+Get the list of valid channels for the community space, including channel IDs and names. **This is the prerequisite step for most commands that require `--channel-id` / `--channel-id-list`: First get the real channel ID here, and then call `+search_posts`, `+get_post_detail`, `+get_comments_summary`, `+get_livestream_list`, etc. with parameters (subject to the reference of each command).
+
+Mapping command: `ae-cli community +get_channel_info`
+
+## Flags
+
+| Flag | Type | Required | Description |
+|------|------|------|------|
+| `--space-id` | number | yes | community space ID |
+| `--game-id` | number | yes | game/space ID |
+
+## Example
+
+```bash
+# Get channel list
+ae-cli community +get_channel_info --space-id 1 --game-id 1
+```

package/skills/ae-community/references/get_comment_tag_analysis.md

@@ -0,0 +1,29 @@
+# ae-community +get_comment_tag_analysis
+
+
+Comment tag analysis: Specify the tag code and return the count and time trend of each tag value.
+
+Mapping command: `ae-cli community +get_comment_tag_analysis`
+
+## Flags
+
+| Flag | Type | Required | Description |
+|------|------|------|------|
+| `--space-id` | number | yes | community space ID |
+| `--game-id` | number | yes | game/space ID |
+| `--channel-id` | number | yes | channel ID |
+| `--uuid` | string | yes | content UUID |
+| `--resource-type` | number | Yes | Resource type: `0` for posts, `1` for videos |
+| `--tag-code` | string | Yes | Tag code (obtain via `get_corpus_tags`) |
+| `--start-time` | string | No | Earliest comment publish date, format yyyy-MM-dd, default is the publishing time of the post |
+| `--end-time` | string | No | Latest comment publish date, format yyyy-MM-dd |
+
+## Example
+
+```bash
+# Analyze comment tags
+ae-cli community +get_comment_tag_analysis \
+  --space-id 1 --game-id 1 \
+  --channel-id 1 --uuid <uuid> \
+  --resource-type 0 --tag-code "sentiment"
+```

package/skills/ae-community/references/get_comments_summary.md

@@ -0,0 +1,32 @@
+# ae-community +get_comments_summary
+
+
+Get a summary of comment analysis for a post, including sentiment distribution and time trends. Only aggregate statistics are returned, no raw review list.
+
+Mapping command: `ae-cli community +get_comments_summary`
+
+## Flags
+
+| Flag | Type | Required | Description |
+|------|------|------|------|
+| `--space-id` | number | yes | community space ID |
+| `--game-id` | number | yes | game/space ID |
+| `--channel-id` | number | yes | channel ID |
+| `--uuid` | string | yes | content UUID |
+| `--start-time` | string | No | Earliest comment publish date, format yyyy-MM-dd, default is the publishing time of the post |
+| `--end-time` | string | No | Latest comment publish date, format yyyy-MM-dd |
+
+## Example
+
+```bash
+# Get comment summary
+ae-cli community +get_comments_summary \
+  --space-id 1 --game-id 1 \
+  --channel-id 1 --uuid <uuid>
+
+#Specify time range
+ae-cli community +get_comments_summary \
+  --space-id 1 --game-id 1 \
+  --channel-id 1 --uuid <uuid> \
+  --start-time 2024-01-01 --end-time 2024-01-07
+```

package/skills/ae-community/references/get_corpus_tags.md

@@ -0,0 +1,20 @@
+# ae-community +get_corpus_tags
+
+
+Query the list of available corpus tags for filtering.
+
+Mapping command: `ae-cli community +get_corpus_tags`
+
+## Flags
+
+| Flag | Type | Required | Description |
+|------|------|------|------|
+| `--space-id` | number | yes | community space ID |
+| `--game-id` | number | yes | game/space ID |
+
+## Example
+
+```bash
+# Get the tag list
+ae-cli community +get_corpus_tags --space-id 1 --game-id 1
+```

package/skills/ae-community/references/get_daily_summary.md

@@ -0,0 +1,22 @@
+# ae-community +get_daily_summary
+
+
+Community daily news for a given day: hot list rankings and selected opinions (positive/negative).
+
+Mapping command: `ae-cli community +get_daily_summary`
+
+## Flags
+
+| Flag | Type | Required | Description |
+|------|------|------|------|
+| `--space-id` | number | yes | community space ID |
+| `--game-id` | number | yes | game/space ID |
+| `--date` | string | Yes | Date, format yyyy-MM-dd |
+
+## Example
+
+```bash
+# Get daily report
+ae-cli community +get_daily_summary \
+  --space-id 1 --game-id 1 --date 2024-01-01
+```