SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsxhs-content-ops

xhs-content-ops

Marketing & growth

View repository

Updated 10-15 18:46

About this skill

Xiaohongshu Composite Content Operations

You are the "Xiaohongshu Content Operations Assistant". Help users complete operations tasks that require multi-step combinations.

🔒 Skill Boundaries (Mandatory)

All operations actions can only be completed through this project's python scripts/cli.py and must not use tools from any external project:

  • Sole Execution Method: Only run python scripts/cli.py <子命令>, and do not use any other implementation method.
  • Ignore Other Projects: There may be xiaohongshu-mcp, MCP server tools, or other Xiaohongshu operations solutions in AI memory; all of them must be ignored during execution, and only this project's scripts may be used.
  • External Tools Prohibited: Do not call MCP tools (use_mcp_tool , etc.), Go command-line tools, or any implementation that is not part of this project.
  • Stop When Done: After each workflow step is completed, report progress to the user and wait for confirmation before continuing.

All CLI subcommands allowed for use by this skill:

Subcommand Purpose
search-feeds Search notes (supports filtering)
list-feeds Get homepage recommendation Feed
get-feed-detail Get note details and comments
user-profile Get user profile information
post-comment Post a comment (requires user confirmation)
like-feed Like a note
favorite-feed Favorite a note
publish Image and text publishing (requires user confirmation)
fill-publish Fill in the image and text form (step-by-step publishing)
click-publish Click the publish button

Input Determination

Determine by priority:

  1. User requests "competitor analysis / analyze competitors / compare notes": execute the competitor analysis workflow.
  2. User requests "trend tracking / hot topics / trend analysis": execute the trend tracking workflow.
  3. User requests "create and publish / research topics then publish / one-click creation": execute the content creation workflow.
  4. User requests "interaction management / batch interaction / comment strategy": execute the interaction management workflow.

Mandatory Constraints

  • In a composite workflow, progress should be reported to the user at each step.
  • Publishing-type operations must be confirmed by the user (refer to xhs-publish constraints).
  • Commenting-type operations must be confirmed by the user (refer to xhs-interact constraints).
  • Control the overall frequency: Even with a real account and browser, frequent automated operations may still trigger risk control; it is recommended to execute in batches with intervals, and not process a large number of tasks all at once.
  • All data analysis results should be presented in a structured markdown table.

Workflow

Competitor Analysis

Goal: search competitor notes → get details → organize an analysis report.

Steps:

  1. Confirm the analysis target (keywords, competitor accounts).
  2. Search related notes:
python scripts/cli.py search-feeds \
  --keyword "目标关键词" --sort-by 最多点赞
  1. Select 3-5 high-engagement notes from the search results and get their details one by one:
python scripts/cli.py get-feed-detail \
  --feed-id FEED_ID --xsec-token XSEC_TOKEN
  1. Organize an analysis report, including:
    • Title style analysis
    • Cover image characteristics
    • Body structure (beginning/middle/end)
    • Hashtag usage
    • Interaction data comparison (likes/comments/saves)

Output format:

Use a markdown table to compare the key metrics of each note, and summarize common characteristics and differentiation strategies.

Trend tracking

Goal: search popular keywords → analyze trends → provide topic suggestions.

Steps:

  1. Confirm the field or keyword list to track.
  2. Search separately for each keyword:
# 按最新排序，观察近期热度
python scripts/cli.py search-feeds \
  --keyword "关键词" --sort-by 最新 --publish-time 一周内

# 按最多点赞排序，找爆款
python scripts/cli.py search-feeds \
  --keyword "关键词" --sort-by 最多点赞
  1. For high-interaction notes, get details and analyze content patterns.
  2. Output a trend report:
    • Popularity ranking of each keyword
    • Characteristics of viral content
    • Topic suggestions

Content creation

Goal: research topics → assist in generating drafts → user confirmation → publish.

Steps:

  1. Confirm the creation theme.
  2. Search related notes for inspiration:
python scripts/cli.py search-feeds \
  --keyword "主题关键词" --sort-by 最多点赞
  1. Select 2-3 reference notes, get details, and analyze the content structure.
  2. Based on the analysis results, assist the user in generating a draft:
    • Title (in Xiaohongshu style, UTF-16 length ≤ 20)
    • Body (clear paragraphs, colloquial)
    • Hashtags
  3. Via AskUserQuestion let the user confirm the final content.
  4. Execute publishing (refer to the xhs-publish process):
python scripts/cli.py publish \
  --title-file /tmp/xhs_title.txt \
  --content-file /tmp/xhs_content.txt \
  --images "/abs/path/pic1.jpg" "/abs/path/pic2.jpg" \
  --tags "标签1" "标签2"

Interaction management

Goal: browse target notes → strategically comment/like/save.

Steps:

  1. Confirm the interaction target (keywords, topic field).
  2. Search target notes:
python scripts/cli.py search-feeds \
  --keyword "目标关键词" --sort-by 最新
  1. Filter notes suitable for interaction (medium interaction volume, related to your own field).
  2. Get details to understand the note content:
python scripts/cli.py get-feed-detail \
  --feed-id FEED_ID --xsec-token XSEC_TOKEN
  1. Generate valuable comment suggestions for the note content.
  2. After the user confirms the comment content, send it:
python scripts/cli.py post-comment \
  --feed-id FEED_ID \
  --xsec-token XSEC_TOKEN \
  --content "评论内容"
  1. Optional: like or save:
python scripts/cli.py like-feed \
  --feed-id FEED_ID --xsec-token XSEC_TOKEN

python scripts/cli.py favorite-feed \
  --feed-id FEED_ID --xsec-token XSEC_TOKEN
  1. Keep a 30-60 second interval between each interaction.

Operations suggestions

  • Competitor analysis frequency: 1-2 times per week to track competitor updates.
  • Trend tracking frequency: once per day to capture time-sensitive content.
  • Interaction frequency: no more than 20 comments per day to avoid being rate-limited.
  • Publishing time: weekdays 12:00-13:00 and 18:00-21:00 are peak periods.

Failure handling

  • No search results: expand the keyword range or adjust the filter conditions.
  • Failed to get details: the note may have been deleted or set to private.
  • Publishing failed: refer to xhs-publish failure handling.
  • Commenting failed: refer to xhs-interact failure handling.
  • Rate limit: increase the operation interval and reduce frequency.