SkillAgentSearch skills...

xiaohongshu-search-full

Search Xiaohongshu (XHS / RedNote) notes by keyword with full field extraction including body text, topics/tags, image list URLs, video stream URL, publish timestamp, and all engagement stats (likes, collects, comments, shares).

Install / Use

npx skills add browser-act/skills --skill xiaohongshu-search-full

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

94/100

Supported Platforms

Universal

Our assessment of xiaohongshu-search-full

xiaohongshu-search-full scores 94/100 on our quality scale, 75th of 319 Customer Support skills we index (top 24%).

Its SKILL.md is 21 KB long, well organised into 21 sections with 3 code examples: a thorough specification that gives an agent plenty to work with.

With 6,001 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
18/20
Description
15/15
Adoption
16/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 3 months ago, so xiaohongshu-search-full is actively maintained.
  • Our last check on 2026-11-16 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-06. Automated pattern scan on 2026-10-06. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

xiaohongshu-search-full compared with similar skills

All 4 of these similar skills score higher than xiaohongshu-search-full; compare them before choosing.

SkillScoreStarsUpdatedFormat
xiaohongshu-search-full (this skill)by browser-act946.0k3mo agoSKILL.md
taste-skillby Leonxlnx100116.8k8d agoCLAUDE.md
LocalAIby mudler10050.4ktodayMCP Server
x402by browser-use100121.0k3d agoSKILL.md
algorithmic-artby anthropics100177.9k55d agoSKILL.md

Frequently asked questions

How do I install xiaohongshu-search-full?
Run npx skills add browser-act/skills --skill xiaohongshu-search-full. The install tabs above show the steps for each supported agent.
Which AI agents does xiaohongshu-search-full work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is xiaohongshu-search-full safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is xiaohongshu-search-full still maintained?
The repository was last updated about 3 months ago, so xiaohongshu-search-full is actively maintained.

name: xiaohongshu-search-full description: "Search Xiaohongshu (XHS / RedNote) notes by keyword with full field extraction including body text, topics/tags, image list URLs, video stream URL, publish timestamp, and all engagement stats (likes, collects, comments, shares). Supports all page filter options: sort order (general, latest, most liked, most commented, most collected), note type (image-text, video), publish time range (within 1 day, 1 week, 6 months), search scope (seen, unseen, followed), and location distance (same city, nearby). Use when user mentions search xiaohongshu notes, xhs keyword search, rednote note search, search xiaohongshu posts, scrape xhs search results, xiaohongshu note discovery, rednote content search, collect xhs notes by keyword, xiaohongshu topic search, xhs note body text, xiaohongshu video notes, xiaohongshu image notes, rednote post filter, xhs search with filters, xiaohongshu full note data, xhs note details from search, extract rednote posts, xiaohongshu content monitoring, xhs search scrape."

Xiaohongshu — Search Notes (Full Fields)

keyword + filters → note list with full metadata (title, body, images, video URL, tags, stats) + detail enrichment

Language

All process output to user (progress updates, process notifications) follows the user's language.

Objective

Search Xiaohongshu notes by keyword, apply page filter options, and extract the maximum available fields from both the search results list and individual note detail pages.

Prerequisites

  • Browser opened to https://www.xiaohongshu.com/search_result/?keyword={keyword}
  • User is logged in (avatar or username visible in the left sidebar)

Phase 0: Collect User Inputs

First action: check whether the search keyword is already present in the user's message.

Keyword is present (e.g., "搜索 BrowserAct", "search for AI tools", "/xiaohongshu-search-full blockchain") → use it directly, skip to Pre-execution Checks.

Keyword is NOT present → STOP. Do NOT output "ready" or proceed with any execution. Ask the user for the keyword:

  • If the AskUserQuestion tool is available → call it immediately with:
    • Question 1 (required): "请问您想在小红书上搜索什么关键词?"
    • Question 2 (optional): pages needed (default: first page only)
    • Question 3 (optional): filters — sort order, note type, publish time range
  • If AskUserQuestion is NOT available → output the following text and wait for the user's reply before doing anything else:

    "请问您想搜索什么关键词?(如需指定页数或筛选条件,也可一并告知)"

Do NOT guess, infer, or assume any keyword. Wait for the user's explicit reply.

Pre-execution Checks

1. Tool Readiness

If browser-act has been confirmed available in the current session → skip this step.

Invoke browser-act via Skill tool to load usage. If installation or configuration issues arise, follow its guidance to resolve then retry.

2. Login Verification

If login status for Xiaohongshu has been confirmed in the current session → skip this step.

Otherwise: open https://www.xiaohongshu.com and observe the left sidebar:

  • User avatar or "Me" entry visible → logged in, continue execution
  • "Login" button visible → not logged in, inform the user that login is required, use remote-assist to let the user scan the QR code

User refuses or cannot log in → terminate execution.

Capability Components

This Skill's operational boundary = what the user can manually do in their browser. It only reads data already displayed to the user on the page, never bypassing authentication or access controls. Its role is equivalent to copy-pasting on the user's behalf — the data is already on screen, automation merely saves time. JS code is encapsulated in Python files under the scripts/ directory, invoked via python scripts/xxx.py {params} | browser-act --session <name> eval --stdin.

Below are all atomic capabilities discovered and verified during the exploration phase, listed by command template with parameters. Simply invoke them as needed — no need to read scripts/*.py source code or re-verify. Only inspect scripts when execution fails for troubleshooting. Combine freely as needed during execution.

DOM: extract search feeds list (preferred method)

Navigate to the search page, then read the rendered note list directly from Vue state. This is the preferred method because it reflects exactly what the page renders — including exact-match notes that the search API omits due to semantic expansion.

  1. navigate https://www.xiaohongshu.com/search_result/?keyword={keyword}
  2. wait stable
  3. (optional) Apply filters — see AI Workflow: apply filters below
  4. python scripts/extract-search-feeds.py | browser-act --session <name> eval --stdin — retrieves all page results. Do NOT pass --keyword for a full keyword search (title + body); see AI Workflow: keyword search (title + body match) below. Pass --keyword {keyword} only when title-only pre-filtering is explicitly required.

Parameters:

  • --keyword {keyword} (optional): plain text keyword — when passed, items contains only title-matched notes and keyword_count is populated. Omit to get all rendered notes (required for body-text matching).

Output example:

{
  "total_count": 40,
  "keyword_count": 3,
  "has_more": true,
  "items": [
    {
      "id": "6a422f88000000001603cdd3",
      "xsec_token": "ABbC…[redacted]",
      "note_url": "https://www.xiaohongshu.com/explore/6a422f88000000001603cdd3?xsec_token=ABbCLy...%3D&xsec_source=pc_search",
      "type": "video",                           // "normal" = image-text, "video" = video note
      "title": "note title text here",
      "publish_date": "06-29",                   // human-readable date string (not exact timestamp)
      "cover_url": "http://sns-webpic-qc.xhscdn.com/...",
      "liked_count": "3",
      "collected_count": "7",
      "comment_count": "0",
      "shared_count": "0",
      "author_nickname": "author nickname here",
      "author_id": "670caaaa000000001d0239d1",
      "author_avatar": "https://sns-avatar-qc.xhscdn.com/..."
    }
  ]
}
  • total_count: all notes rendered by the page (includes semantically expanded results)
  • keyword_count: notes whose title fuzzy-matches the keyword (Levenshtein edit distance ≤ 20% of keyword length, min 1 edit)
  • items: the fuzzy-filtered list (only notes whose title fuzzy-matches the keyword)
  • keyword_count: null means no --keyword was passed and items = all notes

Fuzzy matching details: --keyword uses Levenshtein edit distance with threshold max(1, floor(kw.length * 0.2)) per sliding window over each word in the title. This catches typos, capitalization variants (e.g., linfox → LinkFox, linxfox), and minor spelling differences within the threshold.

Note: has_more indicates whether more pages exist. body text (desc), topics (tagList), video stream URL, and exact publish timestamp (ms) are NOT in this response — use the detail component below to obtain them. When --keyword is passed, matching is title-only (fuzzy); for title + body matching, omit --keyword and follow AI Workflow: keyword search (title + body match) below.

Error handling: if error: true, verify wait stable completed and the page is not a login gate. Reload and retry once.

AI Workflow: keyword search (title + body match)

Run this workflow whenever a keyword is provided. It finds all notes where the keyword appears in either the title OR the body text (desc).

Step 1 — Extract all page results (no --keyword flag):

python scripts/extract-search-feeds.py | browser-act --session <name> eval --stdin

→ all_items list (total_count items, no pre-filtering)

Step 2 — Title filter (in-memory, no extra requests):

  • title_matches = items where keyword fuzzy-matches title (use same Levenshtein threshold as --keyword: max(1, floor(len(keyword) * 0.2)) edits per word, case-insensitive, exact substring first)
  • candidates = remaining items (ALL items not matched by title fuzzy match)
  • Inform user: "Found {len(title_matches)} title match(es). Checking body text of {len(candidates)} candidates..."
  • CRITICAL: When title_matches == 0, do NOT stop. Zero title matches means body-text checking is MORE important, not less — the keyword may appear only in the body. Proceed to Step 3 unconditionally unless total_count == 0.

Step 3 — Body-text check (detail page per candidate, skip only if candidates is empty): For each item in candidates:

  1. browser-act --session <name> navigate https://www.xiaohongshu.com/explore/{id}?xsec_token={xsec_token}&xsec_source=pc_search
  2. browser-act --session <name> wait stable
  3. python scripts/extract-note-detail.py {id} | browser-act --session <name> eval --stdin
  4. If keyword fuzzy-matches (case-insensitive, same Levenshtein threshold) in desc → add to body_matches
  5. Wait 2–3 seconds before next request.

Step 4 — Report:

  • final_results = title_matches + body_matches (in original page order, deduplicated by id)
  • Inform user: "{len(title_matches)} title match(es) + {len(body_matches)} body-only match(es) = {total} notes containing '{keyword}' (from {total_count} page results)"
  • Clearly label each result: match_type: "title" or match_type: "body"

Edge cases:

  • title_matches == 0 AND body_matches == 0 → inform user: no notes found containing {keyword} in title or body text; suggest checking login status or trying a different keyword
  • total_count == 0 → inform user: no results at all; suggest checking login or trying a different keyword

Network Capture: search notes list (fallback method)

Use as fallback only when the DOM feeds extraction above fails. Navigate to the search page and read results from the so.xiaohongshu.com API response captured in browser traffic.

Important limitation: the search API applies semantic expansion — for niche or brand-specific keywords, exact-match notes may be absent or pushed to later pages in the API response even when they appear prominently in the rendered page. Always prefer the DOM feeds method above.

  1. navigate https://www.xiaohongshu.com/search_result/?keyword={keyword}
  2. wait stable
  3. (optional) Apply filters — see AI Workflow: apply filters below
  4. network requests --type xhr,fetch --filter so.xiaohongshu
  5. Identify the request with URL containing /api/sns/web/v2/search/notes
  6. network request <id>
  7. Parse response_body JSON — field paths: data.items[n].id, data.items[n].xsec_token, data.items[n].note_card.display_title, data.items[n].note_card.interact_info.*

Note: data.has_more indicates whether more pages exist.

Error handling: If no request matching /api/sns/web/v2/search/notes is found, check that wait stable completed and the page is a search result page (not a login gate). Reload the page and retry once.

DOM: extract note detail (body, topics, video URL, exact timestamp)

Navigate to the note detail page and extract enriched fields from the Vue SSR state:

  1. navigate https://www.xiaohongshu.com/explore/{note_id}?xsec_token={xsec_token}&xsec_source=pc_search
  2. wait stable
  3. python scripts/extract-note-detail.py {note_id} | browser-act --session <name> eval --stdin

Parameters:

  • {note_id}: note ID from the search list result (id field)
  • {xsec_token}: security token from the search list result (xsec_token field)

Output example:

{
  "noteId": "694692cc000000001d039ea3",
  "title": "note title here",
  "desc": "note body text here",                // full body text
  "type": "video",                               // "normal" or "video"
  "time": 1766232780000,                         // exact publish timestamp (milliseconds)
  "ipLocation": "Fujian",                        // IP location, null if unavailable
  "userId": "59e9658411be10340721cd79",
  "nickname": "author nickname here",
  "avatar": "https://sns-avatar

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars6.0k
CategoryCustomer
Updated2mo ago
Forks304

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions