Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add redfox-data/redfox-community-dsh --skill xiaohongshu-top-accountgit clone --depth 1 https://github.com/redfox-data/redfox-community-dshWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/redfox-data/redfox-community-dsh/xiaohongshu-top-account)<a href="https://agentmods.dev/skills/redfox-data/redfox-community-dsh/xiaohongshu-top-account"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/xiaohongshu-top-account/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/redfox-data/redfox-community-dsh/xiaohongshu-top-account"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/xiaohongshu-top-account.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.04428 |
| Opus 5 | $0.00016 | $0.02214 |
| Sonnet 5 | $0.00006 | $0.00886 |
| Haiku 4.5 | $0.00003 | $0.00443 |
Grade A, and why
xiaohongshu-top-account scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书热门账号推荐
概述
本 Skill 基于 https://redfox.hk/story/api/xhsData/query 数据接口,
提供小红书全品类/分品类账号每日/每周/每月的表现榜单查询。支持三大核心能力:
- 排名查询 — 查日榜、周榜、月榜 TOP50
- 领域查询 — 按品类筛选(美妆、美食、旅行、母婴、健身/体育锻炼等)
- 报告下载 — 生成 HTML 可视化报告,支持导出 PDF/截图
- 定时订阅 — 设置自动化定时推送
鉴权
获取 API Key
请前往 红狐hub 获取API KEY
配置 API Key
方案1: 以OpenClaw为例,将REDFOX_API_KEY添加到~/.openclaw/openclaw.json中
{ "env": { "REDFOX_API_KEY": "ak_xxxx..." } }
方案2: 终端配置:export REDFOX_API_KEY="ak_xxxx..."
export REDFOX_API_KEY="ak_xxxx..."
触发词与意图识别
| 用户意图 | 典型触发词 | 对应操作 |
|---|---|---|
| 排名查询 | 小红书日榜、周榜、月榜、TOP50、最夯账号、排行榜、最新推荐 | 调用 API 并格式化输出 |
| 领域查询 | 美妆类/美食类/旅行类/母婴类/健身类...小红书排名 | 调用 API 并按 category 筛选 |
| 报告下载 | 下载报告、导出榜单、生成报告 | 使用 --html 参数自动生成 HTML |
| 定时订阅 | 订阅日榜/周榜/月榜、定时推送、每天发给我 | 创建 WorkBuddy Automation |
执行流程
严格输出顺序(必须按顺序执行,不得跳过)
第一步:内容输出
- 调用脚本查询榜单数据(默认只查20条):
python scripts/fetch_rank.py --query "用户原始问题" --limit 20 --html - 按标准模板格式化输出榜单数据(Markdown 表格形式,最多20条)
第二步:询问定时订阅
- 输出完榜单数据后,直接追加以下询问(不等待用户回复):
📬 订阅服务 1️⃣ 是否需要订阅每日/周/月的小红书账号最新排名,订阅后定时推送给您?
2️⃣ 是否需要订阅具体赛道的账号表现?我们支持:综合全部、出行代步、休闲爱好、影视娱乐、数码科技、医疗保健、综合杂项、星座情感、时尚穿搭、婚庆婚礼、拍摄记录、学习教育、化妆美容、居家装修、旅行度假、亲子育儿、个人护理、美味佳肴、职业发展、宠物天地、潮流鞋包、日常生活、科学探索、新闻资讯、体育锻炼
第三步:交付 HTML 报告
- 脚本已自动生成HTML文件,使用 deliver_attachments 工具交付脚本输出的 HTML 文件路径
- 追加以下内容:
⚡ 更多操作 • 点击下方下载HTML报告文件,可在浏览器中打开查看,支持一键导出PDF/高清图片 • 本次榜单完整共50条数据,是否需要查看全部?
用户表示需要查看全部数据时:
⚠️ 强制要求:必须同时输出 Markdown 表格和交付 HTML 报告,两者缺一不可。
- 重新调用脚本获取完整50条数据:
python scripts/fetch_rank.py --query "用户原始问题" --limit 50 --html - 在对话中输出完整50条数据的 Markdown 表格(按标准模板格式)
- 必须使用 deliver_attachments 交付 HTML 文件(关键步骤,不可遗漏),告知用户"以下是完整50条数据的 HTML 报告,可直接点击下载查看"
流程一:排名查询(推荐:自然语言模式)
直接传入用户原始问题,脚本自动完成全部解析:
python scripts/fetch_rank.py --query "用户原始问题" --limit 20 --html
自动解析逻辑:
① 时间判断与日期计算
根据当前时间判断最新数据是否已更新:
| 榜单类型 | 更新时间 | 当前时间 < 更新时间 | 当前时间 >= 更新时间 |
|---|---|---|---|
| 日榜 | 每日 19:00 | 取前2天 (offset=2) | 取前一天 (offset=1) |
| 周榜 | 每周一 15:00 | 取前2周 (offset=2) | 取前1周 (offset=1) |
| 月榜 | 每月1日 上午9:00 | 取前2月 (offset=2) | 取前1月 (offset=1) |
日期计算公式:
- 日榜:
date.today() - timedelta(days=offset) - 周榜:
date.today() - timedelta(weeks=offset)后的最近周一 - 月榜:
date.today() - timedelta(days=30*offset)后的每月1日
更新规则(输出时告知用户):
- 日榜:每日 19:00 更新
- 周榜:每周一 15:00 更新
- 月榜:每月 1日 9:00 更新
② 周期判断
自动从用户文本中识别日/周/月(无明确则默认日榜):
- 含"周"/"周榜"→
week - 含"月"/"月榜"→
month - 其余默认 →
day
③ 回溯范围校验
| 榜单类型 | 最大回溯 | 超范围处理 |
|---|---|---|
| 日榜 | 近7天 | 自动切换至最近可用日期 |
| 周榜 | 近3周 | 自动切换至最近可用日期 |
| 月榜 | 近3个月 | 自动切换至最近可用日期 |
超出范围时:-若用户查询当日及未来日期的榜单,在榜单说明输出中增加:「非常抱歉🙏,我们最新的是昨日/上周/上月的数据,将为您提供最接近您需求的昨日/上周/上月热榜。」 -若用户查询时间早于回溯日期,在榜单说明输出中增加回复:「非常抱歉🙏,目前榜单最多支持回溯「过去7天/过去3周/过去3月」,我将为您查询最接近您需求的时间范围~」
④ 赛道(type)匹配
支持模糊匹配,映射表见 references/api_docs.md。
常用映射:
| 用户说 | 映射到 |
|---|---|
| 健身、运动、瑜伽 | 体育锻炼 |
| 美妆、彩妆、护肤 | 化妆美容/个人护理 |
| 美食、探店、烹饪 | 美味佳肴 |
| 旅行、旅游 | 旅行度假 |
| 母婴、育儿 | 亲子育儿 |
| 穿搭、时尚 | 时尚穿搭 |
若无法匹配,输出综合全部,并告知用户无法识别的赛道类别。
⑤ 数据回退机制
重要:部分分类(如体育锻炼)在某些日期可能返回空数据。此时应:
- 自动尝试前一个日期
- 最多回退3天
- 若仍无数据,告知用户该分类在该时间段暂无数据
流程二:报告下载
- 查询时加
--html --limit 50参数,脚本会自动生成HTML报告 - 调用
deliver_attachments交付 HTML 文件(账号名均可点击跳转小红书主页)
流程三:定时订阅
- 询问订阅周期(每日 / 每周 / 每月)。
- 使用
automation_update创建自动化任务:- 每日订阅:
FREQ=DAILY;BYHOUR=8;BYMINUTE=0 - 每周订阅:
FREQ=WEEKLY;BYDAY=MO;BYHOUR=8;BYMINUTE=0 - 每月订阅:
FREQ=WEEKLY;BYDAY=MO;BYHOUR=8;BYMINUTE=0;INTERVAL=4
- 每日订阅:
- automation prompt:
查询小红书最新{period}榜(综合全部)并推送给用户
标准输出模板
必须按以下顺序输出,不得跳过任何步骤:
第一步:内容输出
📊 小红书{period_label} · {category_label}
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 356 lines · 32 tokens per session scan A ad5cef355ca4
xiaohongshu-top-account is a skill published in the GitHub repository redfox-data/redfox-community-dsh (6 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 4,428 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
dsh-hooks-authoring
Instructions for writing and debugging dsh-hooks-plugin scripts, which run during tool or session events such as before a tool call or after it finishes. These scripts return JSON decisions such as allowing, asking about, or denying an action.
web-artifact-designer
A design workflow for producing self-contained HTML or SVG files that open directly in a browser. It covers visual work such as posters, infographics, landing pages, charts, banners, cards, and interface mockups.
dsh-web-pet-developer
Create a pet for the dsh-pet plugin and integrate it into the dsh web GUI — author a v2 pet.json manifest plus an 8-column x 9-row atlas per the Codex/hatch-pet contract (live2d pets, voice packs and status decorations included), drop it into the pet-center user directory or contribute it as a built-in asset under…
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
delivery-proof
Delivery proof and the doublecheck report. Use when the work is done and the delivery must be proven — consolidate the spec, test timeline, review verdicts, and verification checks into a doublecheckreport, and only then claim completion.