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-inspirationgit 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-inspiration)<a href="https://agentmods.dev/skills/redfox-data/redfox-community-dsh/xiaohongshu-inspiration"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/xiaohongshu-inspiration/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-inspiration"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/xiaohongshu-inspiration.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 | $0.00208 | $0.05989 |
| Opus 5 | $0.00104 | $0.02995 |
| Sonnet 5 | $0.00042 | $0.01198 |
| Haiku 4.5 | $0.00021 | $0.00599 |
Grade A, and why
xiaohongshu-inspiration 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 4d 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 — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书内容灵感专家
📝 简介
一个 Skill 覆盖小红书选题灵感全链路——从找爆款、追榜单到选对标，基于红狐数据每日收录的小红书爆款库（互动数 1000 以上收录），帮创作者、品牌方和 MCN 快速找到下一个选题。数据覆盖昨天至 30 天前，各模块更新时间见对应章节。所有数据来源于红狐 API，严禁任何联网搜索；仅在主 Agent 中执行，不派发给子 Agent。
✨ 功能特性
| 功能模块 | 能力描述 | 核心价值 |
|---|---|---|
| M1 关键词爆款搜索 | 按关键词搜索爆款笔记（互动数 1000+ 收录，每日 7:00 更新昨日），三维评分排序推荐 | 找选题灵感，锁定赛道热点 |
| M2 批量获取作品 | 按关键词+日期范围+排序批量获取作品（昨天至 30 天前），支持 Excel/HTML 导出 | 数据化选题，便于复盘分享 |
| M3 每日爆款 TOP50 | 发布后第 3 天相对第 2 天互动增量爆发榜（每日 19:00 更新）+ 爆款规律分析 | 追踪爆发趋势，掌握爆款节奏 |
| M4 低粉爆款挖掘 | 粉丝 < 5000 且点赞 > 500 的黑马笔记 TOP50（每日 19:30 更新） | 小博主可直接复制的起号样本 |
| M5 账号榜单 | 日/周/月榜账号 TOP50，粉丝与互动增量加权评分 | 看赛道排名，找涨粉标杆 |
| M6 对标账号推荐 | 同阶对标（可直接复制玩法）+ 高阶标杆（粉丝量 3-5 倍） | 起号参考与投放选择有据可依 |
🔑 鉴权（REDFOX_API_KEY）
依赖安装（仅 M2/M3 需要 requests，其余模块用标准库）：
pip3 install "requests>=2.28.0"
获取方式：
配置方式（脚本按优先级自动回退）：
| 优先级 | 来源 | 说明 |
|---|---|---|
| 1 | 环境变量 REDFOX_API_KEY |
直接读取当前进程环境变量 |
| 2 | Shell 配置文件 | 自动扫描 ~/.zshrc ~/.bashrc ~/.bash_profile ~/.profile ~/.zprofile |
| 3 | 提示用户配置 | 以上都找不到时，引导用户配置 |
配置示例：echo 'export REDFOX_API_KEY=ak_xxx' >> ~/.zshrc && source ~/.zshrc；验证：echo $REDFOX_API_KEY。Windows：[Environment]::SetEnvironmentVariable("REDFOX_API_KEY", "<值>", "User") 后重启终端。
🔄 功能路由
| 用户意图 | 典型表述 | 模块 |
|---|---|---|
| 关键词搜爆款笔记、找选题灵感 | "搜一下睫毛膏的爆款笔记" | M1 |
| 按时间范围批量获取作品、导出报告 | "获取 8 月穿搭作品数据"、"导出 Excel" | M2 |
| 每日爆款榜、爆发笔记、互动增量 | "今日爆款笔记"、"睫毛膏爆发榜" | M3 |
| 低粉爆款、黑马笔记、小博主爆款 | "低粉爆款"、"粉丝少但很火的笔记" | M4 |
| 账号榜单、涨粉榜、赛道 TOP 账号 | "小红书日榜"、"美妆周榜 TOP50" | M5 |
| 找对标账号、相似账号、起号参考 | "我的 ID 是 xxx，推荐对标"、"做饭 3000 粉素人" | M6 |
混合意图按模块分别执行；无法判断时先询问用户。
⚙️ 全局规则（所有模块共享）
关键词类型判断（M1/M2/M3 共用）
- 细分词/垂直赛道（含场景/人群/风格/属性修饰，如"职场穿搭"、"减脂餐"）→ 直接查询
- 泛化词/大分类（无修饰的大类词，如"美妆"、"美食"、"穿搭"）→ 执行泛化词拓展，禁止直接调用脚本
- 空关键词 → M1 直接查全站热门（无评分列）
泛化词拓展策略（强制等待）：
- 结合近期热门趋势生成 10 个细分方向（趋势词、人群词、场景词、意图词各 2-3 个）
- 输出推荐后立即停止，等待用户回复「拓展」或具体关键词，不得在同一轮对话继续调用脚本
- 用户回复「拓展」→ 搜索这 10 个细分词；回复具体关键词 → 用该词查询
What ships with it
20 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.
- assets/preview-template.html 11 KB
- assets/report_template.html 8.3 KB
- README.en.md 6.4 KB
- README.md 5.5 KB
- references/m1_hot_article_format.md 4.7 KB
- references/m3_core_workflow.md 28 KB
- references/m4_api_spec.md 9.6 KB
- references/m5_api_docs.md 6.2 KB
- references/m5_score_rules.md 989 B
- references/m6_account_template.html 4.3 KB
- scripts/crawl_xhs.py 5.6 KB runs code
- scripts/fetch_explosive_articles.py 49 KB runs code
- scripts/fetch_rank.py 40 KB runs code
- scripts/fetch_xhs_hot_articles.py 24 KB runs code
- scripts/gen_xhs_html.py 34 KB runs code
- scripts/generate_html_on_demand.py 5.0 KB runs code
- scripts/generate_rank_report.py 20 KB runs code
- scripts/generate_xhs_report.py 5.6 KB runs code
- scripts/xhs_daily_fetcher.py 28 KB runs code
- scripts/xiaohongshu-similar-account.py 38 KB runs code
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.
- 4d ago First seen · 335 lines · 208 tokens per session scan A 4f3f41dd9197
xiaohongshu-inspiration is a skill published in the GitHub repository redfox-data/redfox-community-dsh (5 stars, last pushed yesterday), licensed MIT. It adds 208 tokens to every session and 5,989 once invoked, about $0.0010 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 2026-09-08.
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…
living-docs-governance
Keep a long-lived project's documentation from rotting by assigning existing project docs clear constitution, map, status, and history roles, then wiring the active agent harness to those canonical sources. Use in the maintain phase when docs drift from code, agents lose context between sessions, or intentional…