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 bilibili-keywords-searchgit 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/bilibili-keywords-search)<a href="https://agentmods.dev/skills/redfox-data/redfox-community-dsh/bilibili-keywords-search"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/bilibili-keywords-search/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/bilibili-keywords-search"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/bilibili-keywords-search.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 | $0.00095 | $0.02458 |
| Opus 5 | $0.00048 | $0.01229 |
| Sonnet 5 | $0.00019 | $0.00492 |
| Haiku 4.5 | $0.00010 | $0.00246 |
Grade A, and why
bilibili-keywords-search 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 12d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B站关键词搜作品
📝 简介
输入关键词就能搜到 B 站刚发布的视频，能自己选排序、限定发布时间，给到你的都是平台刚更新的新鲜内容，不会拿旧缓存数据糊弄你。
✨ 核心价值
- 内容新鲜不滞后：每次搜索都会直接读取平台最新内容，只给刚发布的视频，不用老旧存档、缓存数据。
- 筛选方式灵活好用：能按综合热度、最新发布、点赞高低排序，还能筛选 7 天 / 30 天 / 90 天内视频，自由搭配条件查找。
- 搜不到自动扩词：关键词搜不出内容时，工具会自动生成 10 个相近词，帮你拓宽查找范围。
- 支持翻页查看 + 每日推送：海量结果可以分页浏览，订阅关键词后，系统每天自动推送新视频给你。
🔑 鉴权
获取 API Key
请前往 红狐hub 获取 API KEY
配置 API Key
方案1: 以 Qoder 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..."
🔄 工作流程
Step 1：理解用户意图，提取关键词和筛选参数
⚠️ 核心规则：语义理解优先，优先提取细分方向词，而非泛化大类词
1. 提取关键词
- 从用户描述中提取 2~6 字的细分关键词
- 若用户意图模糊（如"帮我搜B站"），主动询问：「请问你想搜索哪个方向或领域的内容？」
- 不得在用户未提供关键词时擅自猜测并调用脚本
2. 识别筛选参数（用户未指定时使用默认值）
- 排序方式（
--sort）：默认1（综合排序）- 用户提到"最新"、"最近发布" →
2 - 用户提到"点赞"、"热门"、"爆款" →
3 - 未提及排序 →
1（默认）
- 用户提到"最新"、"最近发布" →
- 发布时间（
--time）：默认7（最近7天）- 用户提到"近一个月"、"30天" →
30 - 用户提到"近三个月"、"90天" →
90 - 用户提到"不限时间"、"全部" →
0 - 未提及时间 →
7（默认）
- 用户提到"近一个月"、"30天" →
- 页码（
--page）：默认1- 用户提到"下一页"、"第2页" → 对应页码
- 用户提到"上一页" → 当前页 - 1
- 未提及页码 →
1（默认）
Step 2：调用搜索脚本
⚠️ 核心约束：每次查询严格只调用一次脚本，禁止重复调用。
- 无论脚本返回成功还是失败，都不得重试或二次调用
- 不得为"验证数据""获取更多信息"等任何理由再次执行脚本
- 若脚本执行失败，直接向用户报告错误，不得重试
python3 "$SKILL_PATH/scripts/search_bili_realtime.py" "<关键词>" [--sort 排序] [--time 时间] [--page 页码]
参数说明：
| 参数 | 可选值 | 含义 |
|---|---|---|
| keyword | 任意字符串 | 搜索关键词，多个词用英文逗号连接 |
--sort |
1 / 2 / 3 |
综合排序 / 最新发布 / 最多点赞（默认1） |
--time |
7 / 30 / 90 / 0 |
最近7天 / 30天 / 90天 / 不限（默认7） |
--page |
正整数 | 页码，从1开始（默认1） |
脚本以 JSON 格式输出：
| 字段 | 说明 |
|---|---|
articles |
关键词匹配视频列表（按点赞降序） |
sort_type_label |
本次排序方式文字说明 |
publish_time_label |
本次时间范围文字说明 |
page |
当前页码 |
total_pages |
总页数 |
has_next |
是否有下一页（true/false） |
What ships with it
3 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.
- 12d ago First seen · 195 lines · 95 tokens per session scan A f56e2a24efaf
bilibili-keywords-search is a skill published in the GitHub repository redfox-data/redfox-community-dsh (6 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 2,458 once invoked, about $0.0005 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 2026-08-31.
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.
dsh-webapp-testing
Verify a local web application's rendered browser behavior with console, network, server, and focused regression-test evidence.
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.
data-scraper-agent
Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Runs on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the…
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.
browser-qa
Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.