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 xyva-yuangui/XyvaClaw --skill research-suitegit clone --depth 1 https://github.com/xyva-yuangui/XyvaClawWrote 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/xyva-yuangui/xyvaclaw/research-suite)<a href="https://agentmods.dev/skills/xyva-yuangui/xyvaclaw/research-suite"><img src="https://agentmods.dev/badge/skills/xyva-yuangui/xyvaclaw/research-suite/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/xyva-yuangui/xyvaclaw/research-suite"><img src="https://agentmods.dev/badge/skills/xyva-yuangui/xyvaclaw/research-suite.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 | $0.00090 | $0.01259 |
| Opus 5 | $0.00045 | $0.00629 |
| Sonnet 5 | $0.00018 | $0.00252 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
research-suite 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.
What it actually says
🔍 Research Suite v3.0 — Perplexity 级融合深度搜索引擎
7 层流水线，从意图分析到迭代深化，对标 Perplexity AI。
架构 (v3.0)
L1: 意图分析 + 查询改写 (LLM, 中英文多角度)
L2: 5源并行搜索: Jina Search(免费主力) + DDG(兜底) + Tavily(付费) + Brave(免费) + SearXNG(自建)
L3: 全文深度提取 (Top 8-12, 15K-20K字/篇): Jina Reader → Trafilatura → Fallback
L4: 来源去重 + 权威排序 (20+权威域名) + 域名多样性 (每域名≤3条)
L5: 结构化LLM合成: 核心回答 → 详细分析(带[1][2]引用) → 矛盾分析 → 局限性
L6: 跟进问题生成 (3个延伸方向)
L7: (deep) 迭代深化: 质量评估 → 缺口识别 → 追加搜索 → 重新合成
使用
# 标准搜索 (Tavily+DDG, 提取5篇全文, LLM合成)
python3 scripts/search.py --query "AI Agent 最新进展"
# 快速搜索 (仅Tavily, 不抓全文, 1-3s)
python3 scripts/search.py --query "今天A股行情" --depth quick
# 深度搜索 (全部引擎, 提取8篇, LLM深度合成)
python3 scripts/search.py --query "2026新能源汽车格局" --depth deep
# 新闻搜索
python3 scripts/search.py --query "半导体" --type news
# JSON 输出 (供其他技能调用)
python3 scripts/search.py --query "..." --json
# 健康检查
python3 scripts/search.py --check
搜索深度
| 深度 | 搜索源 | 全文提取 | LLM合成 | 迭代 | 耗时 |
|---|---|---|---|---|---|
| quick | Jina+DDG | 否 | 否 | 否 | 1-3s |
| standard | Jina+DDG+Tavily+Brave | Top 8 (15K字) | 结构化引用 | 否 | 8-20s |
| deep | 全部5源 | Top 12 (20K字) | 深度引用+矛盾 | 质量评估+追加 | 20-60s |
替代关系
| 旧技能 | 状态 | 说明 |
|---|---|---|
| duckduckgo-search | 已吸收 | 降级为兜底搜索后端 |
| auto-researcher | 搜索层替换 | 保留研究编排，搜索改用本技能 |
| multi-search-engine | 已替代 | 从未实现，已被本技能完全替代 |
| web-scraper | 保留 | 非搜索场景仍需 |
| browser-pilot | 保留 | 交互式浏览仍需 |
配置
openclaw.json → search 段 (所有 API key 均可选，Jina+DDG 免费无需配置):
{
"search": {
"tavily": { "apiKey": "tvly-..." },
"brave": { "apiKey": "BSA..." },
"searxng": { "baseUrl": "http://localhost:8888", "enabled": false }
}
}
v3.0 vs v2.0 升级要点
- 主力搜索从 Tavily(付费) 改为 Jina Search(免费), 无API key也能正常工作
- 新增 Brave Search 后端 (免费2000次/月)
- 全文提取深度 8K→15K-20K 字, 提取页数 5→8-12
- 搜索引擎并行化 (ThreadPool 6 workers)
- LLM 合成结构化: 核心回答→详细分析→矛盾→局限性→延伸问题
- deep 模式增加迭代深化: 评估回答质量→识别缺口→追加搜索
- 域名多样性控制: 同域名≤3条, 防止单一来源主导
- 权威来源扩展至 20+ 域名
What ships with it
2 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 · 105 lines · 0 tokens per session scan A 822f17e2aa9a
research-suite is a skill published in the GitHub repository xyva-yuangui/XyvaClaw (21 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,259 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 2026-08-30.
Other skills, from other repositories
imap-smtp-email
Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.
technology-search
Search tech blogs, developer forums, and IT media (TechCrunch, Hacker News, 36氪, etc.) for software and hardware industry updates with heat ranking and EN↔CN translation. Use this skill only when the topic is clearly about programming, software, hardware, AI, or IT infrastructure.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
article-writer
Multi-style article creation skill. Supports 5 writing styles (deep analysis, practical guide, story-driven, opinion, news brief), including complete workflow: material collection → outline → content → formatting. Activated when users mention "write article", "write post", "create", or "draft".
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.
content-planner
WeChat Official Account topic planning and content calendar management. Based on WeChat article search and trending analysis, generates differentiated topic recommendations and outputs structured content calendars. Activated when users mention "topic", "planning", "content calendar", "trending", or "what to write next…