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 malue-ai/dazee-small --skill deep-researchgit clone --depth 1 https://github.com/malue-ai/dazee-smallWrote 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/malue-ai/dazee-small/deep-research)<a href="https://agentmods.dev/skills/malue-ai/dazee-small/deep-research"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/deep-research/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/malue-ai/dazee-small/deep-research"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/deep-research.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 | $0.00039 | $0.01192 |
| Opus 5 | $0.00019 | $0.00596 |
| Sonnet 5 | $0.00008 | $0.00238 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
deep-research 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 8d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
深度调研
执行多步骤自主调研:市场分析、竞品研究、行业报告、文献综述。自动搜索、分析、综合,生成完整调研报告。
使用场景
- 用户说「帮我调研 AI 办公助手市场」「分析前 5 名竞品」
- 用户说「做一份行业趋势报告」「调研这个赛道的机会」
- 用户说「帮我深入研究这个话题,写一份完整报告」
- 用户说「收集整理过去一周AI行业的热点新闻资讯」
执行方式
使用爬虫类 Skill(如 Crawl4AI)快速获取完整网页内容,大幅缩短调研时间。
调研流程
Step 1: 理解调研目标
↓ 明确范围、深度、输出格式
Step 2: 制定调研计划
↓ 拆解为 3-5 个子课题
Step 3: 批量搜索 + 内容抓取 (核心)
↓ 3.1 调用 web_search 工具获取相关 URL 列表 (自动选择 Tavily/Exa/Jina)
↓ 3.2 爬虫类 Skill (Crawl4AI) 并发抓取完整内容
↓ Playwright 浏览器引擎 → 突破反爬
↓ PruningContentFilter → 去除噪声
↓ 自动输出干净 Markdown
Step 4: 交叉验证
↓ 多个来源互相印证
Step 5: 综合分析
↓ 发现趋势、对比、洞察
Step 6: 生成报告
↓ 结构化输出
实现示例
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, CacheMode
from crawl4ai.content_filter_strategy import PruningContentFilter
from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
# Step 1: 调用 web_search 工具获取 URL(自动选择最佳搜索源)
search_queries = ["AI 办公助手 市场分析", "AI 办公助手 竞品对比"]
all_urls = []
for query in search_queries:
# 直接调用 web_search 工具(自动降级 Tavily → Exa → Jina)
results = await web_search(query=query, max_results=10, search_depth="advanced")
all_urls.extend([r["url"] for r in results.get("results", [])[:5]])
unique_urls = list(set(all_urls))[:15]
# Step 2: Crawl4AI 并发抓取完整内容
config = CrawlerRunConfig(
cache_mode=CacheMode.BYPASS,
markdown_generator=DefaultMarkdownGenerator(
content_filter=PruningContentFilter(threshold=0.4)
),
)
async with AsyncWebCrawler() as crawler:
results = await crawler.arun_many(unique_urls, config=config)
# Step 3: 提取成功的文章
valid = [r for r in results if r.success]
# Step 4: 构建上下文给 LLM 分析
context = ""
for article in valid:
content = article.markdown.fit_markdown or article.markdown.raw_markdown
context += f"来源: {article.url}\n\n"
context += f"{content[:2000]}\n\n---\n\n"
# Step 5: LLM 综合分析 (基于完整内容,质量远高于搜索摘要)
报告结构
# [调研主题] 调研报告
**调研日期**: YYYY-MM-DD
**调研范围**: [描述]
## Executive Summary
[1-2 段核心发现]
## 1. 背景与现状
[行业/市场背景]
## 2. 主要发现
### 2.1 [子课题 1]
[详细分析]
### 2.2 [子课题 2]
[详细分析]
## 3. 对比分析
[表格对比、优劣势分析]
## 4. 趋势与预测
[基于数据的趋势判断]
## 5. 建议与行动项
[可执行的建议]
## 参考来源
[标注所有信息来源 URL]
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.
- 8d ago First seen · 147 lines · 39 tokens per session scan A ef3f1bbd9e4d
deep-research is a skill published in the GitHub repository malue-ai/dazee-small (36 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 1,192 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…