$ ~/registry/skill/affaan-m-deep-research

SKILL

deep-research

Name: deep-research
Author: affaan-m

Conduct multi-source web research and produce cited, source-attributed reports.

Stars

★ 229,796

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 210.5k

Summary

The skill appears to be an open-source, prompt-only research template with no built-in secrets, remote endpoints, or local execution logic, so its intrinsic risk is low. The main caveat is that it is designed to orchestrate external MCPs such as firecrawl/exa; actual network egress, data access, and permissions depend on those configured tools rather than this skill itself.

CredentialsLow risk

The materials explicitly state that no keys or environment variables are required, and the skill itself does not ask for, store, or forward credentials. If firecrawl/exa are later connected, any credential exposure risk would belong to those external MCP configurations, not to this prompt-only skill itself.

Network egressCaution

The skill itself declares no remote endpoint, but the README is explicitly designed to use firecrawl and exa MCPs for web search, scraping, and crawling, which would send research queries and target URLs to external services. Because the skill is not the component that connects directly, the relevant risk mainly comes from the configured MCPs’ actual endpoints, logging, and retention policies, which are not detailed here.

Code executionLow risk

Based on the stated checks, this is a prompt-only artifact, and the documentation does not include install scripts, executables, shell commands, or requirements to spawn local processes. It provides a research workflow and calling guidance rather than a component that directly executes code on the host.

Data accessLow risk

The materials do not declare any ability to read or write local files, system directories, databases, or other protected resources; they only suggest enabling relevant MCPs in configuration files. The skill itself appears limited to conversational context and shows no sign of overbroad data access.

Supply chainLow risk

The source is an open GitHub repository with very strong community adoption (about 210.5k stars), both of which are strong positive signals; the artifact is also prompt-only, which improves auditability. The missing license declaration and unknown maintenance status are worth noting, but without concrete red flags they do not justify a high-risk rating.

Recommendations

Review the firecrawl/exa MCP endpoints, logging, privacy policy, and permission scope before enabling this skill.
Do not send sensitive business data, unpublished documents, or personal information directly in research queries to external search/scraping tools.
Pin and document the exact MCP tool names and versions in use, since the README notes the setup is drift-prone.
Verify the repository’s license and maintenance status before adopting it for long-term production use.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "deep-research" skill from askskill:
1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/deep-research/SKILL.md
2. Save it as ~/.claude/skills/deep-research/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Research industry trends

Prompt

Please conduct deep research on 2024 global generative AI trends in enterprise services. Synthesize reliable sources into a structured report with key trends, notable companies, market data, risks, and citations for every major conclusion.

Expected

A cited industry research report with trend summaries, supporting data, examples, and source links.

Compare competitor solutions

Prompt

Research and compare the enterprise knowledge base capabilities of Notion, Confluence, and Coda. Summarize feature differences, pricing, ideal teams, and review patterns with verifiable source links, then provide a recommendation.

Expected

A cited competitor comparison report with a comparison table, pros and cons, and a recommendation.

Verify a trending topic

Prompt

Please deeply verify the claim that 'the EU's latest AI regulations will fully restrict open-source models.' Search authoritative sources, separate facts from misinterpretations and disputed points, and produce a cited conclusion summary.

Expected

A fact-check summary based on authoritative sources, with clear conclusions and cited evidence.

// docs

Deep Research

Drift-prone skill. Firecrawl/Exa MCP tool names, quotas, and result shapes change. Verify the configured MCP tools and current API docs before promising coverage or quoting live source counts.

Produce thorough, cited research reports from multiple web sources using firecrawl and exa MCP tools.

When to Activate

User asks to research any topic in depth
Competitive analysis, technology evaluation, or market sizing
Due diligence on companies, investors, or technologies
Any question requiring synthesis from multiple sources
User says "research", "deep dive", "investigate", or "what's the current state of"

MCP Requirements

At least one of:

firecrawl — firecrawl_search, firecrawl_scrape, firecrawl_crawl
exa — web_search_exa, web_search_advanced_exa, crawling_exa

Both together give the best coverage. Configure in ~/.claude.json or ~/.codex/config.toml.

Workflow

Step 1: Understand the Goal

Ask 1-2 quick clarifying questions:

"What's your goal — learning, making a decision, or writing something?"
"Any specific angle or depth you want?"

If the user says "just research it" — skip ahead with reasonable defaults.

Step 2: Plan the Research

Break the topic into 3-5 research sub-questions. Example:

Topic: "Impact of AI on healthcare"
- What are the main AI applications in healthcare today?
- What clinical outcomes have been measured?
- What are the regulatory challenges?
- What companies are leading this space?
- What's the market size and growth trajectory?

Step 3: Execute Multi-Source Search

For EACH sub-question, search using available MCP tools:

With firecrawl:

firecrawl_search(query: "<sub-question keywords>", limit: 8)

With exa:

web_search_exa(query: "<sub-question keywords>", numResults: 8)
web_search_advanced_exa(query: "<keywords>", numResults: 5, startPublishedDate: "2025-01-01")

Search strategy:

Use 2-3 different keyword variations per sub-question
Mix general and news-focused queries
Aim for 15-30 unique sources total
Prioritize: academic, official, reputable news > blogs > forums

Step 4: Deep-Read Key Sources

For the most promising URLs, fetch full content:

With firecrawl:

firecrawl_scrape(url: "<url>")

With exa:

crawling_exa(url: "<url>", tokensNum: 5000)

Read 3-5 key sources in full for depth. Do not rely only on search snippets.

Step 5: Synthesize and Write Report

Structure the report:

# [Topic]: Research Report
*Generated: [date] | Sources: [N] | Confidence: [High/Medium/Low]*

## Executive Summary
[3-5 sentence overview of key findings]

## 1. [First Major Theme]
[Findings with inline citations]
- Key point ([Source Name](url))
- Supporting data ([Source Name](url))

## 2. [Second Major Theme]
...

## 3. [Third Major Theme]
...

## Key Takeaways
- [Actionable insight 1]
- [Actionable insight 2]
- [Actionable insight 3]

## Sources
1. [Title](url) — [one-line summary]
2. ...

## Methodology
Searched [N] queries across web and news. Analyzed [M] sources.
Sub-questions investigated: [list]

Step 6: Deliver

Short topics: Post the full report in chat
Long reports: Post the executive summary + key takeaways, save full report to a file

Parallel Research with Subagents

For broad topics, use Claude Code's Task tool to parallelize:

Launch 3 research agents in parallel:
1. Agent 1: Research sub-questions 1-2
2. Agent 2: Research sub-questions 3-4
3. Agent 3: Research sub-question 5 + cross-cutting themes

Each agent searches, reads sources, and returns findings. The main session synthesizes into the final report.