Skills-compatible agents / Research
Deep Research
Turns a research question into a sourced report by searching multiple angles, reading key pages and separating evidence from inference.
298,453 repository stars · checked 2026-11-06. Count applies to affaan-m/ECC, not this individual skill.
Guide by IDAKIM Digital. Source review: . Original explanation based on the linked publisher sources.
What it does
ECC is a broad agent-workflow repository; Deep Research is the specific skill selected here. It plans several subquestions, uses Firecrawl or Exa MCP tools, reads important sources beyond snippets and assembles an attributed report. Repository stars describe the whole ECC project, including material unrelated to this research workflow.
When to use it
- Compare technologies before making an engineering decision.
- Investigate a market or competitor with traceable evidence.
- Prepare a current topic briefing with explicit knowledge gaps.
Step-by-step workflow
- Clarify the decision or audience and research depth.
- Break the question into a few distinct subquestions.
- Search alternative terms and prioritize authoritative sources.
- Open the strongest pages and compare claims across independent evidence.
- Write a cited synthesis, source list, methodology and unresolved questions.
Example request
Use deep-research to compare hosted and self-hosted search for a small support portal. Cover cost drivers, operational work, privacy and migration constraints. Use official documentation for product claims and distinguish vendor statements from independent findings. Produce a decision table, dated citations and unresolved questions. Do not invent prices that are not public.
Worked example
Two articles repeating the same vendor announcement are not independent confirmation. Trace product limits back to the vendor documentation and operational claims to actual evidence. If private pricing prevents a fair comparison, list the missing quote rather than guessing a monthly bill.
What you get
A structured report with attributed findings, practical takeaways and research limitations.
How to evaluate the result
- Confirm the requested artifact or behavior is actually delivered, with evidence appropriate to this workflow.
- Repeat the example on your own inputs and check the stated limits; repository popularity is not an execution test.
- Verify important facts, permissions and failure paths before adopting the result.
What you need
A host with at least one supported Firecrawl or Exa MCP integration, network access and any required service credentials.
Setup and activation
Follow the publisher README for your specific client and preserve the complete selected skill folder, including companion references and scripts. Claude Code, Codex and other hosts may use different plugin or Agent Skills installation paths. This guide does not establish that every host has the same tools. Security-scan the exact version before installation; this website installs or executes nothing.
Limits and considerations
Search integrations may use paid credits. The skill describes broad research and optional parallel work; this catalogue has not executed either. Source volume alone does not prove reliability.
Related workflows
- Use a task-specific validation workflow to check the final result.
- Review companion scripts and references before adding this skill to an agent.
License and reuse
MIT at repository level; inspect per-file terms and separately licensed assets before reuse.
Further reading
Read the original source
Publisher: affaan-m/ECC
Source reviewed: 2026-11-06
Source reviewed; not installed, executed or security-scanned for this directory. These example requests were written by IDAKIM Digital. Upstream content can change.