AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

deep-research

Use when a wrong answer is expensive: strategy research, comparing several products or markets, validating a hypothesis with outside data. Fans out searches and sub-agents, triangulates each claim across 3+ sources and saves every source with quotes. Quick facts: answer directly.

Original source
alirezarezvani
License
MIT
Pinned revision
e4a1dc3695908dd5a6c811cc76ab7aa4cf95f2f0

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

Ask your assistant

Use Agentic Memory skills to read alirezarezvani--deep-research at revision e4a1dc3695908dd5a6c811cc76ab7aa4cf95f2f0, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 2

references/full-catalog.md

Full catalog & upstream

This skill is a self-contained methodology. The complete, continuously-maintained catalog it draws on — 29 search channels, 460+ statistical sources, 39 validated APIs, and 103 report blocks — lives in the upstream project, where a weekly CI job re-validates every API endpoint and flags dead links:

https://github.com/Socialpranker/claude-deep-research

What's upstream (kept there to avoid duplicating a large, fast-moving catalog):

  • phases.yaml — the canonical phase definitions and depth gating.
  • references/channels.md — the 29 named search channels.
  • references/stat_sources/ — the 460+ statistical-source registry.
  • references/api_sources/ — the 39 API definitions with auth and fallback notes.
  • references/blocks/ — the 103 report building blocks per genre.

The SKILL.md here is the operating discipline; pull the upstream catalog when you want the full sourcing surface or the auto-validated API list.