agentsclimarketplace

Deep research

Skill Fusion-Data-Company/bristol-os/plugins/bristol-os/skills/deep-research

One-paste Claude setup that turns Claude into an institutional multifamily research & underwriting teammate for Bristol Development Group — zero-config, fully cited, self-evolving (V1→V2→V3).

Install
npx -y skills add Fusion-Data-Company/bristol-os --skill deep-research

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Go deep on any question across many sources and return a cited, decision-ready briefing. Use when the user asks to "research," "look into," "go deep on," "find out everything about," or needs a sourced answer to a non-trivial question — markets, regulations, competitors, costs, trends, people/companies, or any topic where a single web result isn't enough.

SKILL.md

2.7 KB, as published. Nobody here has run it

Deep Research

Turn a plain-language question into a thorough, source-cited briefing. This is the research engine the other Bristol plays lean on.

When to use

The user wants more than a quick answer: "research the Nashville multifamily market," "what's happening with construction costs," "look into this developer," "find everything on this incentive program."

Tools, in order of preference

  1. Baked-in research keys (always available, no setup): load bristol-os/keys.env and call Tavily, Exa, and Firecrawl directly — exact commands in bristol-os/docs/DATA-SOURCES.md. Also FRED/Census for macro & demographic facts, and Quarry (quarry-parcels) for property/owner facts.
  2. Claude's built-in web search — always available.
  3. Yardi Matrix / finance connectors if connected (real estate / market data). Run the full method below regardless of which tools fire.

Method

  1. Clarify the decision. One sharp question if scope is unclear: what decision will this inform, and how deep do they need it? Then proceed.
  2. Decompose the question into 4–8 sub-questions. State them.
  3. Fan out: search each sub-question. Prefer primary and authoritative sources (government data, company filings, official market reports, reputable trade press). Note the date of every source.
  4. Triangulate: confirm important facts across 2+ independent sources. Flag anything you can only find once as "single-source — verify."
  5. Adversarially check: actively look for data that contradicts the emerging answer. Note disagreements rather than smoothing them over.
  6. Synthesize into the output format below. Lead with the answer.
  7. Cite everything with source + date. Never present an unsourced number as fact.

Output (save to the workspace, e.g. research/<topic>-<date>.md)

  • Bottom line — the answer in 3–5 sentences.
  • Key findings — the important points, each with a source and date.
  • What's uncertain / contested — gaps, conflicting data, single-source items.
  • So what for Bristol — implications for the deal/market/decision at hand.
  • Sources — list with links and dates.

Accuracy

  • If you can't verify a claim, say so. Do not fabricate figures, comps, dates, or names.
  • Distinguish fact (sourced) from estimate (your reasoning) — label estimates.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.