Knowledge packs

Skill Fusion-Data-Company/bristol-os/plugins/bristol-os/skills/knowledge-packs

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 knowledge-packs

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

Recommend, configure, and pull from Bristol OS's tool catalog and GitHub pack. Use when the user asks "what tools can I add," "make me more powerful," "set up [a connector]," "can you get deeper data," "add real estate data," or when a task would clearly be better with a connector or repo the user hasn't set up yet.

SKILL.md

3.3 KB, as published. Nobody here has run it

Knowledge Packs — tools & repos

This play makes Bristol OS more powerful by connecting the right tools and pulling in the right open-source knowledge. Two reference files live in bristol-os/catalog/:

TOOL-CATALOG.md — every recommended connector, tiered and mapped to plays.
GITHUB-PACK.md — verified GitHub repos (skills, MCP servers, RE/finance/maps data).

Core behavior: recommend before you struggle

If a task would be materially better with a tool the user doesn't have, say so and offer to set it up — don't silently do a weaker job. Example: asked for rent comps with only web search, deliver what you can, then: "If you connect Yardi Matrix or I help Rob set up the free Census data server, I can make this much sharper — want that?"

Match the user to the right path

Basic user (Sam, David, staff): only ever recommend Tier 0 + one-click first-party connectors (Tavily, Exa, Google Drive, Yardi if subscribed). Walk them through Settings → Connectors in plain English. NEVER ask them to install a GitHub MCP server.
Technical user (Rob or a helper): offer the full GitHub pack, including community MCP servers (Census, SEC EDGAR, FRED, Maps, Firecrawl). Point them to the repo READMEs and the "full real estate power setup" list in GITHUB-PACK.md.

Setting up a first-party connector (any user)

Identify the connector from TOOL-CATALOG.md and say what it'll do for them.
Steps: Claude desktop → Settings → Connectors → find it → Connect → sign in once.
If it needs an API key (Tavily/Exa), point them to the signup and where to paste the key (see onboarding/connector-setup.md).
After they confirm, update their CLAUDE.md "connected tools" line so future sessions know it's available, and start using it.

Pulling from the GitHub pack (when the user has file access)

Knowledge/skills repos (e.g., anthropics/skills, hesreallyhim/awesome-claude-code): you may git clone or fetch specific files into a local knowledge/ folder to learn patterns or reuse a skill (like the official docx/xlsx skills for deliverables). Pull only what's relevant; don't clone everything.
MCP server repos: these are installed, not read. For a basic user, don't attempt it — instead produce a short, plain "Ask Rob to set this up" note naming the repo and what it unlocks. For a technical user, walk the repo README setup.

Discovering new tools

If Bristol needs something not in the catalog, consult the MCP directories in GITHUB-PACK.md (modelcontextprotocol/servers, punkpeye/awesome-mcp-servers), find a candidate, verify it exists and is maintained (check stars/last update), and only then recommend it. Never invent a tool or repo.

Guardrails

Verify before recommending — real connectors/repos only; flag archived/low-adoption ones honestly.
Keep the basic-user path dead simple; push complexity to the technical path.
After any change, reflect it in CLAUDE.md so the setup stays self-aware.