SiftStack

Full-stack real estate investing operations platform built around DataSift.ai.

Two things live in this repo:

1. The REI skill library. 27 current packages that teach Claude to run a specific REI workflow: comp a property, estimate a rehab, find the heirs, score your phone numbers, grade your cold calls. Install them into Claude Code or Claude Cowork from the plugin marketplace, and they keep themselves up to date. You do not need the platform to use these.
2. The platform. The pipeline that pulls county distress data, enriches it through 10 steps, and pushes it into DataSift ready for sequential marketing. Requires a DataSift.ai account.

Start with the skills. Most people never need anything else.

---

Install the skill library

Claude Code (two commands, then it updates itself)

/plugin marketplace add DataSift-Ty-Personal/SiftStack
/plugin install siftstack-all@siftstack

That installs all 27 current packages as plugins. Then turn on updates once: run /plugin, open Marketplaces, select siftstack, choose Enable auto-update. From then on every improvement pushed here reaches you on its own. Claude Code leaves auto-update off for any marketplace that is not Anthropic’s, which is why this step exists.

Want one division instead of everything? Install a bundle: siftstack-deal-analysis, siftstack-market-intel, siftstack-crm, siftstack-coaching or siftstack-operations. Or install any single skill by name, such as /plugin install rehab-estimator@siftstack.

Then ask Claude to run the SiftStack doctor. It tells you what works right now, what needs a key, what each key costs, and the free route without it.

If the install fails with Unrecognized key: "dependencies", your Claude Code predates bundles. Run claude update and try again.

Claude Cowork

Same library, same updates. Customize, then Plugins, then Add marketplace, and enter DataSift-Ty-Personal/SiftStack. Install siftstack-all or any single plugin from the list. Use Update on the marketplace to pull the latest.

Cowork runs skills inside a sandbox with restricted network access. The skills that need no credentials work there as they do anywhere. A skill that calls a paid API may be blocked from reaching it, and in that case run it from Claude Code instead.

Without plugins (any Claude Code version, one command)

# macOS / Linux
curl -fsSL https://raw.githubusercontent.com/DataSift-Ty-Personal/SiftStack/main/install.py | python3 -

# Windows PowerShell
irm https://raw.githubusercontent.com/DataSift-Ty-Personal/SiftStack/main/install.py | python -

That copies the skills into ~/.claude/skills/. Restart Claude Code and they are live. No clone, no pip install, no virtualenv. Python 3.9 or newer, standard library only. This route does not update itself: re-run it to pull changes. Add --plugins and it registers the marketplace and installs every plugin for you instead, which works even on a Claude Code too old for bundles.

Prefer to read the script before running it? That is the right instinct:

curl -fsSL -o install.py https://raw.githubusercontent.com/DataSift-Ty-Personal/SiftStack/main/install.py
less install.py
python3 install.py

Pick and choose

python3 install.py --list                                  # the catalog, with descriptions
python3 install.py --only rehab-estimator comp-package     # just these
python3 install.py --category "Deal Analysis"              # a whole category
python3 install.py --dest .claude/skills                   # into a project, not your home dir
python3 install.py --dry-run                               # report, write nothing

Re-running is safe. Anything already current is skipped, and a package is only swapped in after it downloads and unpacks cleanly, so a failed update cannot leave you with a half-written skill.

Projects and the claude.ai app

Chat and Projects take the packaged file rather than a plugin. Download the .skill you want from dist/ and upload it to your session or Project:

https://raw.githubusercontent.com/DataSift-Ty-Personal/SiftStack/main/dist/rehab-estimator.skill

Every package in the catalog below is at that same path with its own name. .plugin files work the same way.

Point Claude at this repo and let it do the work

If you are already in a Claude Code session, this is usually the fastest route:

Read https://raw.githubusercontent.com/DataSift-Ty-Personal/SiftStack/main/skills/manifest.json and install the Deal Analysis skills for me.

The manifest is the machine-readable index of the whole library: every package, its category, its description, its download URL, and a SHA-256 of the exact bytes. It is what install.py reads, and it is regenerated by CI on every push so it cannot drift from what is actually published.

---

The catalog

27 current packages. python3 install.py --list prints this with full descriptions.

Deal Analysis

Market Intelligence

Operations

Coaching and Performance

CRM

Setup

Two superseded packages (deep-prospecting, deep-prospecting-v4) stay in the repo so old runs still resolve. The installer skips them unless you ask for one by name. Use deep-prospecting-v5, which is about 5x cheaper and returns relatives on records where v4 returned nothing.

What a skill needs from you

14 work on install, out of 27 current packages. No key, no login, no card. Ask Claude to run the SiftStack doctor, or from a terminal:

python3 install.py --doctor

It reads your environment and a .env if you have one, then prints what works now, what needs you signed in somewhere, and what needs a credential. Every blocked skill prints its no-API alternative on the same line, so you are never told no without being told what to do instead. It sends no requests, spends nothing, and never prints a credential value.

Every paid step has a no-API route. Comping runs by browser, heir research runs off obituaries and free people-search, KPIs run off a CSV export, coaching runs off any dialer’s recordings. The no-API playbook has the method for each, and is honest about the three things that have no substitute.

Skills degrade rather than fail: a missing key means that step is skipped and the run says so.

---

The agent system

The platform is 82 agents across 9 divisions.

• The interactive map, searchable and filterable by division, status, and whether a human still signs off.
• docs/AGENT-MAP.md, the same thing as a document you can read in the repo or hand to Claude.

Both render from docs/agents.json, so they cannot disagree about what the system does.

Each agent carries a trigger, the steps it runs, where a person signs off, what comes out, and the trap it exists to avoid. That last field is the one worth reading: every one is a real production failure, and most of them failed silently for days or weeks before anyone noticed.

  Web scrape (gated site)   ──┐
  Scanned PDF (OCR)         ──┤
  Courthouse photos         ──┼──►  Enrichment  ──►  DataSift  ──►  Sequential
  Dropbox auto-poll         ──┤     (10 steps)       (API)          marketing
  CSV re-import             ──┘
                                          │
                                          ▼
                          Deal analysis ──► Dispo ──► Lender package

Divisions: Data Acquisition, Enrichment and Identity, Deal Analysis, Dispo and Buyers, Outreach and Marketing, CRM Operations, Market Intelligence, Coaching and Performance.

Every gated action routes to a human. Outreach identity is anchored to the assigned person rather than a company name, and no agent sends a dollar figure to a seller or a buyer without a person approving it.

---

The platform

Requires a DataSift.ai account. Works with any market, any county, any state.

Quick start

git clone https://github.com/DataSift-Ty-Personal/SiftStack.git
cd SiftStack
pip install -r requirements.txt
playwright install chromium
cp .env.example .env          # then fill in your keys

python src/main.py daily                          # new notices since last run
python src/main.py daily --upload-datasift        # scrape, enrich, upload
python src/main.py daily --counties Knox --types foreclosure,probate

Data intake

All five produce the same records and flow through the same enrichment pipeline.

Enrichment pipeline

Deduplicate, filter vacant land, flag entity owners, resolve probate property, tax delinquency, address standardization (Smarty), property data (Zillow), obituary and heir research, skip trace (Tracerfy), phone scoring (Trestle).

Every API is optional. A missing key skips that step and the run reports it.

Scheduled cloud pull

The county pull runs unattended on Fly.io rather than on a workstation. deploy/FTM_RUNBOOK.md is the runbook.

python src/ftm_runner.py --doctor        # credentials, egress, state, saved searches
python src/ftm_runner.py --max-notices 2 # bounded dry run, writes nothing
python src/ftm_runner.py --commit        # the real thing
python src/ftm_schedule.py --next        # next 5 fire times

The scrape is gated on egress IP, not on code. From an office IP the notice page carries no CAPTCHA at all, just a refusal to serve. From a datacenter IP it serves the normal challenge. A blocked run exits 3 rather than 1, because no retry fixes it and treating it as a normal failure sends you debugging the parser. Run --doctor before anything else.

Zero notices is a failure, not a quiet day. There is deliberately no inference that a missing challenge means a cleared gate. That exact reasoning reported 13 consecutive dead runs as successful over 19 days.

Deal analysis

# Comps, ARV, rehab, buyers, into one workbook
python src/comp_package.py --address "158 Old State Rd" --zip 37914 \
    --beds 2 --baths 1 --sqft 1946 --bbox "35.996,36.016,-83.895,-83.840"

# The hour after you walk a house: 9 sheets, anchored to the live CRM record
python src/post_walkthrough.py --walkthrough-template
python src/post_walkthrough.py --address "..." --walkthrough walk.json

# The 8-piece private lender package
python src/lender_package.py --spec deals/EXAMPLE_lender_spec.json
python src/lender_docs.py    --spec deals/EXAMPLE_lender_spec.json

deals/EXAMPLE_lender_spec.json is a scrubbed, working spec. Copy it and fill it in.

Configuration

Every variable is documented in .env.example. The ones that matter most:

Running one county daily costs roughly $40 per month in API spend.

Adapting to your market

The architecture is market-agnostic. Knox and Blount County, TN are what it is proven on.

1. Edit SAVED_SEARCHES in src/config.py for your county’s notice site.
2. Add your county’s tax API alongside Knox in src/tax_enricher.py.
3. The parser handles 7 notice types already: foreclosure, tax sale, tax delinquent, probate, eviction, code violation, divorce.
4. Photo import and the enrichment pipeline are county-independent and work nationwide.

---

Contributing to the skill library

The source of truth is the folder, not the ZIP. skills// is what you edit and what gets reviewed; dist/.skill is a build product.

# edit skills/rehab-estimator/SKILL.md, then
python tools/build_skills.py --build --manifest
python tools/build_skills.py --verify        # CI runs this

CI blocks a merge if a distributed archive drifts from its source, if the manifest is stale, if any SKILL.md is missing its name or description frontmatter, or if anything that looks like a credential appears in a package.

That frontmatter check exists because a skill with no frontmatter is silently undiscoverable. Claude has nothing to match a request against, so it simply never fires and no error is ever raised. One skill shipped that way for months.

1. Fork, branch, commit.
2. Run python tools/build_skills.py --build --manifest before you push.
3. Open a pull request.

License

MIT. See LICENSE.

Built by DataSift.ai for the REI community.