← Back to Skills Marketplace
ivangdavila

Home Buying

by Iván · GitHub ↗ · v1.0.0
linuxdarwinwin32 ✓ Security Clean
377
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install home-buying
Description
Buy a home with budget guardrails, listing scorecards, offer strategy, due diligence triage, and closing readiness checks.
README (SKILL.md)

Setup

If ~/home-buying/ does not exist or is empty, read setup.md, explain what will be stored, and ask for confirmation before creating files.

When to Use

Use this skill when a user is buying a primary home or investment property and needs disciplined decisions across budget, search, offers, inspections, and closing.

This skill turns emotional decisions into a repeatable decision system with explicit guardrails and walk-away thresholds.

Architecture

Memory lives in ~/home-buying/. See memory-template.md for structure and status fields.

~/home-buying/
|-- memory.md             # Decision defaults, status, and recurring constraints
|-- active-deals.md       # Deal pipeline with stage and risk notes
|-- offer-log.md          # Offer ladder history and outcomes
`-- closing-checks.md     # Lender, title, insurance, and final walkthrough status

Quick Start

Use this workflow in order:

  1. Define buy-box and monthly guardrails.
  2. Score listings using one scoring rubric.
  3. Build a tiered offer ladder before writing any offer.
  4. Run inspection and document risk transfer plan.
  5. Gate closing on a readiness checklist.

Quick Reference

Use the smallest relevant file for the current step.

Topic File
Setup and activation behavior setup.md
Memory template memory-template.md
Budget math and guardrails budget-guardrails.md
Listing scoring rubric listing-scorecard.md
Offer strategy and concessions offer-ladder.md
Inspection and contingency triage due-diligence.md
Closing readiness gates closing-readiness.md

Core Rules

1. Build the Buy Box Before Browsing

  • Define non-negotiables (location radius, bedroom count, commute cap, property type) before reviewing listings.
  • Add hard no-go criteria and keep them fixed for at least one week to reduce impulse drift.

2. Underwrite Total Monthly Cost, Not List Price

  • Use all-in monthly cost: principal, interest, taxes, insurance, HOA, utilities estimate, and maintenance reserve.
  • Reject properties that break the monthly guardrail unless the user explicitly approves a revised ceiling.

3. Score Listings With One Rubric

  • Apply the same weighted scorecard to every candidate property.
  • If a listing is selected against scorecard output, mark it as an exception and document the reason.

4. Use a Tiered Offer Ladder

  • Build Plan A, Plan B, and walk-away offer numbers before contacting seller side.
  • Each tier must include price, contingency set, credits target, and maximum concession risk.

5. Treat Due Diligence as Risk Transfer

  • Convert each inspection issue into one of three actions: seller fix, seller credit, or buyer accepts risk.
  • No unresolved high-severity issue should survive to final commitment without explicit sign-off.

6. Protect Timeline and Financing Certainty

  • Keep a dated checklist for lender docs, appraisal milestones, title items, and insurance binders.
  • Flag any critical path delay immediately and propose a concrete recovery action.

7. Keep a Decision Log for Every Deal

  • Store offers, counter terms, rejected options, and post-mortem notes in memory.
  • Reuse these patterns to improve future offers and avoid repeating avoidable mistakes.

Home-Buying Traps

  • Shopping first, budgeting later -> overexposure and rushed compromises.
  • Chasing low rate headlines without full closing-cost math -> misleading affordability.
  • Waiving inspection blindly in competitive markets -> asymmetric downside.
  • Negotiating only on price -> missed credits, repairs, or timeline value.
  • Ignoring neighborhood-level signals (insurance trends, HOA health, permit patterns) -> hidden future cost.
  • Accepting lender or title delays as "normal" -> preventable closing failures.

Data Storage

  • Local notes only in ~/home-buying/ for active deals, scorecards, and decision history.
  • Store concise operational data, not full personal identity packages.
  • Ask before saving sensitive personal or financial details.

Security & Privacy

Data that leaves your machine:

  • None by default. This skill is workflow guidance and local-memory only.

Data that stays local:

  • Decision context, deal notes, and checklist state under ~/home-buying/.

This skill does NOT:

  • Submit offers automatically.
  • Call lender, MLS, escrow, or title APIs automatically.
  • Share user data with external services by default.
  • Modify files outside ~/home-buying/ for memory.
  • NEVER modifies its own skill definition file.

Related Skills

Install with clawhub install \x3Cslug> if user confirms:

  • real-estate-skill - Broad real-estate transaction guidance across roles and stages.
  • property-valuation - Comparable and income-based valuation support.
  • contract - Contract structure and clause review support.
  • rental - Rental economics and landlord or tenant decision support.
  • house - Home ownership operations after purchase.

Feedback

  • If useful: clawhub star home-buying
  • Stay updated: clawhub sync
Usage Guidance
This skill appears internally coherent and low-risk, but take these simple precautions before enabling it: (1) When prompted, read the exact confirmation text before the skill creates ~/home-buying/ and verify what it will store. (2) Avoid entering full account numbers, passwords, or other sensitive identifiers into the memory files; follow the skill's own guidance to redact or summarize such data. (3) If you prefer manual use, set activation preference to manual so it won't run automatically. (4) Periodically inspect ~/home-buying/ to confirm only expected notes are stored, and delete or encrypt any items you consider sensitive.
Capability Analysis
Type: OpenClaw Skill Name: home-buying Version: 1.0.0 The skill bundle is benign. All files, including `SKILL.md` and `setup.md` which contain instructions for the AI agent, consistently describe a local-memory, workflow guidance tool. The `SKILL.md` explicitly states 'Data that leaves your machine: None by default' and 'Share user data with external services by default' is false. It also confirms the skill 'Does NOT... Modify files outside `~/home-buying/` for memory.' The instructions for the agent are focused on user interaction, local file management within `~/home-buying/`, and storing non-sensitive decision context, with explicit guidance to 'Redact sensitive data before storing' in `memory-template.md` and `setup.md`. No evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts to subvert the agent's intended behavior was found.
Capability Assessment
Purpose & Capability
The skill's name/description (home-buying decision workflow) matches what it asks for: a local config path ~/home-buying/ and a set of guidance documents. There are no unrelated environment variables, binaries, or external APIs requested.
Instruction Scope
The SKILL.md and companion docs clearly confine runtime behavior to reading/writing files under ~/home-buying/ and asking for confirmation before creating that folder. The docs explicitly state it will not submit offers or call external APIs and that it will ask before saving sensitive personal/financial details. Recommend verifying the agent actually prompts for confirmation and that the definition of 'sensitive' is acceptable to you.
Install Mechanism
No install spec or code is present (instruction-only). This is lowest-risk: nothing is downloaded or written by an install process beyond the local memory files the skill itself may create after user confirmation.
Credentials
The skill requests no environment variables, no credentials, and no external config paths beyond ~/home-buying/. This is proportionate to the stated purpose of local workflow guidance and note-taking.
Persistence & Privilege
The skill persists decision memory and notes in ~/home-buying/, which is expected for this purpose. It does not request always:true and does not claim to modify other skills or system-wide settings. Be aware the agent is allowed to invoke the skill autonomously by default (platform default); if you do not want automatic activation, confirm activation preference during setup or set the skill to manual invocation.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install home-buying
  3. After installation, invoke the skill by name or use /home-buying
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release with a full home-buying decision workflow from budget setup through closing readiness.
Metadata
Slug home-buying
Version 1.0.0
License
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Home Buying?

Buy a home with budget guardrails, listing scorecards, offer strategy, due diligence triage, and closing readiness checks. It is an AI Agent Skill for Claude Code / OpenClaw, with 377 downloads so far.

How do I install Home Buying?

Run "/install home-buying" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Home Buying free?

Yes, Home Buying is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Home Buying support?

Home Buying is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).

Who created Home Buying?

It is built and maintained by Iván (@ivangdavila); the current version is v1.0.0.

💬 Comments