Look up NYC ACRIS deeds, mortgages, liens, sales, and ownership history. Use for property transactions or recorded ownership; not permits or violations.
npx skills add https://github.com/AlpacaLabsLLC/skills-for-architects --skill nyc-acris
Look up ACRIS (Automated City Register Information System) property records — deeds, mortgages, liens, and other recorded documents. Uses a 3-table join across Legals, Master, and Parties datasets. No API key required.
/as:nyc-acris 120 Broadway, Manhattan
/as:nyc-acris 1000770001 (BBL)
/as:nyc-acris 1001389 (BIN)
Read ../nyc-property-report/pluto-resolution.md (shared by all 7 NYC due-diligence skills) and follow it: parse the input (address, BBL, or BIN) and resolve via PLUTO.
This skill's delta: parsing the BBL into separate boro/block/lot components (per the shared file) is REQUIRED — the ACRIS Legals table has no combined BBL field. BIN resolution is only needed when the user's input was a BIN.
Dataset IDs and field names are canonical in ../nyc-property-report/socrata-reference.md — on any disagreement, the reference wins.
IMPORTANT: ACRIS requires BBL (not BIN). The Legals table uses separate borough, block, lot fields — not a combined BBL field.
https://data.cityofnewyork.us/resource/8h5j-fqxa.json?borough={boro}&block={block}&lot={lot}&$order=good_through_date DESC&$limit=20
Extract document_id from each row. These are the join keys for the next two queries.
Build a $where clause with the document_ids from Step 3a:
https://data.cityofnewyork.us/resource/bnx9-e6tj.json?$where=document_id IN ('{id1}','{id2}','{id3}',...)&$order=document_date DESC
Key fields: document_id, record_type, crfn, doc_type, document_date, document_amt, recorded_datetime (NOT doc_date/doc_amount/recorded_filed — those fields don't exist and 400)
Same document_ids:
https://data.cityofnewyork.us/resource/636b-3b5g.json?$where=document_id IN ('{id1}','{id2}','{id3}',...)
Key fields: document_id, party_type, name, address_1, city, state, zip
Party types: 1 = Grantor (seller/borrower/assignor), 2 = Grantee (buyer/lender/assignee)
Fetch once to translate doc_type codes to descriptions:
https://data.cityofnewyork.us/resource/7isb-wh4c.json?$limit=200
Common codes: DEED, MTGE (Mortgage), AGMT (Agreement), ASST (Assignment), SAT (Satisfaction), RPTT (Transfer Tax), ALIS (Assignment of Leases), UCC1 (UCC Filing), MCON (Mortgage Consolidation)
For each document_id:
## Property Records (ACRIS) — {Address}
**BBL:** {bbl} (Borough {boro}, Block {block}, Lot {lot})
**Documents found:** {count} (showing 20 most recent)
### Deeds (Ownership)
| Date | Doc Type | Amount | From (Grantor) | To (Grantee) |
|------|----------|--------|----------------|--------------|
| YYYY-MM-DD | Deed | $X,XXX,XXX | ... | ... |
**Current owner (per most recent deed):** {grantee name}
### Mortgages
| Date | Amount | Lender (Grantee) | Borrower (Grantor) |
|------|--------|-------------------|---------------------|
| YYYY-MM-DD | $X,XXX,XXX | ... | ... |
### Other Documents
| Date | Doc Type | Amount | Grantor | Grantee |
|------|----------|--------|---------|---------|
| ... | Assignment | ... | ... | ... |
**Note:** Condo units may have records on both the unit lot and the parent condo lot. If results seem incomplete, try querying the main condo lot as well.
Source: [ACRIS Real Property](https://data.cityofnewyork.us/City-Government/ACRIS-Real-Property-Master/bnx9-e6tj)
If no documents found: "No ACRIS records found for this property."
This skill produces regulatory output. End every report this skill produces — printed in chat or saved to a file — with the canonical disclaimer block from rules/professional-disclaimer.md, followed by one blank line and the machine-readable marker, exactly as shown:
> **Disclaimer:** This is an AI-generated analysis for preliminary planning purposes. All findings must be verified by a licensed professional before use in design, permitting, or regulatory submissions.
<!-- architecture-studio:requires-disclaimer -->
The marker is a single end-of-file sentinel — it appears exactly once, as the last line of the report. The post-write-disclaimer-check hook parses saved .md reports for the marker and blocks the write if the canonical disclaimer block is missing.
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take alpacalabsllc/nyc-acris from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.