Skip to content

AlpacaLabsLLC/skills-for-architects / skills/nyc-property-report

nyc-property-report

Verified

Compile NYC landmarks, DOB, ACRIS, HPD, and BSA findings into one property due-diligence report. Use for a full report; use individual NYC skills for one dataset.

FileKindSize
README.mdmarkdown336 B
SKILL.mdskill md5.9 KB
host-contract.jsonconfig1.7 KB
pluto-resolution.mdmarkdown1.3 KB
socrata-reference.mdmarkdown1.4 KB

socrata-reference.md

View on GitHub
# NYC dataset query procedure

This is an Arch Studio procedure, not a Socrata field dictionary. The [source catalog](../../corpus/sources/catalog.json) owns dataset IDs, original URLs and publisher metadata/column locators. Filter `nyc`, `property` and the relevant domain. Fetch the selected publisher metadata and API documentation before constructing queries; record dataset revision and query scope. Do not assume field names, code meanings, row limits, rate limits or status semantics from plugin prose.

Use an available supported fetch route. Select/filter only fields identified in the actual publisher metadata and safely encode user values; never concatenate untrusted query fragments. Keep credential material out of output and manifests. Page through the selected scope according to the current API behavior and record any cap/truncation. Never label a partial page the full result.

Resolve join keys and coded values from the publisher's current documentation or lookup dataset. Keep original values alongside display labels and preserve one-to-many relationships. A query failure is not zero records; empty results establish only no matching rows in that particular query. Record source, filters, timestamp, matched count, retrieved count and limitations. On a schema error, refresh original metadata before retrying; do not silently retry guessed fields. Respect actual rate-limit responses, bound retries and report remaining gaps.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall