数据库搜索

Name: 数据库搜索
Author: diegosouzapw

AI 智能已审计 v1.1.0

作者仓库星标 39
作者更新于实时读取
作者仓库 awesome-omni-skill

流狐档案事实层信息：领域、Agent、信任分、运行环境、权限与网络

领域: AI 智能
兼容 Agent: Claude Code
Cursor
Cline
Codex
Windsurf
Gemini CLI

+20
信任分: 92 / 100 · 已通过审计
作者 / 版本 / 许可: @diegosouzapw · v1.1.0 · 未声明 license
Token 消耗评级: 低消耗
接入复杂程度: 需简单配置
是否需要外部 API Key: 不需要
兼容的系统: 未声明（默认跨平台）
底层运行要求: 无特殊要求
文件与系统权限: 只读
允许写入 / 修改
Shell 执行
网络行为: 仅限本地
安装命令数: 26 条

档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。

需要注意： 未限定 allowed-tools，默认拥有全部工具权限。

输出预览 wprdc.preview

---
name: wprdc
description: Query Pittsburgh's Western PA Regional Data Center (WPRDC) — 363+ datasets covering property ass…
category: AI 智能
runtime: 无特殊运行时
---

# wprdc 输出预览

## PART A: 任务判断
- 适用问题：提示词、Agent 工作流、模型评估或自动化推理。
- 输入要求：目标材料、限制条件、期望输出和验收方式。
- 证据边界：围绕“Quick Start / Commands / search <query>”读取原文规则，不把推断写成作者承诺。

## PART B: 执行结果
- **01** 任务判断：确认你的需求是否属于提示词、Agent 工作流、模型评估或自动化推理，并标出输入、限制和预期结果。
- **02** 执行计划：优先按“Quick Start / Commands / search <query>”拆成步骤，说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果：给出可复制的命令、文件改动、检查清单或内容草稿，并说明如何继续迭代。
- **04** 风险边界：结合 读取文件、写入/修改文件、执行终端命令、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。

## Running Rules
- 读取文件、写入/修改文件、执行终端命令；主要在本地完成；通常不需要额外 API Key。
- 先小样例验证，再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。

SKILL.md SKILL.md

---
name: wprdc
description: Query Pittsburgh's Western PA Regional Data Center (WPRDC) — 363+ datasets covering property ass…
category: AI 智能
source: diegosouzapw/awesome-omni-skill
---

# wprdc

## 什么时候使用
- 把 AI / Agent方向的常用动作沉淀成 Agent 可调用的技能 适合处理AI Agent、提示词、模型评估与自动化推理，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。 把任务拆成可执行、可检查…
- 面向提示词、Agent 工作流、模型评估或自动化推理，优先处理能明确输入、步骤和验收标准的工作。

## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。

## 执行规则
- 围绕「Quick Start / Commands / search <query>」组织步骤，不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令；主要在本地完成；通常不需要额外 API Key。
- 先跑小样例，确认结果可检查后再扩大任务范围。

## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown，不编造命令、平台或依赖。

证据边界与执行链路

作者原文负责流程事实；仓库文件负责来源和命令；流狐只补充适用场景、限制和质量判断。

skill "wprdc" {
  输入层     -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
  上下文层   -> Quick Start / Commands / search <query>
  规则层     -> SKILL.md 触发条件 / 执行顺序 / 输出格式
  运行层     -> 无特殊运行时 | 读取文件、写入/修改文件、执行终端命令 | 主要在本地完成
  安全层     -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
  输出层     -> 可复制结果 + 检查清单 + 下一步迭代
}

解读按原文结构重写，命令、链接、术语均保留；右侧可核对作者原始 SKILL.md

先判断是否适合

核心用途：把 AI / Agent方向的常用动作沉淀成 Agent 可调用的技能适合处理AI Agent、提示词、模型评估与自动化推理，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。把任务拆成可执行、可检查、可继续迭代的步骤…
适用任务：更适合 AI Agent、提示词、模型评估与自动化推理，尤其是输入、步骤、验收口径可以反复复用的场景。
不宜硬套：如果任务只有一次性问答、来源材料很少，或需要作者没有说明的命令和外部服务，应先降级为普通对话。

作者设计意图

触发依据：使用时机、上下文收集、输出格式和失败处理共同决定它是否适合当前任务。
来源边界：作者原文负责事实，仓库文件负责命令和文件证据；Fluxly 只补充用途、限制和使用判断。

作者的方法与取舍

执行主线：任务围绕「Quick Start / Commands / search 」组织，把触发条件、必要上下文、执行规则和交付标准连成一条可复核的链路。
设计重点：重点不在重复教程，而在解释作者为什么规定这些步骤、哪些条件不可省略，以及结果偏离时应回到哪一层检查。
使用判断：先确认任务与原文边界一致，再决定是否启用；来源没有说明的命令、平台和依赖保持未知，不由 Fluxly 补写。

边界和复核

依赖条件：通常不需要额外 API Key，适合先用小任务验证触发是否稳定。
权限提醒：会涉及 read / write / shell-exec 权限，执行前要说明可读写范围、命令边界和回退方式。
质量标准：结果应包含明确产物、必要证据和下一步动作；如果只是泛泛解释，需要补充输入和验收条件后重跑。

WPRDC - Pittsburgh Regional Data Center

Query 363+ datasets from the Western PA Regional Data Center. Property assessments, air quality, 311 requests, jail census, overdose data, parking, permits, violations — all queryable via SQL without downloading.

Quick Start

# Search for datasets
<skill>/wprdc.py search "property sales"
<skill>/wprdc.py search "air quality" --org allegheny-county

# Get dataset info
<skill>/wprdc.py info property-assessments

# List resources (tables) in a dataset
<skill>/wprdc.py resources property-assessments

# See field schema
<skill>/wprdc.py fields assessments

# SQL query (the killer feature!)
<skill>/wprdc.py query 'SELECT "PARID", "PROPERTYADDRESS" FROM @assessments WHERE "PROPERTYCITY"='"'"'PITTSBURGH'"'"' LIMIT 5'

# Quick parcel lookup
<skill>/wprdc.py parcel 0028F00194000000

# Download a dataset
<skill>/wprdc.py download property-assessments --format csv

Commands

`search <query>`

Search for datasets by keyword.

Options:

--org <name> — Filter by organization (e.g., allegheny-county, city-of-pittsburgh)
--group <name> — Filter by topic group (e.g., health, housing-properties)
--limit <n> — Max results (default: 10)
--json — Raw JSON output

`info <dataset>`

Get detailed information about a dataset, including description, resources, and metadata.

`resources <dataset>`

List all resources (tables/files) in a dataset with their IDs and queryability status.

`fields <resource>`

Show the field schema for a resource. Use shortcut names or resource IDs.

`query <sql>`

Execute SQL queries against live data. This is the power feature!

Important: Column names must be double-quoted because PostgreSQL is case-sensitive:

SELECT "PARID", "PROPERTYADDRESS" FROM @assessments WHERE "PROPERTYCITY"='PITTSBURGH' LIMIT 5

Use @shortcut notation for common tables (see Shortcuts below).

Options:

--json — Raw JSON output
--table — Format as ASCII table

`parcel <pin>`

Quick property lookup by parcel ID. Returns address, assessments, building info, and last sale.

<skill>/wprdc.py parcel 0028F00194000000

`download <dataset>`

Download a resource to a file.

Options:

--resource <id|name> — Specific resource
--format <csv|json|geojson> — Preferred format
--output <path> — Output filename

`orgs`

List all organizations publishing data.

`groups`

List all topic groups (categories).

`shortcuts`

Show available query shortcuts.

Query Shortcuts

Use @shortcut in SQL queries instead of long resource IDs:

Shortcut	Dataset
`@assessments`	Property Assessments (584K parcels)
`@sales`	Property Sales
`@311`	311 Service Requests
`@permits`	PLI Permits
`@violations`	PLI Violations
`@overdoses`	Fatal Accidental Overdoses
`@jail`	Jail Daily Census
`@air-quality`	Air Quality
`@fishfry`	Fish Fry Map

Example:

<skill>/wprdc.py query 'SELECT * FROM @overdoses WHERE "death_year"=2024 LIMIT 10'

Before Querying, Ask Yourself

Scope: Is this City of Pittsburgh only, or all of Allegheny County?
- PLI violations, 311, permits → City of Pittsburgh only (90 neighborhoods)
- Property assessments, overdoses, jail → All of Allegheny County (130 municipalities)
Freshness: When was this dataset last updated? Run info <dataset> first.
Fields: What columns exist? Run fields <resource> before writing SQL.
Size: How many records? Start with LIMIT 10, expand once you know it works.

NEVER Do

NEVER use CAST(), ROUND(), AVG(), or other SQL functions — WPRDC blocks them. You'll get "Access denied: Not authorized to call function". Do aggregation client-side.
NEVER query without LIMIT on large tables — Assessments has 584K rows. Queries timeout. Always add LIMIT.
NEVER assume county-wide coverage for City datasets — PLI violations, 311, permits are City of Pittsburgh only. Aspinwall, Fox Chapel, Mt. Lebanon = separate municipalities, not in the data.
NEVER trust "under maintenance" datasets — County plumbing inspections, housing inspections, food facilities are currently broken. Check info first.
NEVER forget column quoting — UPPERCASE columns need double quotes ("PARID"), lowercase don't (case_year). Wrong quoting = cryptic "column does not exist" errors.
NEVER use wildcards on unindexed text — LIKE '%something%' on large tables will timeout. Be specific.

Common Errors

Error	Cause	Fix
`409 CONFLICT` + "column does not exist"	Unquoted uppercase column	Add quotes: `"PARID"` not `PARID`
`Access denied: Not authorized to call function`	Used CAST/ROUND/AVG	Remove function, process client-side
Timeout / no response	Query too large	Add `LIMIT`, narrow `WHERE` clause
Empty results	Filter mismatch	Check exact string values with a broad query first
"resource not found"	Wrong resource ID	Use `resources <dataset>` to get correct ID

SQL Tips

Quote UPPERCASE column names — PostgreSQL is case-sensitive:

SELECT "PROPERTYADDRESS" FROM @assessments  -- ✓ uppercase needs quotes
SELECT case_year FROM @overdoses            -- ✓ lowercase works without quotes

GROUP BY works, but not aggregate functions:

SELECT "PROPERTYCITY", COUNT(*) as cnt 
FROM @assessments 
GROUP BY "PROPERTYCITY" 
ORDER BY cnt DESC 
LIMIT 10

Check fields first — Column names vary wildly between datasets

Coverage Map (Critical!)

Dataset	Coverage	Municipalities
Property Assessments	All Allegheny County	130 municipalities
Property Sales	All Allegheny County	130 municipalities
Fatal Overdoses	All Allegheny County	By zip code
Jail Census	All Allegheny County	County facility
911 Dispatches	Most of county	111 of 130 municipalities
Air Quality	All Allegheny County	Monitor locations
PLI Violations	City of Pittsburgh ONLY	90 neighborhoods
PLI Permits	City of Pittsburgh ONLY	90 neighborhoods
311 Requests	City of Pittsburgh ONLY	90 neighborhoods

If someone asks about Fox Chapel, Aspinwall, Mt. Lebanon, etc. → Only county-wide datasets apply. No PLI/311 data for suburbs.

Organizations & Topics

Use orgs and groups commands to explore. Major publishers:

allegheny-county (143 datasets) — assessments, health, jail
city-of-pittsburgh (126 datasets) — 311, permits, violations

Example Queries

# Property lookup by parcel ID
<skill>/wprdc.py parcel 0028F00194000000

# Search by address (use SQL)
<skill>/wprdc.py query 'SELECT * FROM @assessments WHERE "PROPERTYHOUSENUM"='"'"'251'"'"' AND "PROPERTYADDRESS" LIKE '"'"'%PASADENA%'"'"''

# Overdose trends by year
<skill>/wprdc.py query 'SELECT case_year, COUNT(*) as deaths FROM @overdoses GROUP BY case_year ORDER BY case_year'

# Filter by neighborhood (City of Pittsburgh only)
<skill>/wprdc.py query 'SELECT "VIOLATION", COUNT(*) FROM @violations WHERE "NEIGHBORHOOD"='"'"'Hazelwood'"'"' GROUP BY "VIOLATION" ORDER BY COUNT(*) DESC LIMIT 10'

# Cross-tab query
<skill>/wprdc.py query 'SELECT combined_od1, race, COUNT(*) FROM @overdoses GROUP BY combined_od1, race ORDER BY COUNT(*) DESC LIMIT 20'

Known Issues (as of Jan 2026)

311 Data stopped updating Feb 2025 — new system transition
County Plumbing Inspections — under maintenance
County Housing Inspections — under maintenance
County Food Facilities — under maintenance

Always run info <dataset> to check last update date before relying on data.

安装命令

一键复制安装选择包管理器,点击右侧复制,粘贴到终端回车即可

npx skills add diegosouzapw/awesome-omni-skill/skills/data-ai/wprdc -y

查看通用安装教程

查看 Skill 原文

兼容工具

Claude Code
Cursor
Cline
Codex
Windsurf
Gemini
OpenCode
Roo Code
AAide
+Augment
GitHub Copilot
OpenClaw
KKiro
Junie
WWarp
Goose
Trae
Kilo Code
OpenHands
Amp
Zencoder
CContinue
AIAider
CodeBuddy
CodeGeeX
Replit Agent

安全审计

92 / 100

已审计

未声明 license/许可。
未限定 allowed-tools，默认拥有全部工具权限。

元信息

来源: github
diegosouzapw/awesome-omni-skill
版本: 1.1.0
English

@diegosouzapw 的其他技能

分类与标签

分类 AI 智能

先判断是否适合

作者设计意图

作者的方法与取舍

边界和复核

WPRDC - Pittsburgh Regional Data Center

Quick Start

Commands

search <query>

info <dataset>

resources <dataset>

fields <resource>

query <sql>

parcel <pin>

download <dataset>

orgs

groups

shortcuts

Query Shortcuts

Before Querying, Ask Yourself

NEVER Do

Common Errors

SQL Tips

Coverage Map (Critical!)

Organizations & Topics

Example Queries

Known Issues (as of Jan 2026)

讨论

`search <query>`

`info <dataset>`

`resources <dataset>`

`fields <resource>`

`query <sql>`

`parcel <pin>`

`download <dataset>`

`orgs`

`groups`

`shortcuts`