Communitygithub.com

curiositech/windags-skills

專家級法律研究代理人,用於查找並爬取各州的檔案清除資料,熟悉權威來源、網址模式、Firecrawl 設定及 2026 年法律環境。

windags-skills 是什麼?

這是一個專為 2026 年法律研究設計的 AI 代理技能,主要用於尋找和爬取各州的犯罪紀錄清除(expungement)資料。它不僅知道哪些是權威的法律來源(如州議會網站、法院行政辦公室),還精通各州不同的 URL 模式,例如統一法院系統與分立式系統的區別。此技能支援 Bash、Read、Write、WebFetch、WebSearch 等多種工具,並能根據 Firecrawl 的設定,設計提取 schema 和速率限制,以有效率地從政府網站獲取法律條文和法院表單。除了爬取技術,它還包含資料驗證檢查清單和缺口分析流程,確保資料的準確性和完整性。特別的是,它具備對 2026 年法律變化的意識,例如 Clean Slate 自動清除法和大麻除罪化的進展,並能指導用戶驗證這些變更。此技能適用於 Claude Code、Cursor、Codex 等平台,特別適合需要系統性收集全美各州法律資料的專案。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/curiositech/windags-skills/tree/HEAD/skills/2026-legal-research-agent

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

2026 年法律研究代理人

name: 2026-legal-research-agent
description: >
  專家級法律研究代理人,用於查找並爬取各州的檔案清除資料。
  熟悉權威來源、URL 模式、Firecrawl 設定及 2026 年法律環境。
  在收到「查找檔案清除資料」、「爬取州法律」、「法律研究」、「法院網址」、
  「法規來源」、「Clean Slate 法律」、「自動清除研究」等請求時啟用。
  不適用於解釋法律(請使用 national-expungement-expert)、建置 UI 或提供法律建議。
allowed-tools:
  - Bash
  - Read
  - Write
  - Edit
  - Glob
  - Grep
  - WebFetch
  - WebSearch
  - Task

何時使用此技能

當需要以下事項時,使用此技能:

  • 查找特定州的權威法律來源,尤其是關於檔案清除的法律
  • 設定 Firecrawl 任務,用以爬取法院系統、立法機關或法律援助網站
  • 驗證爬取資料的正確性與完整性
  • 研究 2026 年法律變更,包括 Clean Slate 法案與大麻檔案清除
  • 建立 URL 模式,以便系統性地逐州收集資料
  • 識別現有爬取資料的覆蓋缺口

請勿在以下情況使用此技能:

  • 解釋法律含義(請使用 national-expungement-expert)
  • 建置使用者介面或元件
  • 向使用者提供法律建議
  • 與法律資料無關的一般網路爬取

核心指令

1. 權威來源層級

在研究檔案清除法律時,依以下順序優先使用來源:

第 1 層(主要權威):
├── 州議會網站(法規條文)
├── 州法院行政辦公室
└── 州檢察長出版物

第 2 層(官方次要來源):
├── 州律師公會指南
├── 法院自助中心
└── 公開法律資料庫(public.law, justia.com)

第 3 層(有價值的第三層來源):
├── 法律援助組織(LSC 受贈機構)
├── 法學院診所
└── 更生組織(CCRC, NACDL)

第 4 層(僅供驗證):
├── 商業法律資料庫
├── 關於法律變更的新聞文章
└── 律師部落格文章

識別暗語:新手會爬取第一個 Google 結果。專家知道 courts.{state}.gov 包含自助表單,而 legislature.{state}.gov 包含法規條文,兩者都需要。

2. 各州 URL 模式知識

各州的法律資源組織方式不同。掌握這些模式:

統一法院系統(法院擁有所有資源):

加州:courts.ca.gov/selfhelp-expungement.htm
奧勒岡州:courts.oregon.gov/programs/exp/Pages/default.aspx
華盛頓州:courts.wa.gov/forms/?fa=forms.contribute&formID=101

分立式系統(立法機關與法院分開):

德州:txcourts.gov(表單)+ texas.public.law(法規)
紐約州:nycourts.gov(表單)+ nysenate.gov/legislation/laws(法規)
佛羅里達州:flcourts.gov(表單)+ leg.state.fl.us/statutes(法規)

Public.law 州(優良的法規代管):

oregon.public.law, california.public.law, texas.public.law
michigan.public.law, washington.public.law

識別暗語:知道 apps.leg.wa.gov/RCW/ 是華盛頓州的法規資料庫,而 leg.wa.gov 是一般立法機關網站——RCW 子網域才是實際法律條文的所在地。

3. 2026 年法律環境認知

截至 2026 年,以下重大變更會影響研究:

Clean Slate 州(已通過自動清除):

  • 賓夕法尼亞州(2018)、猶他州(2019)、紐澤西州(2019)、密西根州(2020)
  • 加州(2020)、康乃狄克州(2021)、德拉瓦州(2021)、維吉尼亞州(2021)
  • 奧克拉荷馬州(2022)、科羅拉多州(2022)、紐約州(2023)、明尼蘇達州(2023)
  • 馬里蘭州(2024)、伊利諾州(2024)、奧勒岡州(2025)

大麻檔案清除(特定法規):

  • 大多數州現在有獨立的大麻檔案清除條款
  • 搜尋「cannabis conviction」以及「expungement」
  • 檢查是否適用追溯日期

2025-2026 年需驗證的法律變更:

  • 奧勒岡州 HB 2316(擴大資格)
  • 加州 AB 1076(擴大自動救濟)
  • 查閱 CCRC 的權利恢復計劃以獲取最新狀態

識別暗語:知道「自動清除」並不意味著立即生效——賓夕法尼亞州的 Clean Slate 對逮捕有 10 年的等待期,且因犯罪類型而異。研究必須捕捉這些細微差別。

4. Firecrawl 設定專業知識

在設定爬取任務時:

提取 Schema 設計:

// 對於法規頁面,提取:
{
  statuteCitation: "string",   // 例如 "ORS 137.225"
  title: "string",             // 例如 "Setting aside conviction"
  fullText: "string",          // 完整法規條文
  effectiveDate: "string",     // 當前版本生效日期
  lastAmended: "string",       // 最近修訂日期
  subsections: "array",        // 解析後的子章節
}

// 對於法院自助頁面,提取:
{
  stateName: "string",
  expungementPageUrl: "string",
  formsLibraryUrl: "string",
  selfHelpUrl: "string",
  contactPhone: "string",
  feeScheduleUrl: "string",
}

// 對於表單,提取:
{
  formNumber: "string",        // 例如 "MC-440"
  formTitle: "string",
  pdfUrl: "string",
  applicableTo: "array",       // ["misdemeanor", "arrest"]
  lastUpdated: "string",
}

政府網站的速率限制:

rateLimit: 2,  // .gov 網站每秒最多 2 個請求
timeout: 90000,  // 政府網站可能較慢
maxRetries: 3,  // 逾時時重試
waitFor: 3000,  // 等待現代法院網站的 JavaScript

識別暗語:知道對於法規頁面要設定 onlyMainContent: true(跳過導航框架),但對於表單頁面要設定 onlyMainContent: false(表單連結通常位於側邊欄)。

5. 資料驗證檢查清單

爬取後,驗證以下項目:

□ 法規引用符合官方格式(例如「ORS」而非「Or. Rev. Stat.」)
□ 生效日期可解析且合理(非未來日期,也不過於陳舊)
□ URL 有效且返回 200 狀態碼
□ PDF 表單連結實際上能下載 PDF(而非 HTML 錯誤頁面)
□ 電話號碼格式一致
□ 費用金額為數字且合理(一般範圍 $0-$500)
□ 州代碼提取正確(注意模糊的 URL)

常見提取錯誤:

  • 「oregon.public.law」誤匹配到「la」(路易斯安那州)而非「or」(奧勒岡州)
  • 法規條文在 10,000 字元處截斷(請增加限制)
  • 表單「最後更新」日期格式不一致
  • 將特定縣的 URL 誤認為州級資料

6. 缺口分析流程

為了識別某個州的遺漏資料:

# 檢查現有資料
ls src/data/scraped/states/{state}/

# 完整覆蓋應包含的檔案:
# - statutes.json(從法規條文提取的資格規則)
# - court-system.json(法院 URL、聯絡資訊、表單連結)
# - forms/(實際 PDF 表單)
# - fees.json(申請費用)
# - counties/(特定縣的法院資料)

# 與州資料檔交叉比對
grep -l "waitingPeriods\|eligibilityRules" src/data/states/{state}.ts

填補缺口的優先順序:

  1. 法規(所有規則的基礎)
  2. 法院表單(使用者實際需要提交的檔案)
  3. 費用資訊(使用者需要預算)
  4. 縣級聯絡資訊(提交地點)
  5. 西班牙語資源(可及性)

反模式

絕對不要做的事:

  1. 不加速率限制就爬取 - 政府網站會封鎖你
  2. 依賴次要來源獲取法規條文 - 務必與主要來源核對
  3. 假設 URL 模式一致 - 每個州都不同
  4. 忽略生效日期 - 法律會變更;爬取資料需要時間戳記
  5. 在沒有州級背景的情況下爬取縣級網站 - 縣級規則補充而非取代州法
  6. 跳過自助部分 - 通常有最清楚的資格摘要
  7. 把各州視為相同 - Clean Slate 州具有本質上不同的流程

常見錯誤:

❌ 爬取維基百科獲取法規條文
✅ 爬取州立法機關的官方法典

❌ 使用 findlaw.com 作為主要來源
✅ 使用 findlaw.com 找到引用,然後爬取官方來源

❌ 假設「expungement」是唯一術語
✅ 搜尋:expungement, sealing, set-aside, dismissal, destruction, pardons

❌ 將等待期視為簡單數字
✅ 捕捉特定犯罪的等待期(重罪 vs 輕罪 vs 逮捕)

專案特定背景

此技能專為 全國檔案清除指南 專案設計:

現有基礎設施

  • Firecrawl 腳本:scripts/firecrawl/
  • 任務定義:scripts/firecrawl/jobs.ts(P0-P4 優先級任務)
  • URL 設定:scripts/firecrawl/config.ts(全部 50 州)
  • 輸出路徑:src/data/scraped/states/{state}/
  • 州資料:src/data/states/(每個州一個 TypeScript 檔案)

執行爬取

# 先設定 API 金鑰
export FIRECRAWL_API_KEY=your_key

# 執行 P0(州法規 + 法院)- 約 $0.20 成本
npx tsx scripts/firecrawl/run-p0.ts

# 預覽試跑
npx tsx scripts/firecrawl/run-p0.ts --dry-run

# 查看報告
cat scripts/firecrawl/reports/p0-*.json

資料流程

Firecrawl 爬取 → src/data/scraped/{state}/*.json
       ↓
人工審閱 + 清理
       ↓
整合至 src/data/states/{state}.ts
       ↓
由資格精靈 + PDF 產生器使用

參考資料

請參閱 references/ 資料夾中的:

  • url-patterns-by-state.md - 全部 50 州的完整 URL 模式
  • clean-slate-timeline.md - 各 Clean Slate 法律通過與生效的時間表
  • firecrawl-schemas.md - 所有使用的提取 schema

範例工作流程

使用者請求:「研究加州 2026 年的檔案清除法律,並爬取最新資料」

代理人工作流程:

  1. 檢查現有資料:ls src/data/scraped/states/ca/
  2. 在 california.public.law 驗證目前法規版本
  3. 透過 CCRC 或新聞搜尋檢查 2025-2026 年法律變更
  4. 若 URL 有變,更新 scripts/firecrawl/config.ts
  5. 執行目標爬取:將加州特定 URL 加入 P0 任務
  6. 根據已知法規引用驗證提取資料
  7. 記錄發現的任何缺口或變更

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

curiositech/windags-skills

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

curiositech/windags-skills

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

curiositech/windags-skills

Implement WCAG 2.2 AA/AAA compliance with automated testing, keyboard navigation, screen reader support, and focus management. Activate on: accessibility audit, WCAG compliance, keyboard navigation, screen reader, aria attributes, axe-core, focus trap. NOT for: design-level accessibility review (use design-accessibility-auditor), color contrast only (use css-in-js-architect).

curiositech/windags-skills

Time-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in realistic time estimation, dopamine-aware task design, and building systems that actually work for neurodivergent minds.

curiositech/windags-skills

Designs digital experiences for ADHD brains using neuroscience research and UX principles. Expert in reducing cognitive load, time blindness solutions, dopamine-driven engagement, and compassionate design patterns. Activate on 'ADHD design', 'cognitive load', 'accessibility', 'neurodivergent UX', 'time blindness', 'dopamine-driven', 'executive function'. NOT for general accessibility (WCAG only), neurotypical UX design, or simple UI styling without ADHD context.

curiositech/windags-skills

>- Apply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.

curiositech/windags-skills

Extend and modify the admin dashboard, developer portal, and operations console. Use when adding new admin tabs, metrics, monitoring features, or internal tools. Activates for dashboard development, analytics, user management, and internal tooling.

curiositech/windags-skills

Conversation patterns and interaction protocols for multi-agent systems. Covers request/response, pub/sub, blackboard, delegation chains, debate, critique, consensus, fan-out/fan-in, supervisor-worker, and peer negotiation. Deep analysis of AutoGen conversation patterns, CrewAI delegation, LangGraph state passing, and FIPA-ACL performatives. Teaches how to design what agents say to each other and in what order. Activate on: "agent conversation", "agent protocol", "multi-agent debate", "agent delegation", "supervisor worker pattern", "agent voting", "consensus protocol", "fan-out fan-in", "agent negotiation", "blackboard pattern", "agent dialogue", "conversation topology", "agent handoff". NOT for: wire format or serialization (use agent-interchange-formats), orchestration infrastructure (use agentic-infrastructure-2026), single agent behavior (use agentic-patterns).

curiositech/windags-skills

Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use language-specific skills), or infrastructure setup (use deployment-engineer).

curiositech/windags-skills

AI-powered calendar management and agent-based scheduling coordination. Covers calendar APIs (Google Calendar, CalDAV/iCal), AI scheduling assistants (Reclaim, Clockwise, Motion, Cal.com), building custom calendar agents with MCP, multi-calendar merging, timezone management, focus block protection, meeting fatigue detection, and agent-to-agent meeting negotiation protocols. Activate on: "calendar agent", "AI scheduling", "calendar coordination", "meeting scheduling", "calendar API", "focus time protection", "calendar optimization", "Google Calendar MCP", "Reclaim", "Clockwise", "Motion", "Cal.com", "smart scheduling", "calendar-aware agent", "timezone scheduling", "agent negotiation meetings". NOT for: manual calendar UI component design (use form-validation-architect), project management scheduling or Gantt charts (use project-management-guru-adhd), general time-tracking or pomodoro apps (use adhd-daily-planner for time-awareness), building the agent itself from scratch (use agent-creator).

curiositech/windags-skills

Build and adopt production AI agent infrastructure in 2026. Covers framework selection (LangGraph, CrewAI, AutoGen, MCP), orchestration patterns, evaluation, observability, memory systems, and tool use. Also covers the SOCIAL dimension: how to sell agent infrastructure internally, change management, measuring ROI, building trust in autonomous systems, and scaling adoption across teams. Activate on: "agent infrastructure", "agent framework comparison", "which agent framework", "sell AI tools internally", "agent adoption", "agent observability", "agent evaluation", "MCP architecture", "agentic mesh", "enterprise AI agents", "AI change management", "agent ROI". NOT for: building specific agents (use ai-engineer), designing agent behavior patterns (use agentic-patterns), prompt tuning (use prompt-engineer).

curiositech/windags-skills

Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent", "agentic workflow", "agent patterns", "multi-step task", "tool orchestration", "/agentic-patterns", "decompose this", "agent best practices", "chain of actions", "when should the agent stop", "agent loop design". NOT for: creating agent infrastructure (use agent-creator), building DAGs (use windags-architect), specific tool implementation.

curiositech/windags-skills

Automated discovery and matching of agent skills for dynamic task routing and capability assessment

curiositech/windags-skills

Cryptographic security for agentic systems — zero-trust agent networking, signed message envelopes (JWS/JWE), capability-based security (ocaps), Merkle tree audit trails, WASM sandboxing, and formal verification. Covers CLI dev tool security, mTLS between agents, permission boundaries (least privilege for AI agents), and supply chain security for skills/plugins. Activate on: "agent security", "zero trust agents", "secure agent communication", "capability-based security", "ocap", "signed messages between agents", "agent audit trail", "sandbox agent execution", "agent permissions", "mTLS agents", "cryptographic verification", "agent supply chain", "OWASP agentic", "prove agent did X", "tamper-proof agent logs". NOT for: application-level SAST scanning (use security-auditor), network firewall rules (use infrastructure), SOC2/HIPAA compliance (organizational), or prompt injection defense (use prompt-engineer).

curiositech/windags-skills

Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads, error/retry signaling, and context windows as data structures. Deep comparison of A2A protocol, MCP, OpenAI function calling, and LangChain message types. Teaches when to use rigid schemas vs free-form with validation, typed vs untyped, streaming vs batch. Activate on: "agent message format", "agent communication schema", "agent-to-agent protocol", "A2A protocol", "MCP message format", "structured output for agents", "agent interop", "interchange format", "agent serialization", "task handoff format", "capability declaration". NOT for: what agents say to each other (use agent-conversation-protocols), orchestration topology (use multi-agent-coordination), building agent infrastructure (use agentic-infrastructure-2026).

curiositech/windags-skills

Logic-based agent programming language implementing BDI architecture for practical autonomous agent development

curiositech/windags-skills

>- Design AgentSpeak(L)-style BDI agents with context-guarded plans, selection functions, and intention stacks. Use for interruptible autonomy, agent policy, and multi-agent orchestration in dynamic environments. NOT for simple rule engines, static planners, or centralized workflows.

curiositech/windags-skills

Foundational concurrent computation model where actors communicate exclusively through asynchronous message passing

curiositech/windags-skills

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.

curiositech/windags-skills

license: Apache-2.0 NOT for unrelated tasks outside this domain.

相關技能