데이터·AI 스킬

Produces neutral, section-pinned U.S. legislative bill summaries translating statutory language into plain terms with identifying data, provisions, fiscal impacts, and controversy. Use when summarizing bills, analyzing proposed legislation, preparing bill briefs, digesting committee reports or fiscal notes, or writing legislative updates.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Produces privilege-safe U.S. corporate legal billing summaries from time and expense data. Converts entries into client-friendly narratives with categorized hours, rates, expenses, and milestones while enforcing engagement-letter rules and ethical billing safeguards. Use when asked to create a billing summary, invoice narrative, timekeeper breakdown, expense summary, or fee narrative.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

律师驱动的 AI 数据合规冷启动工作流：律师描述 AI+产业合规需求后，Skill 四步引导完成冷启动——产业信息收集 → 知识库构建 → 数据流图与评估报告 → 以《生成式AI行业网络数据安全风险评估工作手册》为指引的进企调研前文件包。适用于内部律师或 AI 协作代理快速搭建任意 AI 产业（客服/知识助手/营销生成/合同审查/医疗等）的数据合规项目；不用于自动出具正式法律意见、绕过律师复核、未经授权开展外部检索或处理非本项目数据。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generate contextual briefings for legal work. Supports three modes — daily brief (morning summary of legal-relevant items), topic brief (research synthesis on a specific legal question), and incident brief (rapid briefing for developing situations like data breaches or regulatory inquiries).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Summarizes raw background check data into structured executive reports with risk categorization (GREEN/YELLOW/RED). Use when processing criminal records, court filings, employment/education verification, sanctions screening, or adverse media for pre-employment screening, executive due diligence, or investment-grade investigations.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

法外功夫 — Non-legal business skills for lawyers. Decision analysis, game theory, contract design, accounting, finance, microeconomics, law & economics, statistics, and regression analysis distilled into deep, actionable frameworks for legal practice. Each domain includes formulas with LaTeX notation, worked examples, adversarial checklists, and book-aligned structure. | 律师必备的非法律商业技能深度参考：决策分析、博弈论、合同设计、会计、金融、微观经济学、法经济学、统计分析、多元回归。每章都包含完整公式推导、worked examples、对抗清单与经典判例。当用户涉及和解谈判、合同激励、财务尽调、企业估值、损害赔偿计算、反垄断分析、统计证据评估、歧视诉讼回归分析、hold-up、效率违约、Daubert 动议等场景时触发。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

当用户希望对内部 AI 用例、AI 产品功能、LLM 工作流或第三方 AI 供应商进行 AI 治理、法律风险、隐私、合规、采购或供应商风险审查时，使用本技能。当事实或证据缺失时，技能首先提出受理和澄清问题，识别所需的文件和缺失的证据，将用例映射到 AI 治理框架和适用的法律领域，并产出带记分卡、发现、责任方、补救行动和后续问题的初步或最终治理审查。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Scaffolds a structured investigation in scratch/ for empirical research and documentation. Use when the user says "start an investigation" or wants to: trace code paths or data flow ("trace from X to Y", "what touches X", "follow the wiring"), document system architecture comprehensively ("document how the system works", "archeology"), investigate bugs ("figure out why X happens"), explore technical feasibility ("can we do X?"), or explore design options ("explore the API", "gather context", "design alternatives"). Creates dated folder with README. NOT for simple code questions or single-file searches.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Search DigiKey by keyword or part number, check stock and price breaks, retrieve component specifications, and download or synchronize datasheets for an electronics project. Use when the user explicitly wants DigiKey data, a DigiKey prototype-order comparison, or direct datasheet synchronization. For distributor-neutral sourcing, multi-vendor price comparison, or order-file generation, use the bom skill instead.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Review Circuit Weaver's exhaustive placement proposal and apply approved SVG coordinates to a real electrically annotated KiCad PCB. Use after schematic generation for placement optimization, official-reference review, interactive SVG editing, strict reference reconciliation, and PCB placement handoff. Do not treat review artifacts as fabrication data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Performs static analysis of binary code using radare2 and Ghidra — function enumeration, cross-reference tracing, decompilation, and control flow graphs without executing the binary. Use when disassembling or decompiling code, mapping functions, tracing data flow, or building hypotheses before dynamic verification.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generate weekly or monthly status updates from local PM data. Use this skill when: - It's end of week and you need a status update for leadership or stakeholders - You need a monthly executive summary - You want to draft an email update using data from meetings, tracker tickets, and decisions - The user says "weekly update", "status report", "what happened this week?", "weekly summary" - The user says "Friday update", "send status email", "EOW update" Pulls from work logs, meetings, ticket tracker, and decisions — no manual input needed.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Update user personas from new feedback, pilot data, or research. Use this skill when: - New pilot data or feedback reveals changed user behaviors or pain points - Annual persona review is due (1-2x per year) - New user segments are discovered that need persona documentation - Existing personas need validation against recent data

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Synthesize pilot observations into structured debrief reports and spec updates. Use this skill when: - A pilot has completed and you have observation notes, tickets, or feedback transcripts - You need to turn messy pilot data into actionable spec changes - You want to generate edge case user stories from field observations - You need negative acceptance criteria from pilot bugs - You want a structured debrief report for stakeholder communication

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build Opportunity Solution Trees using Teresa Torres' framework for structured product discovery. Use this skill when: - You need to map a desired outcome to opportunities, solutions, and experiments - You want to decide WHAT to build next based on user research and discovery data - You have workshop findings, pilot feedback, or user research to structure into actionable options - You need a visual tree diagram showing the path from outcome to testable experiments

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Behavioral guardrails against the six most common LLM coding failure modes: unstated assumptions, overbuilding, changes beyond the ask, no success condition, claiming done without output, and sprawling non-atomic changes. Use when writing, editing, reviewing or refactoring code, when the user says 'keep it simple', 'surgical change', 'don't over-engineer', 'minimal diff' or 'verify before saying done', or when a change keeps growing beyond the ask. For a full code review, see code-review.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design and implement features from raw data for machine learning models. Use when the user says "engineer features", "feature engineering for X", "create features from this dataset", "transform these variables", "encode categoricals", "handle skew", "create interaction features", "lag features", "extract features from text or dates", "improve model performance with better features", or wants to move from raw columns to model-ready inputs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generate a data dictionary documenting entities, fields, and business rules. Use when the user says "data dictionary", "document the data model", "what fields are in this table", "data definitions", "field descriptions", "CRUD matrix", "entity relationship", "data catalogue", "what data does this system store" - even if they don't explicitly say "data dictionary".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Write a structured client status report for a consulting engagement. Use when a consultant says "write my weekly status update", "I need to send a status report", "draft the client update", "what should be in the weekly report", "client wants a progress update", "help me write the RAG status", "I need to report on blockers", "end of week update to the client", or "help me communicate what's stuck". Also trigger when someone needs to communicate engagement progress, surface blockers to the client, or flag decisions that need to be made by the sponsor.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Analyze and interpret financial statements to surface performance signals, quality concerns, and red flags. Use when an accountant says "review these financials", "analyze the income statement", "look at the balance sheet", "what does the cash flow statement tell us", "check the financial health", "ratio analysis", "are the earnings real", "working capital review", "does this company have liquidity issues", or needs to interpret any of the three core financial statements - even if they don't explicitly say "financial statement review". Also trigger when someone shares P&L, balance sheet, or cash flow data and asks what it means.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Write an ETL operational runbook. Use when the user says "ETL runbook", "pipeline runbook", "data job runbook", "how to operate this ETL", "on-call guide for data pipelines", "what to do when the data job fails", "pipeline troubleshooting guide", "data ops runbook", or needs to document how to operate, monitor, and recover a data pipeline or ETL job - even if they don't explicitly say "runbook".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Write a data pipeline design document. Use when the user says "pipeline design doc", "document this pipeline", "pipeline architecture doc", "data flow document", "how does this pipeline work", "design doc for ETL", "pipeline spec", or needs to capture the architecture, data flow, and operational details of a data pipeline - even if they don't explicitly say "design doc".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Write a data schema specification document. Use when the user says "schema spec", "document this schema", "schema design doc", "data model spec", "table spec", "field definitions", "schema contract", "data dictionary", "define these fields", or needs to formally document a database schema, event schema, or API payload schema - even if they don't explicitly say "schema spec".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run exploratory data analysis on a dataset and produce a structured report. Use when the user says "explore this dataset", "EDA on X", "analyze this data", "what's in this dataset", "summarize this data", "first look at the data", "understand this dataset before modeling", "data quality check", "describe this dataframe", or wants to understand a new dataset before building models or dashboards.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.