'aria' 검색 결과

Use this skill when reasoning about generative AI, adversarial machine learning, neural network security, algorithmic fairness, or deep learning fundamentals. This skill channels the thinking of Ian Goodfellow, inventor of Generative Adversarial Networks (GANs). Trigger this skill when the user asks about model robustness, mitigating bias, evaluating AI guardrails, designing generative models, or defending against adversarial attacks. Apply his frameworks of minimax games, adversarial feature learning, and worst-case robustness analysis to shift the user's perspective from average-case optimization to adversarial resilience.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

N-round adversarial review pipeline for empirical research output — the chain from data to LaTeX tables to a manuscript that cites them. A Claude drafter proposes minimal diffs, a deterministic mechanical battery gates every diff from a clean state with a regression gate, a Codex reviewer files check-backed critiques, and a blind judge panel decides residual disputes. Manual-invoke ONLY: trigger when the user explicitly runs /adversarial-empirical-review or names 'adversarial-empirical-review' / 'adversarial empirical review'. Do NOT auto-trigger on generic 'review my results', 'check my tables', or manuscript-editing requests. For prose-style refinement use style-emulation instead; this skill AUDITS WHETHER THE TABLES ARE CORRECT — that each number in the tables is what the analysis code computes, reproduces from the data, and is internally consistent. It is an empirical + code review: the manuscript is read only to resolve table numbering, and prose is not examined.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Orientação de liderança técnica para equipes de engenharia, decisões de arquitetura e estratégia de tecnologia. Inclui analisador de débito técnico, calculadora de escalabilidade de equipes, frameworks de métricas de engenharia, ferramentas de avaliação de tecnologia e templates de ADR. Use ao avaliar débito técnico, escalar equipes de engenharia, avaliar tecnologias, tomar decisões de arquitetura, estabelecer métricas de engenharia ou quando o usuário menciona CTO, débito técnico, débito técnico, escalabilidade de equipes, decisões de arquitetura, avaliação de tecnologia, métricas de engenharia, métricas DORA ou estratégia de tecnologia.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

予算実績差異分析スキル。勘定科目タイプ（収益/費用）に応じた有利・不利差異の自動判定、 差異の分解（価格差異・数量差異）、重要度ランキング、根本原因の仮説提示を行う。 CSVデータのアップロードによる自動分析に対応。 Use when: 予算と実績の比較分析を行いたいとき。月次・四半期の予実管理レポート作成、 差異の原因分析、経営会議向けの予実サマリ作成に使用。 Triggers: "予実差異", "予算実績", "budget variance", "budget vs actual", "予算対比", "差異分析", "variance analysis"

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, create individual components with proper variant sets and variable bindings, set up theming (light/dark modes), document foundations, or reconcile gaps between code and Figma. Also use when the user asks to create or generate any component in Figma — even a single one — since components require proper variable foundations, variant states, and design token bindings to be production-quality. This skill teaches WHAT to build and in WHAT ORDER — it complements the `figma-use` skill which teaches HOW to call the Plugin API. Both skills should be loaded together.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Review form validation so users, including people using screen readers, can understand and correct errors. Check field descriptions, required states, and grouped choices in rendered HTML, while accounting for React forms that handle submission in the browser.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Make form errors understandable to screen reader users
• Check how required fields and grouped choices are marked
• Review validation in React forms

Review drag-and-drop interfaces for keyboard and screen reader access. Inspect the rendered HTML, identify missing alternative controls and status announcements, and guide changes so users can perform equivalent actions through different input methods.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing keyboard alternatives to dragging
• Checking screen reader status announcements
• Inspecting rendered drag-and-drop markup

Review buttons for missing or unclear names, including controls that contain only icons. Add text or labels that explain each action to screen reader users, and replace buttons used for page navigation with links.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding buttons without descriptive names
• Labeling icon-only buttons for screen readers
• Checking whether navigation controls should be links

Review form errors, success messages, and live updates so screen reader users receive important notifications. Check the HTML delivered to the browser, announcement settings, display duration, and dismissal controls, then identify specific elements that need changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing form error announcements
• Checking success message display duration
• Auditing live update notifications

Review tooltips so their extra information is available to screen reader users. Check accessible names, meaning labels available to assistive technology, and links to the elements that trigger them, then suggest fixes and verification steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether tooltip information can be read aloud
• Reviewing links between tooltips and their triggers
• Auditing shared tooltip components

Review collapsible accordion sections for keyboard and screen reader access. Check button triggers, expanded-state attributes, panel links, and heading structure, then guide fixes using the HTML actually delivered to the browser.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking keyboard access to collapsible sections
• Making accordion states clear to screen readers
• Reviewing shared accordion components

Create ad headlines, body text, and static or video concepts tailored to advertising platforms. Use performance data and customer feedback to develop variations, check format limits, and define measurable tests for the next round.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Drafting search ad headlines within character limits
• Developing new variations from ad performance data
• Planning static ads grounded in customer reviews

Store genomic variant records in TileDB-VCF, add samples over time, and retrieve selected samples or genomic regions. Supports batch reading, allele statistics, quality checks, and VCF/BCF export, with workflows for local storage and TileDB Cloud.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a variant dataset and add samples incrementally
• Extract variants for selected samples and genomic regions
• Review allele statistics and sample quality

Forecast sales and other time series with Google’s TimesFM without task-specific training. Prepare regularly spaced CSV data, export predicted values and uncertainty ranges, add explanatory variables, and evaluate forecasts against held-out observations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Forecast monthly sales or revenue from CSV data
• Export predicted values with uncertainty ranges
• Forecast with additional explanatory variables

Create paid ad headlines, descriptions, and primary text for platforms including Google Ads, Meta, LinkedIn, and TikTok. Organize variations by message angle, check character limits, and use performance data to guide the next round.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create headlines and descriptions for Google Ads
• Write social ad copy from several message angles
• Develop new variations from ad performance data

Turn character, environment, and prop concepts into detailed image generation prompts. Plan reference sheets with multiple views and create variations from an approved main image, keeping appearance, materials, and spatial layout consistent across related assets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning character reference sheets with distinct views
• Keeping connected environments visually consistent
• Creating outfit or time-of-day variations from a main image

Check training data and machine learning models for malicious changes, including backdoors that cause unexpected behavior on specific inputs. Combine data quality checks, model analysis, and file integrity verification, then document findings and retest after remediation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Screening third-party data before training
• Checking downloaded model weights before deployment
• Investigating unexpected behavior on specific inputs

Use Intel CHIPSEC to inspect firmware protections, including BIOS write locks and Secure Boot settings. Save test results, extract firmware for offline comparison, and review UEFI variables to investigate configuration weaknesses or suspicious changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Establishing a firmware security baseline for new hardware
• Checking BIOS and SPI flash write protection
• Extracting firmware for comparison with a known-good image

Design tests that assess an AI agent's capabilities and reliability. Covers repeated runs to measure variation, checks for required behavior, and adversarial testing to expose failures that ordinary successful examples may miss.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Measuring variation across repeated runs of the same test
• Checking whether an agent follows required behavior
• Testing responses to unexpected or adversarial inputs

Plan and verify accessibility when changing Handsontable interfaces. Covers keyboard navigation, screen reader messages, focus behavior, and theme contrast, with Playwright tests and axe scans to check changes and resolve reported issues.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding accessible menus or dialogs
• Checking keyboard navigation and focus
• Fixing issues reported by axe scans

Find other occurrences of a known bug across a codebase by tracing its root cause. Gradually broaden search patterns, assess matching candidates, assign severity, and document findings with rules to help prevent recurrence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding similar issues after discovering a vulnerability
• Building CodeQL or Semgrep queries from a known bug
• Checking whether similar code shares the same root cause

Writes, reviews, and debugs property-based tests, which generate inputs to check general rules. Helps test conversions, parsers, normalization, and state invariants, assess whether existing assertions are meaningful, and distinguish faulty rules from implementation bugs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing encode/decode round trips across generated inputs
• Checking normalization and sorting properties
• Reviewing whether existing property tests assert meaningful rules

Validate security patches by comparing vulnerable and patched code against exploit tests, related attack variants, and normal behavior. Produce reproducible logs showing remaining flaws, regressions, newly introduced security failures, and gaps that still need testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Validate an AI-generated security patch before review
• Check related attack variants for incomplete fixes
• Check whether a fix breaks normal behavior

Plan or run DNA analysis to find small genetic changes in tumors, using tumor samples alone or paired with normal tissue. Check sample pairing, contamination, data quality, filtering, and annotations that add information to detected variants.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning analysis of paired tumor and normal samples
• Reviewing filtering and limitations for tumor-only analysis
• Checking quality in whole-genome, exome, or cancer-panel data