Results for “sensitivity-labels”

Use this when reviewing or designing UI for keyboard access, semantic structure, focus handling, labels, contrast, error communication, motion sensitivity, or screen-reader-friendly behavior.

Identify sensitive data exposure vulnerabilities including API key leakage, PII in responses, insecure storage, and unprotected data transmission during security assessments.

Label Noise SGD Provably Prefers Flat Global Minimizers

`analysis-agent`/`task-agent`/`review-agent`: primary-Skill-selected for logs, metrics, traces, alerts, SLI/SLO, or diagnostics; never task owner; skip without signal impact.

Audits test code in any language using the academic testsmells.org 19-smell catalog, producing a severity-ranked report with specific locations and actionable fixes.

Skill for the Observability area of paddock. 105 symbols across 26 files.

Tests APIs for excessive data exposure where endpoints return more data than the client application needs, relying on the frontend to filter sensitive fields. Maps to OWASP API3:2023 Broken Object Property Level Authorization.

Provides practical accessibility patterns for React and Next.js, covering form labeling, semantic HTML, ARIA attributes, keyboard navigation, focus management, and screen reader support.

Observability Designer (POWERFUL)

Strengthen interfaces against edge cases, errors, internationalization issues, and real-world usage scenarios that break idealized designs.

Projeta métricas, logs, traces, dashboards, alertas e SLO com Prometheus, Grafana, Loki, Tempo, Mimir, Zabbix e Alertmanager, incluindo consultas PromQL e boas práticas de alertas.

Benchmarks LLM bias by scoring responses to automatically generated open-ended questions across sensitive attributes, producing a composite fitness score from 0 to 5.

ScepticAgent UI and styles reference. Use whenever the user wants to change the side panel UI, modify highlight colours, update the markdown renderer, work with CSS architecture, add or change category colours, or understand how the sidepanel renders analysis output.

Electric neon glow effects with high-contrast color pairings for bold, attention-grabbing interfaces.

Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready.

Evaluate and improve interface usability using heuristic analysis based on Nielsen's 10 heuristics, Krug's laws, and severity ratings.

Reviews UI accessibility: keyboard, focus, semantics, labels, contrast, motion, forms, dialogs, tables, and screen readers.

Design a comprehensive product metrics dashboard with key metrics, data sources, visualization types, and alert thresholds.

Evaluate UI designs through an emotional resonance lens, identifying what's missing and prescribing specific changes at the copy, motion, and interaction layer.

Use to identify signals of customer vulnerability in support conversations and audit whether they were recognised and acted on. Trigger for "identify vulnerable customers", "did we spot the vulnerability signals", "customers in financial difficulty", bereavement or health disclosures in support, vulnerable customer handling audits, or designing vulnerability recognition for a support team.

CPRA §1798.121 sensitive personal information restrictions and compliance. Covers all 9 sensitive PI categories including SSN, precise geolocation, racial/ethnic origin, biometric, genetic, health, and sex life data. Right to limit use/disclosure, permitted purposes, and implementation.

Explains term sheet key terms, SAFE/convertible note structures, cap table dilution calculations, and negotiation red flags for startup fundraising.

融合分类系统与符号抽象能力，通过符号系统增强分类体系的表达和理解，创造更具表现力的分类框架。

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

Nocaps: Novel Object Captioning at Scale

Implements security-sensitive changes with conservative trust boundaries, secret protection, tests, and verification.

Defines a design system for ElevenLabs with colors, typography, layout, and component tokens for building brand-consistent interfaces.

Holistic evaluation framework for language models measuring accuracy, calibration, robustness, and fairness

Quantifies how sensitive a language model benchmark's reliability and ranking stability are to specific design choices, such as the selection of scenarios, subscenarios, examples, and few-shot prompts. Use when the user has predictions and gold and needs to compute DIoR.

Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors.

Time-Series Data

Documents Sentri's design language with color tokens, typography hierarchy, and layout patterns for a developer-tools brand.

Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores, drug sensitivity data, and gene effect profiles to identify cancer-specific vulnerabilities, synthetic lethal interactions, and validate oncology drug targets.

Performs differential expression analysis on label-free quantitative (LFQ) proteomics data from MaxQuant and DIA-NN outputs, including preprocessing, imputation, statistical testing, and visualization.

Use before sensitive, clinical, identifying, or raw interview data is placed in front of an AI tool, when transcripts or student materials need de-identification, or when a data-minimization gate must run before any analysis or drafting.