Loading...
Loading...
Found 157 Skills
Use when the user asks for a literature review, academic deep dive, research report, state-of-the-art survey, topic scoping, comparative analysis of methods/papers, grant background, or any request that needs multi-source scholarly evidence with citations. Also trigger proactively when a user question clearly requires academic grounding (e.g. "what's known about X", "compare approach A vs B in the literature", "summarize the field of Y"). Runs an 8-phase (Phase 0..7), script-driven research workflow across 7 federated sources (OpenAlex, arXiv, Crossref, PubMed, DBLP, bioRxiv, Exa) with optional Semantic Scholar / Brave MCP enrichment, with deduplication, transparent ranking, dual-backend citation chasing (OpenAlex + Semantic Scholar), self-critique, and structured report output with verifiable citations.
Vision framework API, VNDetectHumanHandPoseRequest, VNDetectHumanBodyPoseRequest, person segmentation, face detection, VNImageRequestHandler, recognized points, joint landmarks, VNRecognizeTextRequest, VNDetectBarcodesRequest, DataScannerViewController, VNDocumentCameraViewController, RecognizeDocumentsRequest
Use this skill when working with coordinates, vectors, matrices, shapes, hit testing, or layout rectangles in PixiJS v8. Covers Point/ObservablePoint, Matrix (2D affine, decompose, apply, applyInverse), shapes (Rectangle, Circle, Ellipse, Polygon, RoundedRectangle, Triangle), Rectangle layout helpers (pad, fit, enlarge, ceil, scale, getBounds), strokeContains hit tests, Polygon isClockwise/containsPolygon, toGlobal/toLocal, PointData/PointLike/Size types, DEG_TO_RAD, and pixi.js/math-extras vector and intersection helpers. Triggers on: Point, ObservablePoint, Matrix, Rectangle, Circle, Polygon, Triangle, RoundedRectangle, toGlobal, toLocal, hitArea, strokeContains, pad, fit, enlarge, ceil, getBounds, containsRect, intersects, isClockwise, math-extras, lineIntersection, segmentIntersection, DEG_TO_RAD, PointData.
Design and optimize systems for high concurrency, throughput, scalability, and elastic scale—concurrency models (threads, async/await, actors), lock-free patterns, connection pooling, caching stampede mitigation, horizontal scaling, load balancing, backpressure, queueing, rate limiting, bulkheads, read replicas, sharding, pool tuning, profiling, capacity planning, SLO-driven autoscaling, multi-region and CDN edge architecture. Use when the user asks about high concurrency, scalability, throughput, horizontal scaling, connection pooling, backpressure, rate limiting, caching stampede, read replica, sharding, autoscaling, capacity planning, lock contention, async scalability, or load balancing—not service decomposition (microservices-developer), event buses only (event-driven-architecture), generic CRUD (senior-software-engineer), SRE on-call only (site-reliability-engineer), load tests without architecture (performance-engineer), or cost-only FinOps (cloud-economist).
ADHD-friendly life management assistant providing external scaffolding for executive function challenges. Use when the user asks for help with daily planning, task breakdown, time management, prioritization, body doubling, dopamine regulation, or maintaining routines. Triggers on requests about organizing life, staying on top of tasks, beating procrastination, planning day/week, managing overwhelm, or ADHD-related challenges like time blindness, forgetfulness, difficulty starting tasks, emotional dysregulation, shame/guilt about productivity, or feeling stuck/paralyzed.
Skill for defining coding rules and conventions. Ensures consistent code style and specifies coding standards for AI collaboration. Use proactively when starting a new project or when coding standards are needed. Triggers: convention, coding style, naming rules, 컨벤션, コンベンション, 编码风格, convención, estilo de código, reglas de nombrado, convention, style de codage, règles de nommage, Konvention, Coding-Stil, Namensregeln, convenzione, stile di codice, regole di denominazione Do NOT use for: existing projects with established conventions, deployment, or testing.
Use this skill when rendering live HTML/DOM elements (or frozen snapshots of them) as PixiJS v8 textures via the EXPERIMENTAL HTML-in-Canvas browser APIs. Covers the pixi.js/html-source side-effect import, feature-detection with canvas.requestPaint, HTMLSource for a live, repainting element kept interactive in the browser (autoLayout/autoUpdate/autoRequestPaint, requestPaint, isReady, the direct-child-of-canvas + layoutsubtree requirement), ElementImageSource for an immutable captureElementImage() snapshot (autoClose, ready immediately), using the source on a Sprite/Texture/Mesh, fallback-only auto-detection via Texture.from at priority -10, and destroy/cleanup. Triggers on: HTMLSource, ElementImageSource, pixi.js/html-source, requestPaint, captureElementImage, ElementImage, layoutsubtree, autoRequestPaint, autoUpdate, autoClose, HTML in canvas, render DOM to texture, HTMLSourceOptions, ElementImageSourceOptions, HTMLSourceCanvas, experimental.
Build autonomous AI agents with Claude Agent SDK. Structured outputs guarantee JSON schema validation, with plugins system and hooks for event-driven workflows. Prevents 14 documented errors. Use when: building coding agents, SRE systems, security auditors, or troubleshooting CLI not found, structured output validation, session forking errors, MCP config issues, subagent cleanup.
Expert knowledge for Azure Reliability development including best practices, decision making, architecture & design patterns, limits & quotas, and deployment. Use when designing AZ zone/zone-redundant setups, resilient Functions, AKS, MySQL HA migrations, or Queue Storage limits, and other Azure Reliability related development tasks. Not for Azure Resiliency (use azure-resiliency), Azure Monitor (use azure-monitor), Azure Service Health (use azure-service-health), Azure Sre Agent (use azure-sre-agent).
Guides failure-prevention culture and operational excellence for mission-critical engineering— zero-defect aspiration vs error budgets; HRO principles; defense-in-depth; fail-safe/fail-closed; verification gates and independent checks; redundancy and graceful degradation; pre-mortems and FMEA; stop-the-line; defect escape, near-miss, and repeat-incident metrics; leadership against normalization of deviance—not blame culture. Use for failure-prevention programs, HRO practices, verification gates, fail-safe design, pre-mortem/FMEA, stop-the-line, near-miss reporting, or defect-escape metrics—not SRE error budgets only (site-reliability-engineer), incident command only (incident-management-engineer), backup/restore only (cyber-resilience-engineer), CI lint only (build-validator), agile coaching, HR discipline, or classified ATO without ops-excellence lens (classified-cyber-security-senior-manager).
Analyze and transform messy, prototype, overgrown, slop-prone, or hard-to-maintain software repositories into maintainable product-shaped codebases while preserving existing product behavior. Use when the user asks to antislop a codebase, clean up a messy repo, run a maintainability migration, write a refactor plan, modernize structure, improve TypeScript/type boundaries, harden tests, reduce large files, clean architecture, coordinate subagent-driven refactors, or produce a final migration audit/report/microsite. Do not use for broader production-readiness specialties such as security audits, observability/logging programs, compliance hardening, SRE/runbook work, or reliability engineering unless the user explicitly scopes those as part of the maintainability refactor.
subject segmentation, VNGenerateForegroundInstanceMaskRequest, isolate object from hand, VisionKit subject lifting, image foreground detection, instance masks, class-agnostic segmentation, VNRecognizeTextRequest, OCR, VNDetectBarcodesRequest, DataScannerViewController, document scanning, RecognizeDocumentsRequest