Loading...
Loading...
Found 3,866 Skills
MANDATORY before starting any task. Enforces the GPA execution loop that prevents tool call sprawl. G: GATHER phase combines discover queries + memory reads + file reads into one phase. P: Plan in text with zero tool calls. A: APPLY all writes/edits/verification in one phase. One call per tool type per phase — batch all same-type operations together. Covers dependency analysis, batch opportunities, scope estimation, and loop-back triggers.
Analyze code performance, detect bottlenecks, suggest optimizations for algorithms, queries, and resource usage. Use when improving application performance or investigating slow code.
An agent that helps relationship managers prepare for upcoming client meetings by synthesizing a tailored Point of View and detailed Speaker Notes from multiple information sources.
React 성능 최적화 및 베스트 프랙티스 스킬. Vercel Engineering 가이드 기반, 프레임워크 비종속. 다음 상황에서 사용: (1) React 컴포넌트(.tsx, .jsx) 작성 또는 수정 시, (2) 상태 관리, hooks, 리렌더링 최적화 작업 시, (3) 비동기 데이터 페칭 또는 Suspense 패턴 작업 시, (4) 번들 사이즈 최적화 또는 코드 스플리팅 시, (5) 'react', 'useState', 'useEffect', 'useMemo', 'useCallback', 'memo', 'Suspense', 'lazy' 키워드가 포함된 작업 시
Discovers, tests, and manages remote SSH infrastructure hosts and Docker services across 5 hosts (infra.local, deus, homeassistant, pi4-motor, armitage). Use when checking infrastructure status, verifying service connectivity, managing Docker containers, troubleshooting remote services, or before using remote resources (MongoDB, Langfuse, OTLP, Neo4j). Triggers on "check infrastructure", "connect to infra/deus/ha", "test MongoDB on infra", "view Docker services", "verify connectivity", "troubleshoot remote service", "what services are running", or when remote connections fail.
Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.
Create and maintain a repository-root ROADMAP.md as the single source of truth for project milestones and accepted plans. Use when bootstrapping any new project, accepting/completing a plan, defining or updating milestone/version roadmaps, marking milestones as reached/changed/de-scoped, or answering where roadmap and milestone status should be referenced.
Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C/C++/Rust code handling secrets, keys, passwords, or other sensitive data.
Search group Yuque knowledge bases with natural language queries and provide summarized answers with key points and source links. For group use — searches within team/group repositories. Requires group Token.
Document undocumented public APIs in PyTorch by removing functions from coverage_ignore_functions and coverage_ignore_classes in docs/source/conf.py, running Sphinx coverage, and adding the appropriate autodoc directives to the correct .md or .rst doc files. Use when a user asks to remove functions from conf.py ignore lists.
ChatGPT-style deep research strategy with problem decomposition, multi-query generation (3-5 variations per sub-question), evidence synthesis with source ranking, numbered citations, and iterative refinement. Use for complex architecture decisions, multi-domain synthesis, strategic comparisons, technology selection. Keywords: architecture, integration, best practices, strategy, recommendations, comparison.
Production-grade UI/UX guidance and review skill. Transforms vague design feedback into actionable, implementable recommendations. Two modes: `guide` (principles + do/don't rules for modern interfaces) and `review` (structured audit with prioritized fixes). Covers task-first UX, information architecture, CRAP visual hierarchy, accessibility, responsive design, typography, color systems, cognitive psychology, and interaction patterns. Enforces a modern minimal aesthetic — clean, spacious, typography-led — with zero tolerance for emoji-as-icons, decoration-first design, or AI-generated visual excess.