Loading...
Loading...
Found 1,839 Skills
Building and training neural networks with PyTorch. Use when implementing deep learning models, training loops, data pipelines, model optimization with torch.compile, distributed training, or deploying PyTorch models.
Warden skill: evaluates first-pass findings and proposes deterministic lint rules that could permanently catch the same patterns. Requires Warden's multi-pass pipeline (phase 2).
WebGPU fundamentals for high-performance canvas rendering. Covers device initialization, buffer management, WGSL shaders, render pipelines, compute shaders, and web component integration. Use when building GPU-accelerated graphics, particle systems, or compute-intensive visualizations.
Generate production-ready monorepo structures for full-stack applications including frontends (Next.js, React), APIs (Hono, Express), and data pipelines. Use when creating new monorepo projects, scaffolding multi-project architectures (web apps, APIs, workers, CLI tools), setting up shared packages, or configuring workspace tooling with Bun, PNPM, or Yarn.
Multi-route literature expansion + metadata normalization for evidence-first surveys. Produces a large candidate pool (`papers/papers_raw.jsonl`, target ≥1200) with stable IDs and provenance, ready for dedupe/rank + citation generation. **Trigger**: evidence collector, literature engineer, 文献扩充, 多路召回, snowballing, cited by, references, 元信息增强, provenance. **Use when**: 需要把候选文献扩充到 ≥1200 篇并补齐可追溯 meta（survey pipeline 的 Stage C1，写作前置 evidence）。 **Skip if**: 已经有高质量 `papers/papers_raw.jsonl`（≥1200 且每条都有稳定标识+来源记录）。 **Network**: 可离线（靠 imports）；雪崩/在线检索需要网络。 **Guardrail**: 不允许编造论文；每条记录必须带稳定标识（arXiv id / DOI / 可信 URL）和 provenance；不写 output/ prose。
Use when prettier integration with editors, pre-commit hooks, ESLint, and CI/CD pipelines.
Guide for using Docker - a containerization platform for building, running, and deploying applications in isolated containers. Use when containerizing applications, creating Dockerfiles, working with Docker Compose, managing images/containers, configuring networking and storage, optimizing builds, deploying to production, or implementing CI/CD pipelines with Docker.
QCSD Verification phase swarm for CI/CD pipeline quality gates using regression analysis, flaky test detection, quality gate enforcement, and deployment readiness assessment. Consumes Development outputs (SHIP/CONDITIONAL/HOLD decisions, quality metrics) and produces signals for Production monitoring.
Playbook iterativo para llevar proyectos Node y TypeScript (NestJS + React en monorepo) a cumplir Quality Gates de SonarQube sin romper build ni pipelines. Usar cuando se necesite subir cobertura priorizando New Code, eliminar issues nuevos (Bugs, Vulnerabilities, Code Smells), revisar Security Hotspots y controlar duplicacion y deuda tecnica.
Automated PRD generation pipeline from BRD documents - analyzes dependencies, validates readiness, generates PRDs, performs final review, and supports parallel execution
ioredis v5 reference for Node.js Redis client — connection setup, RedisOptions, pipelines, transactions, Pub/Sub, Lua scripting, Cluster, and Sentinel. Use when: (1) creating or configuring Redis connections (standalone, cluster, sentinel), (2) writing Redis commands with ioredis (get/set, pipelines, multi/exec), (3) setting up Pub/Sub or Streams, (4) configuring retryStrategy, TLS, or auto-pipelining, (5) working with Redis Cluster options (scaleReads, NAT mapping), or (6) debugging ioredis connection issues. Important: use named import `import { Redis } from 'ioredis'` for correct TypeScript types with NodeNext.
Guide for using Nushell for structured data pipelines and scripting. Use when writing shell scripts, processing structured data, or working with cross-platform automation.