Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
tensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
majiayu000/claude-skill-registry 163
-
containers
Core Principles:
majiayu000/claude-skill-registry 163
-
sf-deploy
Comprehensive Salesforce DevOps automation using sf CLI v2. Use when deploying metadata, managing scratch orgs, setting up CI/CD pipelines, or troubleshooting deployment errors.
majiayu000/claude-skill-registry 163
-
production-deployment-phase
Standard Operating Procedure for /ship-prod phase. Automated staging→production promotion.
majiayu000/claude-skill-registry 163
-
containers
Core Principles:
majiayu000/claude-skill-registry 163
-
make-distilled
Transform raw captured content into distilled knowledge by extracting summary, key points, principles, patterns, entities, and quotes, storing the result in the distilled/ directory.
majiayu000/claude-skill-registry 163
-
inference-latency-profiler
Inference Latency Profiler - Auto-activating skill for ML Deployment.
Triggers on: inference latency profiler, inference latency profiler
Part of the ML Deployment skill category.
majiayu000/claude-skill-registry 163
-
unsloth-lora
Configuring and optimizing 16-bit Low-Rank Adaptation (LoRA) and Rank-Stabilized LoRA (rsLoRA) for efficient LLM fine-tuning using triggers like lora, qlora, rslora, rank selection, lora_alpha, lora_dropout, and target_modules.
majiayu000/claude-skill-registry 163
-
docker-optimizer
Reviews Dockerfiles for best practices, security issues, and image size optimizations including multi-stage builds and layer caching. Use when working with Docker, containers, or deployment.
majiayu000/claude-skill-registry 163
-
api-response-optimization
Optimize API response times through caching, compression, and efficient payloads. Improve backend performance and reduce network traffic.
majiayu000/claude-skill-registry 163
-
api-spectral
API specification linting and security validation using Stoplight's Spectral with support for OpenAPI, AsyncAPI, and Arazzo specifications. Validates API definitions against security best practices, OWASP API Security Top 10, and custom organizational standards. Use when: (1) Validating OpenAPI/AsyncAPI specifications for security issues and design flaws, (2) Enforcing API design standards and governance policies across API portfolios, (3) Creating custom security rules for API specifications in CI/CD pipelines, (4) Detecting authentication, authorization, and data exposure issues in API definitions, (5) Ensuring API specifications comply with organizational security standards and regulatory requirements.
majiayu000/claude-skill-registry 163
-
cost-optimized-llm
Implement cost-optimized LLM routing with NO OpenAI. Use tiered model selection (DeepSeek, Haiku, Sonnet) to achieve 70-90% cost savings. Triggers on "LLM costs", "model selection", "cost optimization", "which model", "DeepSeek", "Claude pricing", "reduce AI costs".
majiayu000/claude-skill-registry 163
-
api-contract-validator
Validates type contracts between TypeScript interfaces and Pydantic models. Detects field mismatches and type inconsistencies. Related: frontend-backend-mapper for endpoint discovery.
majiayu000/claude-skill-registry 163
-
kanidm-expert
Expert in Kanidm modern identity management system specializing in user/group management, OAuth2/OIDC, LDAP, RADIUS, SSH key management, WebAuthn, and MFA. Deep expertise in secure authentication flows, credential policies, access control, and platform integrations. Use when implementing identity management, SSO, authentication systems, or securing access to infrastructure.
majiayu000/claude-skill-registry 163
-
aws-s3-management
Configure S3 buckets with security, lifecycle, and replication policies
majiayu000/claude-skill-registry 163
-
tech-debt-resolver
Loop automatizado de melhoria contínua que usa o Chat RAG para identificar débitos técnicos, implementa correções, reingere a base de conhecimento e valida até eliminar 100% dos débitos.
majiayu000/claude-skill-registry 163
-
github-issue-filer
File AnyPod GitHub issues (bug or feature) with the official templates and publish them through the gh CLI.
majiayu000/claude-skill-registry 163
-
vercel-cost-tuning
Optimize Vercel costs through tier selection, sampling, and usage monitoring.
Use when analyzing Vercel billing, reducing API costs,
or implementing usage monitoring and budget alerts.
Trigger with phrases like "vercel cost", "vercel billing",
"reduce vercel costs", "vercel pricing", "vercel expensive", "vercel budget".
majiayu000/claude-skill-registry 163
-
bundle-optimization
Bundle size reduction strategies, icon optimization, tree-shaking, and performance analysis. Use when reducing bundle size or optimizing imports.
majiayu000/claude-skill-registry 163
-
admin-infra-oci
Deploys infrastructure on Oracle Cloud Infrastructure (OCI) with ARM64 instances (Always Free tier eligible).
Handles compartments, VCNs, subnets, security lists, and compute instances.
Use when: setting up Oracle Cloud infrastructure, deploying ARM64 instances, troubleshooting OUT_OF_HOST_CAPACITY errors, optimizing for Always Free tier.
Keywords: oracle cloud, OCI, ARM64, VM.Standard.A1.Flex, Always Free tier, OUT_OF_HOST_CAPACITY, oci compartment, oci vcn
majiayu000/claude-skill-registry 163
-
clojure-charred
High-performance JSON and CSV parsing library for Clojure. Use when working with JSON or CSV data and need fast in Clojure, efficient parsing/writing with a clojure.data.json/clojure.data.csv compatible API.
majiayu000/claude-skill-registry 163
-
hsl-to-oklch-converter
This skill converts HSL color values to OKLCH color values. It can process single or multiple colors, provided either directly by the user or from a specified file.
majiayu000/claude-skill-registry 163
-
vercel-analytics
Implements privacy-friendly web analytics with Vercel Analytics for traffic insights and Web Vitals. Use when tracking page views and performance metrics in Next.js applications deployed on Vercel.
majiayu000/claude-skill-registry 163
-
ops-incident-response
Structured workflow for production incident management following SRE best practices.
Covers incident declaration, triage, coordination, resolution, and post-mortem.
majiayu000/claude-skill-registry 163