Make the architecture's layering machine-enforced so it can't silently erode. Use when a monorepo has a layered/acyclic package graph but nothing prevents back-edges or…
Automatically validate and fix Django import patterns to use absolute modular imports with aliases. Use when writing imports, creating new Python files, modifying existing files,…
Fix import statements across the codebase to align with clean architecture layer boundaries. Use when: fixing imports, layer boundary violations, circular import issues,…
Script Python per parsare file XML e inserire i dati in un database MS Access, utilizzando una tabella di configurazione per la conversione dei tipi (`tipo_access`), saltando i…
Improve readiness criterion C3.1 (Architecture Depth) in the current project by generating architecture documentation. Raises the fulfillment level by one step.
Survey the codebase, pick ONE high-leverage deepening opportunity (filtering out anything already proposed), and publish it as a PRD-shaped GitHub issue via /to-prd-project.
Incrementally implement feature improvements from docs/improvements.md with tests and atomic commits. Focuses on new functionality rather than refactoring.
Use when you want measured, behavior-preserving improvements, not speculative refactors. For profiling-led hot-path optimization specifically, see code-ops-suite:performance.
Refactor and improve code quality. Use for code refactoring, performance optimization, and quality improvements. Includes Context7 refactoring patterns lookup.
[Extended thinking: This workflow implements a sophisticated debugging and resolution pipeline that leverages AI-assisted debugging tools and observability platforms to…
Drives live incident response and postmortems SRE-style: severity triage (P0–P3), log/metric/trace correlation to find what changed, safe mitigation, comms updates, and blameless…
Constructs incident timelines from PagerDuty Events API v2, Datadog Monitors API, and Slack message archives. Correlates alerts with deployment events for root cause analysis.
Guide for optimizing MSBuild incremental builds. Only activate in MSBuild/.NET build context. USE FOR: builds slower than expected on subsequent runs, 'nothing changed but it…
Build resilient data ingestion pipelines from APIs. Use when creating scripts that fetch paginated data from external APIs (Twitter, exchanges, any REST API) and need to track…
Use when implementing features or refactoring with TDD - enforces writing ONE test at a time, implementing minimal code to pass, then repeating, preventing batch test writing that…
Use when analyzing RNA-seq count data from a DESeq2 workflow where you have fitted negative binomial generalized linear models and need to extract final results.
Use when the user asks to build, refresh, or extend a per-repo codebase index; when onboarding to an unfamiliar microservice, library, or infra-heavy repo; when mapping domains,…
High-level technical SEO and site architecture auditor. Invoke to scan local or live environments for indexing, crawl budget, and structural errors. — from WHOISABHISHEKADHIKARI
Use when a task needs the judgment of an Industrial Engineering Technologist/Technician — sizing a time study or work-sampling study to hit a target confidence and precision,…
Use when designing or reviewing the integration layer between Salesforce Industries clouds (Insurance, Communications, Energy & Utilities) and vertical backend systems such as…
Build modern SPAs with Inertia.js and Rails using React, Vue, or Svelte. Use when creating Inertia pages, handling forms with useForm, managing shared props, or implementing…
Inference Latency Profiler - Auto-activating skill for ML Deployment. Triggers on: inference latency profiler, inference latency profiler Part of the ML Deployment skill category.
Pick attention implementation, KV cache strategy, quantization, and speculative decoding for a new inference deployment. Use when you need help with inference optimizer.
Use when you have trained two or more graph neural network models on the same CCS dataset split (using identical hyperparameters, loss functions, and optimization settings) and…
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable — from…
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, o — from…
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 fa — from…
Always-on visible-output token compression for AI programming agents. Use when user asks for fewer tokens, terse coding-agent output, high information-to-ink ratio, compact…
Claude™ is a trademark of Anthropic PBC. ClaudSkills (also referred to as Claude Skills or Claude Code Skills Catalog) is an independent community-curated registry of SKILL.md files, not affiliated with, endorsed by, or sponsored by Anthropic.
Install ClaudSkills — browse 70k+ skills offline, one tap from your home screen.