Scripting

This skill should be used when reviewing, auditing, or improving existing Claude Code skills to ensure they follow Anthropic best practices, have proper structure, use current domain-specific patterns, and include all necessary resources. It analyzes skill quality, identifies gaps, suggests improvements, and can automatically enhance skills with updated best practices. Trigger terms include review skill, audit skill, improve skill, enhance skill, update skill, check skill quality, skill best practices, fix skill, optimize skill, validate skill structure.

This skill should be used when translating a spec into code using parallel subagents. Use when the orchestrator invokes the implement phase or when executing a well-defined implementation plan.

Automated tooling and detection patterns for analyzing npm dependencies, unused packages, and dead code. Provides tool commands and what to look for—not how to structure output.

Use when exploring Python project structure, finding virtualenv paths (python/pip/pytest), or locating package metadata (name, version, pyproject.toml).

Generate and execute Python code to analyze large log datasets, detect patterns, and extract actionable insights

Detect and fix memory leaks in Python and PyTorch code, especially matplotlib figures and unreleased tensors. This skill should be used during Phase 4 performance optimization when memory usage grows over time.

Format and lint GDScript files using gdscript-formatter. Use after editing GDScript files to ensure code style consistency.

Master Python fundamentals, OOP, data structures, and scripting for data engineering

Use when implementing X-Trend or attention-based trading models. Covers LSTM encoders, cross-attention, self-attention, sequence representations, entity embeddings, Variable Selection Networks, encoder-decoder patterns, Deep Momentum Networks, and interpretable predictions for trend-following strategies.

Proactively analyze git repository status. Use automatically before git operations and during code reviews. Must be used when examining repository state, commit history, or file changes.

Intelligently choose between semantic and text search based on query intent. Automatically selects the best search mode (semantic for concepts, text for exact terms, symbols for definitions) and provides relevant results. Use when user wants to find code.

Expert-level Google Cloud CLI (gcloud) skill for managing GCP resources. This skill should beused when working with gcloud commands, gcp, google cloud, cloud run, cloud scheduler, alloydb,cloud storage, gcs buckets, firebase deploy, gcloud auth, gcloud config, service accounts,workload identity federation, iam permissions, or artifact registry. Use this to install gcloudon macOS, Windows, or Linux. Use this to manage multi-account configuration of GCP with gcloud.Use this to configure authentication on GCP with gcloud for OAuth, service accounts, andWorkload Identity Federation (WIF). Use this to set up IAM roles, permissions, and governance.Use this to deploy applications to Cloud Run or Firebase. Use this to manage database instancesincluding AlloyDB and Cloud SQL. Use this to configure GitHub Actions or Cloud Build CI/CDpipelines. Use this to set up Docker container deployments. Use this to write bash scripts forGCP automation. Use this to manage git-triggered deployments or configure API authent

Best practices for Python development including PEP 8, modern Python 3.10+ features, and package management.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging. | Sử dụng khi: chụp màn hình, tự động hóa trình duyệt, debug web, performance, network.

Perform per-change code reviews for C# and Python with language-specific best practices.Use when asked about: code review, review this code, check my code, review PR, best practices,is this code good, code quality, review changes, review my changes.Also triggers automatically after significant code changes.NOT for: architectural assessments, system design reviews (use architecture-review skill instead).

Enterprise systematic code review orchestrator with TRUST 5 principles, multi-language support, Context7 integration, AI-powered quality checks, SOLID principle validation, security vulnerability detection, and maintainability analysis across 25+ programming languages; activates for code reviews, quality standard validation, TRUST 5 enforcement, architectural audits, and automated review automation

Ruby Sinatra environment setup for beginners

Use when creating PRs to enforce code quality standards. Automated detection of anti-patterns, security issues, and code smells. Python 3.8+

Write Python code to interact with ClickHouse using clickhouse-connect. Use when creating ETL scripts, data pipelines, analytics applications, or any Python code that needs to query or insert data into ClickHouse.

Python package reorganization with pyproject.toml inside package directory