Skill UI

Audits GitHub Actions workflows that invoke AI coding agents to surface prompt injection and sandbox risks, tracing attacker-controlled inputs through env vars, reusable actions, and workflow references before deployment or code review.

Detects missing zeroization of secrets and flags compiler-optimized removals with mandatory assembly/IR evidence, helping auditors verify C/C++/Rust cryptographic code through dataflow, CFG, and runtime validation.

Guides engineers through a disciplined four-phase debugging workflow so they investigate root causes, analyze patterns, test hypotheses, and implement fixes based on evidence before touching code.

This model provides an engineering operational framework for teams that leverage AI agents to generate large volumes of code. It shifts the focus from simple syntax to process quality, robust architecture design, rigorous testing, and systematic risk control, ensuring the development of highly stable and reliable systems in AI-assisted environments.

This skill helps users create a new Git branch that strictly adheres to established project naming conventions (e.g., Sentry standards). It automatically determines the appropriate branch type (such as `feat`, `fix`, `chore`, etc.) and generates a descriptive, standardized branch name by analyzing the provided work description or local code differences (diff). It guides the entire branching workflow, ensuring proper lineage and classification for code submissions.

This guide provides a deep, investigation-driven methodology for reviewing Django and Django REST Framework (DRF) codebases. It helps identify critical authorization gaps, focusing on Insecure Direct Object References (IDOR) and object-level access failures. Learn how to trace data flows, analyze custom managers, and verify that users can only access resources they are explicitly authorized to view or modify.

Transform recurring debugging patterns or solutions into portable, reusable skills. Use /si:extract to package recurring fixes, lessons, or workflows into standalone SKILL.md files that can be installed in any project. Ideal for capturing complex multi-step solutions that are easy to forget across different codebases.

A comprehensive quick reference for the Option type within fp-ts. This pattern is crucial for handling nullable, optional, or potentially missing values in a functional and type-safe manner. It allows developers to safely compose operations (mapping, flatMapping) on data that might not exist, eliminating verbose null checks and ensuring robust, predictable code flow in TypeScript.

This skill acts as an expert resource for the Makepad layout system. It helps users generate correct layout code and explain advanced UI concepts like flow direction, alignment, padding, and spacing. Use it when positioning, aligning, or structuring widgets in a Makepad application, ensuring responsive and complex UI compositions.

This skill provides a structured workflow for porting existing Semgrep security rules to multiple target languages. It guides users through applicability analysis, test-first rule creation, and validation for each language variant, ensuring consistent and accurate security coverage across polyglot codebases.

A deep expert system for Anthropic's Claude Code CLI. This skill maximizes productivity by managing advanced features like hooks, persistent context via CLAUDE.md, memory management, sub-agent orchestration, and integrating with local development ecosystems. Ideal for complex coding tasks, debugging, and advanced workflow automation.

This skill monitors the performance of Claude Code and the local operating system. It diagnoses slowdowns, measures CPU/RAM/Disk usage, checks API latency, and generates detailed system health reports. It helps determine if the bottleneck is local hardware or the remote API connection, providing actionable corrective suggestions to improve the development workflow.