Protocol health check skill - ensures AI protocol layer integrity and compliance. Supports file validation, naming conventions, and token analysis.
Ask clarifying questions and get approval before implementation.
Guide for benchmarking FlashInfer kernels with CUPTI timing
Securely connect to and manage remote Linux/Unix servers via SSH. Execute commands, transfer files (SCP/SFTP), set up port forwarding and tunnels. Use when the user asks to SSH into a server, connect to a remote machine, run remote commands, upload/download files to servers, set up tunnels, or perform server administration tasks. Works on Windows, macOS, and Linux.
Amazon SageMaker for building, training, and deploying machine learning models. Use for SageMaker AI endpoints, model training, inference, MLOps, and AWS machine learning services.
Structured code review criteria for pre-implementation plan review (Critic) and post-implementation security/quality review. Covers security, performance, maintainability, and correctness with severity ratings.
Add a new endpoint or endpoints to Ghost's Admin API at `ghost/api/admin/**`.
This skill should be used when the user asks to "pentest WordPress sites", "scan WordPress for vulnerabilities", "enumerate WordPress users, themes, or plugins", "exploit WordPress vulnerabilities", or "use WPScan". It provides comprehensive WordPress security assessment methodologies.
**Activation**: `/rollback` or `/rollback <phase>`
Three.js lighting - light types, shadows, environment lighting. Use when adding lights, configuring shadows, setting up IBL, or optimizing lighting performance.
Author Markdown content files for Nuxt Content using MDC syntax. Use when creating or editing .md files in content/ directories, writing documentation, blog posts, or any content that uses Vue components in Markdown. Triggers on content authoring, MDC syntax, Nuxt Content files.
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Review documentation changes for compliance with the Metabase writing style guide. Use when reviewing pull requests, files, or diffs containing documentation markdown files.
Orchestre cycle de vie modules (planification, exécution, finalisation), génère rapports professionnels, met à jour RAPPORT_GENERAL
Extract learnings from recent git commits, current conversation, and security reviews. Captures both reactive fixes (what went wrong) and preventive patterns (what to always do). Routes learnings to global or skill-specific files so all future Claude sessions benefit. Use when: - User says "/opi" or "opi" - "What did we learn?" - "Extract learnings" / "Update learnings" - End of session reflection - After a security review or audit - After creating reusable components/patterns that other skills should know about Triggers: "opi", "learn", "oppia", "mitä opittiin", "extract learnings", "add learning"
Review release readiness by checking ChangeLogs and version definitions and then create a git tag for the requested version. Use when asked to release or tag a version (e.g., "Please release 0.2.0", "Please tag 0.2.0") or to verify ChangeLog/version consistency before tagging.
Y---
Use when working in this dotfiles repository - modifying shell configs, SSH, neovim, or scripts. Covers symlink architecture, agent selection, and permission model.
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
Set up common Claude Code hooks - auto-formatting after edits, blocking dangerous commands, and notifications. Interactive setup for your project.