**Best-of-N parallel implementation for any task type.**
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →**Best-of-N parallel implementation for any task type.**
Linux kernel development skill grounded in local references/labs and references/lectures materials. Use for kernel modules, system calls, process scheduling, interrupts, locking, memory management, filesystems, networking, architecture, debugging, profiling, and device model work.
Extract best practices from PR review comments to build a curated library for code review automation
Manage Google Docs and Google Drive with full document operations and file management. Includes Markdown support for creating formatted documents with headings, bold, italic, lists, tables, and checkboxes. Also supports Drive operations (upload, download, share, search).
> Transforms any GitHub Pull Request into a beautiful, single-page interactive HTML course that teaches the problem, solution, and code changes.
Guide for adding liquid glass morphism components to React/Next.js projects using Ein UI, built on Shadcn/Radix UI primitives with Tailwind CSS v4.
Senior engineer CLI expertise for AI agents — workflows, safety guardrails, gotchas, and anti-patterns across cloud, IaC, containers, databases, dev tools, and platforms
This directory contains pure Python **Diagnostic Skills** (Tools) for the Android BSP
Use this skill for any Android responsive layout or scaling question — including making apps look right on tablets, foldables, or different screen sizes — and whenever the user mentions appdimens-dynamic, sdp, hdp, wdp, ssp, DimenCache, autoResize, responsive dp/sp, or scaling strategies. Also trigger when the user wants to add the AppDimens Dynamic dependency, choose between Compose vs Views scaling, implement constraint-based resize, or convert plain dp/sp values to scaled equivalents. When in doubt, use this skill — it covers the full lifecycle: install, strategy selection, Compose/Kotlin/Java implementation, and resize.
Use when choosing which Prefactor SDK skill to load for agent instrumentation or for building a custom provider integration on top of @prefactor/core.
writing-content
Search and extract readable text from multi-megabyte Kapture MCP DOM snapshots by eroding away HTML tag soup. Use when you have a saved DOM from kapture_dom and need to find or read visible on-screen content.
This guide defines how to use `ImageGenMcp.SemanticKernel.Plugin` correctly from both:
Generate a professional, client-ready marketing services proposal. This skill produces a complete proposal document that positions the agency/consultant as the clear choice, frames pricing with anchor
You are an AI coding agent with agent-bridge installed. This machine is a **peer** in a bidirectional bridge -- it can both send commands to and receive commands from other paired machines.
Automate Gmail tasks via Rube MCP (Composio): send/reply, search, labels, drafts, attachments. Always search tools first for current schemas.
Use this skill to design, implement, review, and refine frontend features in React 19 with Vite and TypeScript.
The M4 Python API provides programmatic access to clinical datasets for code execution environments. It mirrors the MCP tools but returns native Python types (DataFrames, dicts) instead of formatted s
Molecular dynamics simulation setup, execution, and trajectory analysis
Comprehensive techniques for acquiring, analyzing, and extracting artifacts from memory dumps for incident response and malware analysis.
Self-referential loop until task completion with architect verification
Aftermarket cybernetic network device framework. nhero is the umbrella for all pill-dispenser-as-network-device modifications — from Hero Health hardware RE to PyHole DNS-style medication routing to killdispenser supply chain primitives. One lowercase word. Append-only reference architecture.
Review requirements or plan documents using parallel persona agents that surface role-specific issues. Use when a requirements document or plan document exists and the user wants to improve it.
Analyze MaxText training job performance using tgs_tagger, TraceLens, and IRLens. Use when the user asks to analyze a training run, profile traces, HLO IR, TGS metrics, GPU utilization, or mentions tag_tgs, TraceLens, IRLens, xplane, or performance analysis.
Configures TrueFoundry AI Gateway for unified OpenAI-compatible LLM access. Covers auth (PAT/VAT), model routing, rate limiting, and budget controls.
Set up ongoing competitor monitoring. Use when: defining tracked competitors, scan frequency, change detection alerts.
Breaks complex systems into atomic components, maps their relationships, and reconstructs them in optimized configurations to identify bottlenecks, critical failure points, and redesign opportunities. Use when dealing with complex systems that need simplification, identifying bottlenecks or critical failure points, redesigning architecture or processes for better performance, breaking down problems that feel overwhelming, analyzing dependencies to understand ripple effects, or when optimization requires understanding how parts interact.
Changelog Automation workflow skill. Use this skill when the user needs Automate changelog generation from commits, PRs, and releases following Keep a Changelog format. Use when setting up release workflows, generating release notes, or standardizing commit conventions and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
Use Claude Code's full tool system with any OpenAI-compatible LLM — GPT-4o, DeepSeek, Gemini, Ollama, and 200+ models via environment variable configuration.
Formal Proof Visualization and Verification for Lean 4
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
Configures the project management tool by guiding selection from supported options, applying the implementation guide, updating way-of-working adoption, and recording the decision via /record-decision. Idempotent — detects existing configuration.
Use persistent markdown files for complex task execution. Creates task_plan.md, findings.md, and progress.md. Use when starting multi-step tasks, research projects, or any task requiring >5 tool calls. Solves the EXECUTION problem - staying focused during long-running tasks.
Guidance for using the .NET Aspire CLI to create, initialize, run, update, publish, deploy, and manage Aspire AppHost projects. Use when selecting or explaining Aspire CLI commands, flags, or workflows (new/init/run/add/update/publish/deploy/do/exec/config/cache/mcp), or when upgrading to Aspire 13.1 CLI behaviors. MCP commands (aspire mcp init) are included when explicitly requested.
Git Commit Command
Developer productivity workflows - PR review, CI monitoring, deploy tracking, code metrics
Read any website or search Google, even when sites block bots or are geo-restricted. Handles CAPTCHAs, JavaScript rendering, and anti-bot protection server-side via residential proxies. Returns HTML or structured JSON.
Manage stories on Shortcut.com kanban boards. Use when creating, updating, or listing tasks/stories on Shortcut project management boards. Supports creating stories with descriptions and types (feature/bug/chore), updating story status, and listing active/completed stories. Includes full checklist task management and comment support.
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
Composite: security audit -> production upgrade -> self-evaluation. Use when user says 'audit', 'check the codebase', 'find and fix issues', or 'is this production-ready'.
Create AI avatar and talking head videos with OmniHuman, Fabric, PixVerse via inference.sh CLI. Models: OmniHuman 1.5, OmniHuman 1.0, Fabric 1.0, PixVerse Lipsync. Capabilities: audio-driven avatars, lipsync videos, talking head generation, virtual presenters. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human