DevOps

Guide decision-making using principles and trade-off analysis frameworks. Use when making technical decisions, evaluating alternatives, designing solutions, or choosing between options. Helps establish lasting principles.

This skill should be used when creating extensions for Claude Code or OpenCode, including plugins, commands, agents, skills, and custom tools. Covers both platforms with format specifications, best practices, and the ai-eng-system build system.

LDE（Law-Driven Engineering）の接地（Grounding）検証スキル。LawとTermの両方について、検証手段・観測手段が設定されているか検証する。CI/CD統合のためのチェックリストとスクリプトを提供。使用タイミング: (1) PR作成前の接地確認、(2) CI/CDパイプラインでの自動検証、(3) 「Grounding Mapを検証して」、(4) Law/Term追加後の接地完了確認、(5) Phase Eで接地を完了させる時

Complete Sveltia CMS skill for lightweight, Git-backed content management.Sveltia is the modern successor to Decap/Netlify CMS with 5x smaller bundle (300 KB),faster GraphQL-based performance, and solves 260+ predecessor issues.Use this skill when setting up Git-based CMS for static sites (Hugo, Jekyll,11ty, Gatsby, Astro, SvelteKit, Next.js), blogs, documentation sites, marketingsites, or migrating from Decap/Netlify CMS. Framework-agnostic with first-classi18n support and mobile-friendly editing interface.Prevents 8+ common errors including OAuth authentication failures, TOML formattingissues, YAML parse errors, CORS/COOP policy problems, content not listing, scriptloading errors, image upload failures, and deployment problems. Includes completeKeywords: Sveltia CMS, Git-backed CMS, Decap CMS alternative, Netlify CMS alternative, headless CMS, static site CMS, Hugo CMS, Jekyll CMS, 11ty CMS, Gatsby CMS, Astro CMS, SvelteKit CMS, Next.js CMS, content management, visual editing, markdown CMS, YAM

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

金融数据处理技能：交易数据导入、持仓数据管理、风险指标计算。Use when: 需要处理交易记录、导入持仓数据、计算风险指标、数据清洗验证。Triggers: "交易", "持仓", "导入", "数据", "IBKR", "风险", "净值", "回撤"

Comprehensive security specialist that performs vulnerability assessments, secure code reviews, dependency audits, and provides remediation guidance following OWASP, CWE, and industry security standards

SmartACE (Agentic Context Engineering) workflow engine with MCP-B (Master Client Bridge) and AMUM-QCI-ETHIC module. Dual database architecture using DuckDB (analytics) + SurrealDB (graph). Uses Blender 5.0 (bpy) and UE5 Remote Control. Use when (1) MCP-B agent-to-agent communication (INQC protocol), (2) AMUM 3→6→9 progressive alignment, (3) QCI quantum coherence states, (4) ETHIC principles enforcement (Marcel/Anthropic/EU AI Act), (5) SurrealDB graph relationships, (6) DuckDB SQL workflows, (7) ML inference with infera/vss, (8) Blender 5.0 headless processing, (9) UE5 scene control, (10) DuckLake time travel.

This skill should be used when working with the Ghostmind development system, which uses meta.json as a central configuration for Docker, Compose, Terraform, and Tmux. Use this skill when creating or modifying configurations for any of these components, setting up new applications, or understanding how the system components interconnect.

Search LOCAL BTR context tree (NOT ByteRover/brv). Use when the user asks "how did we implement", "what's our pattern for", "find context about", "query BTR", "search BTR", "find in BTR", or needs project-specific knowledge.

Deploying fine-tuned models for production inference using native kernel optimization, vLLM, or SGLang. Triggers: inference, serving, vllm, sglang, for_inference, model merging, openai api.

Generate and optimize PRDs, Implementation Plans, and Progress Tracking documents optimized as AI artifacts for development agents. Use when creating new feature plans, breaking down long planning docs (>800 lines), or setting up progress tracking. Supports: 1) Create PRD from feature request, 2) Create Implementation Plan from PRD with phase breakdown and subagent assignments, 3) Optimize existing plans by breaking into phase-specific files, 4) Create progress tracking with task assignments. Example: "Create a PRD for user authentication feature" or "Break down the sidebar-polish implementation plan into phase files" or "Create progress tracking for data-layer-fixes PRD".

Debug SystemVerilog testbench failures in the SVC project. Use when a testbench fails (make <module>_tb), to analyze CHECK_* assertion failures, watchdog timeouts, or unexpected signal values. Provides systematic debugging workflow using VCD waveforms and failure output analysis.

BANKSY spatial transcriptomics analysis tool - complete documentation with precise file name-based categorization

Intelligent revenue opportunity discovery system for financial advisors. Extracts structured revenue scenarios from publications and matches them to client books of business to identify high-value opportunities. Use when analyzing industry articles to discover new scenarios, or when scanning client data to find revenue opportunities and generate Top 25 opportunity reports.

DevOps expertise for deployment, CI/CD, infrastructure, and automation

Follow these patterns when designing guardrails validation contracts in OptAIC. Use for signal bounds, dataset schemas, portfolio constraints, PIT validation, and other domain-specific validation rules. Covers the "Law vs Police" architecture where Definitions contain contracts and the Engine enforces them.

Guide for creating Claude Code hooks - shell commands that execute at specific lifecycle events (SessionStart, SessionEnd, PreToolUse, PostToolUse, etc.). Use when users want to automate actions, add validation, logging, or integrate external tools into Claude Code workflows.

Generate JSON schemas and Python handlers for Qdrant-based retrieval tools used by the RAG agent to search sitemap-crawled textbook content with URL citations.

Systematic architecture analysis following Understand → Research → Specify → Decompose → Plan workflow. Use for system design, solution evaluation, build vs buy decisions, and task decomposition. Activate when users say "design", "architect", "break down", "best approach", or "should I build".