CI/CD

首席信息官专家，精通 IT 战略规划、数据管理、信息系统架构、网络安全和数字化转型

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Advanced skill for SnowTower infrastructure administrators. Use for SnowDDL operations, user provisioning, role management, CI/CD deployments, troubleshooting, and Snowflake administration. Triggers on mentions of snowddl, deploy, user creation, role grants, infrastructure changes, or admin operations.

Create Claude Code subagents. Use when user wants to create a subagent, specialized agent, or custom AI assistant for Claude Code.

Create and manage database schema migrations following best practices for versioning, reversibility, and zero-downtime deployments. Use this skill when creating or modifying database migration files, Alembic migrations, Django migrations, Rails migrations, or any schema change scripts. Use this skill when working with database schema evolution, implementing rollback strategies, managing indexes on large tables, or separating schema changes from data migrations. Use this skill when working with files in migrations/, db/migrate/, alembic/versions/, or similar migration directories. Use this skill when creating new tables, modifying columns, adding indexes, establishing foreign key relationships, or managing database versioning in development and production environments.

OPA RBAC policies preventing cluster-admin privilege escalation, restricting privileged verbs, and blocking wildcard permissions.

Enhance uxscii components from sketch to production fidelity. Use when working with .uxm files marked as "fidelity: sketch" or when user wants to add detail and polish to components.

Minimalist, typography-focused portfolio design system inspired by neo-brutalist and Swiss design principles. Emphasizes bold typography, generous whitespace, monochromatic color schemes, and elegant simplicity for developer/designer portfolios.

Completes Java OOP university assignments from PDF specifications with minimal implementation. Use when user provides a PDF assignment file or mentions completing a Java/FOP/OOP homework exercise. Focuses on writing the least code necessary to satisfy requirements.

Instrument API requests with spans and distributed tracing. Use when tracking request latency or debugging API issues.

Unified debugging workflow enforcing root cause protocol. Investigate → Understand → Reason → Fix. Use when debugging bugs, errors, or unexpected behavior.

Use PROACTIVELY when creating research reports, experiment writeups, technical whitepapers, or empirical study documentation. Orchestrates the complete benchmark report pipeline with structure, diagrams, hi-res PNG capture, and PDF export. Provides working scripts, CSS templates, and complete command sequences for publication-quality AI/ML benchmark reports. Not for slides, blog posts, or simple README files.

Auto-triggered debugging skill for bug/issue diagnosis and fix. Runs systematic root cause analysis, unit tests, deep tracing, and implements fixes.

Advanced persistent context management system for web development work that never loses context between Claude Desktop sessions. Automatically tracks, saves, and restores all work context, session history, decisions, and progress across multiple sessions and projects.

Expert code review specialist. Reviews for quality and intent alignment. Use immediately after writing or modifying code, or when user requests code review. Handles both uncommitted changes and targeted file reviews.

Systematic debugging including root-cause tracing (trace backward through call stack), reproduction strategies, pdb/debugpy usage, logging analysis, binary search debugging, and error pattern recognition. Use when debugging errors, tracing bugs through call stacks, investigating production issues, or reproducing intermittent bugs.

Build headless automation and agentic workflows with Google's Gemini CLI. Covers approval modes (default, auto_edit, yolo), file permission model, Edit vs WriteFile tool selection, smartEdit configuration, GEMINI.md context files, settings.json hierarchy, and MCP server integration. Use when building CI/CD pipelines with Gemini, debugging "0 occurrences found" edit failures, configuring --approval-mode for automation, creating long-running agents with --resume, or integrating external services via Model Context Protocol.

Ensures every UI component looks modern and professional. Enforces clean minimal design, neutral color palettes, consistent spacing (8px grid), clear typography hierarchy, and proper interactive states. No gradients, no clutter.

Use when starting a fine-tuning project to determine if fine-tuning is needed, or when evaluating whether a base model meets quality thresholds for a specific domain task

Examples and patterns for writing effective agent and skill descriptions. Use when crafting descriptions that serve as routing keys for Claude's invocation decisions.