发现 Skills

Create organized bash script structure with color output, menu systems, error handling, and cross-platform support. Standardizes CLI tooling.

Strategic planning and task orchestration agent for breaking down complex tasks into actionable execution plans

Deep research and information-gathering specialist for thorough investigation, pattern analysis, and knowledge synthesis

Customize or personalize a Claude Code plugin for a specific organization's tools and workflows by replacing placeholders and configuring MCP servers.

Deploy specialized AI agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis. Use it for automated multi-agent review workflows, security vulnerability analysis, performance bottleneck detection, and architecture pattern validation.

Synchronize AI swarms with GitHub Projects for visual task management and progress tracking. Use for project board automation, task synchronization, sprint management, and team coordination with GitHub Projects.

Create enterprise-grade interactive charts with Highcharts

Model Selection Skill

Generate standardized Python project structure with pyproject.toml, UV environment, pytest configuration, and workspace-hub compliance. Creates production-ready project scaffolding.

SPARC Architecture phase specialist for system design, component architecture, interface design, scalability planning, and technology selection

SPARC Refinement phase specialist for iterative improvement through TDD, code optimization, refactoring, performance tuning, and quality improvement

A Test-Driven Development methodology enforcing the RED-GREEN-REFACTOR cycle. Use it to write tests first, prevent regressions, and ensure code correctness. Based on obra/superpowers.

Guides agents through CI/CD and release management for data platforms. Use when promoting pipeline code, SQL models, contracts, infra, or configuration across environments with validation gates, staged rollout, and rollback awareness.

Guides practitioners through Delta Lake and medallion-style lakehouse design. Use when building or modifying bronze, silver, and gold layers, Delta Lake mutation patterns, streaming-to-batch lakehouse flows, or Databricks-centered serving architectures.

Use when feature work is complete and changed code should be checked for duplicated logic before final review.

Use this skill when the user's Copilot Studio agent evaluations have come back and they need to interpret scores, diagnose root causes of underperforming test cases, find remediation steps, or analyze patterns to improve their agent. Always use this skill when the user mentions: eval failed, why did this fail, triage, diagnose failure, low pass rate, fix evaluation results, not passing, failing test cases, evaluation results, improve my eval scores, or any situation where eval scores need interpretation and action.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Personal assistant for processing daily voice/text entries from Telegram. Classifies content, creates Todoist tasks aligned with goals, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.

Control Eight Sleep pods (status, temperature, alarms, schedules).

Create requirements.md and tasks.md for a project spec, with traceability and status tracking. Use when the user asks for a spec, requirements, task plan, or execution breakdown (e.g. "做个 spec", "拆任务", "出执行计划", "write a spec", "plan tasks"). Requires an approved specs/<topic>/design.md as input; if missing, route to the brainstorming skill first.

Deploy applications and websites to Vercel with a claimable preview. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment". No authentication required - returns preview URL and claimable deployment link.

JavaScript performance optimization guidelines. Use when writing, reviewing, or refactoring JavaScript/TypeScript code to ensure optimal performance patterns. Triggers on tasks involving loops, data structures, DOM manipulation, or general JS optimization.

Validates Laravel application code against "Laravel Taste" principles — the same design philosophy used by the framework itself. Use when the user wants to audit application-layer code quality, asks "does this follow Laravel conventions?", wants architectural feedback on controllers/models/actions/policies, or says "validate my code", "review this against best practices", "apply Laravel taste", or "check my architecture". Runs the vibemastery-toolkit:laravel-architect agent as the validator for each applicable principle.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.