发现 Skills

Use when designing the analysis framework for a discovery or data analysis project — defines story line, analysis dimensions, sufficiency criteria, and alternative explanations to check

Component stories using Storybook with Svelte CSF. Story patterns, defineMeta, argTypes, snippet-based customization, and visual testing. Keywords: storybook, stories.svelte, defineMeta, Story, args, argTypes, autodocs

This skill defines the single correct architecture for Android projects. Activate it when working on large tasks that touch multiple files and their interconnections within this project.

Convert desktop fonts to optimized web formats with CSS and specimen pages.

Opinionated standards for TypeScript 5.x+. Assumes JavaScript basics; this covers the type system and TS-specific decisions. Based on [TypeScript Documentation](https://www.typescriptlang.org/docs/)...

Orientation to facet-format JIT deserialization (tiering, fallbacks, key types/entry points) and where to look when changing or debugging JIT code

5-phase IoT skill: detect platform, discover devices, control, automate, monitor. Supports Home Assistant, Homebridge/HomeKit, MQTT brokers, and direct HTTP APIs.

Senior IoT Solutions Architect with extensive experience in designing and implementing end-to-end IoT systems. Expert in IoT protocols (MQTT, CoAP, LoRaWAN, Zigbee), edge computing, cloud integration (AWS IoT, Azure IoT Hub, Google Cloud IoT), embedded systems, sensor networks, and industrial IoT (IIoT) applications. Skilled in building scalable, secure, and reliable IoT architectures from hardware to cloud.

CRITICAL: Use for Raft consensus logic, cluster management, and sessions. Triggers on: babuza, babuza framework, babuza getting started, babuza tutorial, babuza example, raft implementation, raft consensus, babuza raft, raft cluster operations, raft session, linearizable read, raft bootstrap, raft join, raft leader

Full-stack WebSocket subscription development. Load when adding WS routes, topic services, or debugging WS data flows

More than 54 structured procedures

Turns a raw product or feature idea into an approved PRD — the product WHY of one change to a capability. Use when a feature, extension, or refactor is being proposed and needs scoping before any technical spec. Classifies the idea (new capability / change to an existing capability / in-shape work needing no pipeline). Does NOT make technical decisions and does NOT produce technical specs.

Use this skill when a user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or when they need guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: 'How do I optimize this query?', 'How do I index this?', 'Why is this query slow?', 'Can you fix my slow queries?', 'What are the slow queries on my cluster?', etc. Do not invoke for general MongoDB query writing unless user asks for performance or index help. Prefer indexing as optimization strategy. Use MongoDB MCP when available.

Use when the user wants to prepare code for open-source release, create reproducible research artifacts, or structure a repository for publication. Triggers on phrases like "publish code", "open source release", "reproducibility", "research repository", "code release", or "prepare for publication".

Validates research, plans, and code against overengineering, underengineering, and hallucination

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when you have a specification or requirements for a multi-step task, before touching any code.

Manage monorepos with Turborepo for workspace configuration, task caching, and CI optimization. Use when building multi-package projects, shared libraries, microfrontends, or when optimizing large codebases and developer/CI workflows.

Add error tracking and performance monitoring to your project services. Use this skill when adding error handling, creating new controllers/routes, instrumenting background jobs or cron tasks, or measuring database/API performance. Supports Sentry, Datadog, New Relic, and other monitoring solutions. ALL ERRORS MUST BE CAPTURED — no exceptions.

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

Audit prompt cache hit rate in Claude Code session transcripts. Cache read = 10% of full cost, so hit rate is a direct signal of latency and cost. Activate: /cache-audit, 'cache hit rate', 'prompt cache audit', 'how much am I saving on cache'.

/Users/filipdopita/.claude/skills/gstack/learn/SKILL.md

5-advisor debate framework with peer review for strategic decisions. Use for DD verdicts, big-bet investments, architectural decisions, pivots, controversial hires, where stakes are high and you want adversarial perspectives before committing. Adapted from tenfoldmarc/llm-council-skill (https://github.com/tenfoldmarc/llm-council-skill).