Loading...
Loading...
Found 1,237 Skills
Complete Convex development mastery — functions (queries, mutations, actions, HTTP actions), schema design, index optimization, argument/return validation, authentication, security patterns, error handling, file storage, scheduling, crons, aggregates, OCC handling, denormalization, TypeScript best practices, and production-ready code organization. The definitive Convex skill. Use when building any Convex backend: writing functions, designing schemas, optimizing queries, handling auth, adding real-time features, setting up webhooks, scheduling jobs, managing file uploads, or reviewing/fixing Convex code. Triggers on: convex, query, mutation, action, ctx.db, defineSchema, defineTable, v.id, v.string, v.object, withIndex, ConvexError, internalMutation, httpAction, ctx.scheduler, ctx.storage, OCC, convex best practices, convex functions, convex schema, convex performance, "how do I do X in Convex".
Agent behavioral profiles that standardize how different LLMs behave. Load this skill when you need to: (1) adopt a specific behavioral mode for a task, (2) switch between creative/strict/talkative modes, (3) ensure consistent behavior across different models. Profiles define personality, decision heuristics, communication style, and quality standards.
Best practices for building Harper applications, covering schema definition, automatic APIs, authentication, custom resources, and data handling. Triggers on tasks involving Harper database design, API implementation, and deployment.
Type-driven design principle: transform unstructured data into structured types at system boundaries, making illegal states unrepresentable. Use when writing or reviewing code that validates input, designs data types, defines function signatures, handles errors, or models domain logic. Use when you see validation functions that return void/undefined, redundant null checks, stringly-typed data, boolean flags controlling behavior, or functions that can receive data they shouldn't. Triggers on: "parse don't validate", "type-driven design", "make illegal states unrepresentable", "input validation", "data modeling", "refactor types", "strengthen types", "smart constructor", "newtype", "branded type".
Agent definition conventions. Use when creating or modifying agents at any level (~/.claude/agents/, .claude/agents/, or project-local). Validate frontmatter, update README.md index. NOT for creating skills, MCP servers, or modifying CLAUDE.md.
Authoritative MCU chip specification query Skill. Auto-activates when users work with MCU/embedded development, chip selection, hardware design, or peripheral configuration. Queries chip parameters, pin definitions, TRM registers, and programming guides via the ChipCtx MCP interface. Trigger keywords: chip models (STM32/ESP32/nRF, etc.), pin definitions, peripheral configuration, UART/SPI/I2C/ADC, registers, datasheets.
MUST READ before writing or modifying ADK agent code. ADK API quick reference for Python — agent types, tool definitions, orchestration patterns, callbacks, and state management. Includes an index of all ADK documentation pages. Do NOT use for creating new projects (use adk-scaffold).
Define corporate color palettes based on Catppuccin warm tones with light/dark mode conventions. Trigger: When defining brand colors, creating theme systems, or implementing light/dark modes.
Use esta skill SEMPRE que a pessoa usuária pedir para criar diagramas, gráficos, fluxogramas, representações visuais de sistemas, arquitetura ou fluxos. Esta skill atuará guiando a pessoa usuária de forma interativa e didática para definir o modelo de diagrama Mermaid ideal.
Use this skill when building Python desktop applications using PySide6 with strict MVC architecture where all UI is defined by .ui files. Covers architecture patterns, controller/model/view separation, signal handling, and .ui file workflows.
Create and manage Kibana Dashboards and Lens visualizations. Use when you need to define dashboards and visualizations declaratively, version control them, or automate their deployment.
Diagnose and fix broken Goldsky Turbo pipelines interactively. Use whenever the user has a specific pipeline that is misbehaving — error state, stuck in 'starting', connection refused, slow backfill, not getting data in postgres/clickhouse, duplicate rows, missing fields, named pipeline failing ('my base-usdc-transfers keeps failing'), or any symptom where something is wrong with a deployed pipeline. Runs goldsky turbo logs and status commands, identifies root cause, and offers to run fixes. For looking up CLI syntax or error message definitions WITHOUT an active problem, use /turbo-monitor-debug instead.