Data & AI

Query and manage local Vercel AI SDK documentation mirror (271 docs across 24 sections). Search AI SDK UI hooks, streaming, providers, core functions, and React Server Components. Use when implementing AI features or answering AI SDK-related questions.

Updates template files in metasaver-marketplace as the source of truth before applying changes elsewhere. Use when standardizing configs across repos - updates template FIRST, then uses it for remediation. For config skills and domain skills with templates.

Comprehensive patterns and techniques for removing AI-generated verbosity and slop

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. Activated when users work with .xlsx, .xlsm, .csv files for spreadsheet operations or data analysis.

Assembles relevant context for agent spawns with prioritized ranking. Ranks packages by relevance, enforces token budgets with graduated zones, captures error patterns for learning, and supports configurable per-agent retrieval limits.

Relational and NoSQL databases including PostgreSQL, MongoDB, Redis. Master database design, optimization, and management.

Guide experienced developers through REFACTOR phase of TDD cycle - improving code quality while maintaining green tests

Use CloudBase HTTP API to access CloudBase platform features (database, authentication, cloud functions, cloud hosting, cloud storage, AI) via HTTP protocol from backends or scripts that are not using SDKs.

Best practices for creating and updating Claude Code skills including YAML frontmatter structure, description patterns for discoverability, content organization, progressive disclosure, and testing strategies. Use when creating new skills or updating existing skills to follow proven patterns.

Validates data with Yup schema builder using chainable methods, custom rules, and TypeScript inference. Use when validating forms with React Hook Form or Formik, or when needing flexible schema validation.

⚡ PRIMARY TOOL for: 'what's tested', 'find test coverage', 'audit test quality', 'missing tests', 'edge cases', 'test patterns'. Uses claudemem v0.3.0 AST with callers analysis for test discovery. GREP/FIND/GLOB ARE FORBIDDEN.

Use when creating new skills or refactoring existing skills - teaches the progressive disclosure architecture pattern to optimize context window usage by organizing skills into 3 tiers (metadata, entry point, references) and avoiding documentation dumps. Essential before any skill creation or modification work.

Use when designing or architecting Elixir/Phoenix applications, creating comprehensive project documentation, planning OTP supervision trees, defining domain models with Ash Framework, structuring multi-app projects with path-based dependencies, or preparing handoff documentation for Director/Implementor AI collaboration

Expert IoT system architecture covering distributed systems, event-driven design, edge computing, and microservices patterns. Use when designing multi-device systems, planning communication architecture, implementing event-driven patterns, or scaling IoT deployments. Specializes in MQTT-based architectures, state synchronization, and real-time constraints.

Security risk assessment from specifications, manuals, and design documents. Threat modeling (STRIDE/DREAD), asset identification, risk matrix generation, and CRA pre-compliance evaluation. Use for upstream security analysis before implementation. Triggers on: risk assessment, threat modeling, security review, design review, specification analysis, STRIDE, DREAD, attack tree, security requirements, pre-implementation security.

Implement comprehensive input validation on both client and server sides with clear error messages, type checking, and sanitization to prevent security vulnerabilities. Use this skill when validating user input, implementing form validation, checking data types and formats, sanitizing input to prevent injection attacks (SQL, XSS, command injection), validating business rules, providing field-specific error messages, implementing server-side validation for all entry points (API endpoints, web forms, background jobs), using client-side validation for immediate user feedback, applying allowlists over blocklists, validating ranges and required fields, or ensuring consistent validation across the application. Apply this skill when handling any user input, building forms, creating API endpoints, or reviewing code for security and data integrity.

Use when starting work on an unfamiliar project or needing to understand a codebase - performs comprehensive analysis discovering architecture, patterns, dependencies, testing coverage, and improvement opportunities. Do NOT use on projects you already know well or for targeted questions about specific files - use direct exploration instead for focused queries.

Write focused, strategic tests for core user flows with behavior-based testing, clear naming, and proper mocking of external dependencies. Use this skill when writing unit tests, integration tests, or end-to-end tests. When working on files in tests/, __tests__/, spec/, or *.test.ts, *.spec.ts files. When deciding what to test during feature development. When naming test cases descriptively. When mocking databases, APIs, or external services. When focusing on testing behavior rather than implementation details.

Translates educational content about Physical AI and Humanoid Robotics from English to Urdu with technical accuracy and cultural appropriateness.

Oracle DBA and DevOps expertise for Autonomous Database (ADB) on OCI. This skill should be used when managing Oracle Autonomous Databases, writing optimized SQL/PLSQL, configuring security (TDE, Database Vault, Data Safe), implementing HA/DR (Data Guard, PITR), using OCI CLI for database operations, or integrating with Oracle MCP servers for AI-assisted database management. Covers Oracle Database versions 19c, 21c, 23ai, and 26ai.