LLM & Agents

Creates Agentforce agents using Agent Script syntax with 100-point scoring. Use when building AI agents, defining topics and actions, or deploying AiAuthoringBundle (v65+) or GenAiPlannerBundle (v65+) metadata.

Comprehensive Salesforce testing skill with test execution, code coverage analysis, and agentic test-fix loops. Run Apex tests, analyze coverage, generate test patterns, and automatically fix failing tests with 120-point scoring.

Required at end of every task; and before editing/creating AGENTS.md/docs/skills

Expert assistant for authoring Claude Code skills. Creates precise SKILL.md files with proper YAML frontmatter, validates naming conventions, and applies official best practices. Triggers on keywords: writing skills, creating skills, skill authoring, SKILL.md, new skill, skill template, skill validation, skill structure, create skill, update skill

Generates or updates an AGENTS.md file by scanning a repository for structure, commands, tests, and conventions. Use when a user asks to create or improve `AGENTS.md` for a repository.

This skill should be used when writing or improving system prompts for AI agents, providing expert guidance based on Anthropic's context engineering principles.

Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure, progressive disclosure, workflows, validation patterns, and XML formatting.

Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).

Use for testing tasks including test strategy design, writing Vitest unit/integration tests, ensuring coverage, and exploring edge cases. Activate when creating tests, reviewing test coverage, or designing test strategies.

Preview command effects without making changes. Simulates file writes, git operations, agent spawns, and state changes. All reads execute normally for accurate preview. Use --dry-run flag on any command.

Guidelines and workflow for working on Laravel 11 or Laravel 12 applications across common stacks (API-only or full-stack), including optional Docker Compose/Sail, Inertia + React, Livewire, Vue, Blade, Tailwind v4, Fortify, Wayfinder, PHPUnit, Pint, and Laravel Boost MCP tools. Use when implementing features, fixing bugs, or making UI/backend changes while following project-specific instructions (AGENTS.md, docs/).

Generate or update CLAUDE.md/AGENTS.md files for AI coding agents through auto-scanning project files combined with interactive Q&A. Supports multiple tech stacks, development environments, and preserves customizations when updating.

Orchestrates multi-agent workflows by delegating ALL tasks to spawned subagents via /spawn command. Parallelizes independent work, supervises execution, tracks progress in UUID-based output directories, and generates summary reports. Never executes tasks directly. Triggers on keywords: orchestrate, manage agents, spawn agents, parallel tasks, coordinate agents, multi-agent, orc, delegate tasks

PowerShell TDD testing framework guidance for Pester v5+. Use when writing, structuring, or debugging PowerShell unit tests; mocking cmdlets, native commands (bash, git, curl), or .NET types; isolating tests with TestDrive/TestRegistry; capturing output streams; generating code coverage or JUnit/NUnit reports for CI/CD; running parameterized or tagged tests; or troubleshooting Pester Discovery vs Run phase issues.

Comprehensive unit testing framework for Bash and POSIX shell scripts using ShellSpec with TDD/BDD best practices. Use when writing tests for shell scripts, debugging test failures, refactoring scripts for testability, setting up test infrastructure, mocking external dependencies, or implementing test-driven development for Bash/shell projects. Covers test structure, isolation, mocking, output capture, coverage, CI integration, and troubleshooting.

Provides comprehensive guidance for Convex backend development including database operations, queries, mutations, actions, schemas, authentication, file storage, real-time subscriptions, scheduling, HTTP APIs, search, AI agents, and deployment. MUST activate when user asks about: backend data operations, Convex functions, database queries, schemas, real-time data, auth setup, file uploads, scheduled jobs, HTTP endpoints, or any Convex-specific implementation questions. DO NOT activate for frontend UI/styling or general React component questions unrelated to Convex.

Expert assistant for creating Claude Code custom slash commands. Guides command file structure, YAML frontmatter configuration, variable syntax, and best practices. Triggers on keywords: writing commands, creating commands, slash command, custom command, new command, command template, make command, /command, create command, update command

Teaches how to discover, validate, and add llms.txt documentation sources to the blz CLI. Use when adding documentation to blz, finding llms.txt or llms-full.txt files, validating sources, refreshing content, or managing the documentation index. Covers source discovery, dry-run validation, and index file handling.

Design and implement long-term memory systems for AI agents using vector stores, knowledge graphs, and hybrid approaches. Includes benchmarks and decision frameworks. Use when building persistent agent memory, implementing RAG, designing knowledge bases, or when user mentions 'memory', 'RAG', 'vector store', 'knowledge graph', 'long-term memory', 'retrieval', or 'embeddings'.

TypeScript/JavaScript Test-Driven Development with Vitest, strict red-green-refactor methodology, React component testing, and comprehensive coverage patterns. Use when implementing TypeScript features with TDD, writing Vitest tests, testing React components, developing with test-first approach, or when user mentions 'TypeScript TDD', 'Vitest', 'React testing', 'JavaScript TDD', 'red-green-refactor', 'TypeScript unit tests', or 'test-driven TypeScript'.