Evaluate LLM outputs with multi-dimensional rubrics, handle non-determinism, and implement LLM-as-judge patterns. Essential for production LLM systems. Use when testing prompts, validating outputs, comparing models, or when user mentions 'evaluation', 'testing LLM', 'rubric', 'LLM-as-judge', 'output quality', 'prompt testing', or 'model comparison'.
AI-augmented software engineering workflow based on Addy Osmani's methodology. Implements structured planning, chunked implementation, extensive context provision, strategic model selection, human oversight, granular commits, and continuous learning. Treats LLMs as pair programmers requiring clear direction rather than autonomous agents.
Generate or update an AGENTS.md file by analyzing a repository's structure, commands, tests, and conventions. Use when asked to create or improve `AGENTS.md`.
Guide for creating effective skills that extend DAIV agent with specialized knowledge, workflows, or tool integrations. Use this skill when the user wants to create a new skill, update an existing skill, or get guidance on skill design patterns.
Set up Claude Code cloud/mobile environments for AILANG development. Use when starting a new cloud session, when tools are missing (Go, make, gh), or when user says "setup cloud", "setup environment", or mentions mobile Claude Code.
Build LLM-powered applications and pipelines using proven methodology - task-model fit analysis, pipeline architecture, structured outputs, file-based state, and cost estimation. Use when building AI features, data processing pipelines, agents, or any LLM-integrated system. Inspired by Karpathy's methodology and production case studies.
Manage coordinator daemon tasks, approve/reject work, monitor autonomous agents. Use when user asks to delegate tasks, check task status, review agent work, manage the coordinator, or use GitHub-driven approval workflow.
AI-powered code review tool that analyzes code for bugs, style issues, and improvements
Guides AILANG parser development with conventions and patterns. Use when user wants to modify parser, understand parser architecture, or debug parser issues. Saves 30% of development time by preventing token position bugs.
Guide for creating effective skills that extend Claude's capabilities. Use when users want to create a new skill, update an existing skill, or need guidance on skill structure and best practices. Triggers: 'create skill', 'new skill', 'skill template', 'build skill', 'skill structure', 'skill design'.
Test, validate, and add new AI models to the eval suite. Use when user asks to add new models, test model access, check pricing, or update models.yml.
Multi-agent workflow orchestration with state persistence, handoff patterns, and resumable workflows. Use when building multi-agent workflows, coordinating complex tasks, or implementing resumable processes. Triggers: 'orchestration', 'workflow', 'context save', 'handoff', 'multi-agent'.
Design effective MCP tools and Claude Code integrations using the consolidation principle. Fewer, better-designed tools dramatically improve agent success rates. Use when creating MCP servers, designing tool interfaces, optimizing tool sets, or when user mentions 'tool design', 'MCP', 'fewer tools', 'tool consolidation', 'tool architecture', or 'tool optimization'.
Comprehensive research, analysis, and content extraction system. USE WHEN user says 'do research', 'do extensive research', 'quick research', 'minor research', 'research this', 'find information', 'investigate', 'extract wisdom', 'extract alpha', 'analyze content', 'can't get this content', 'use fabric', OR requests any web/content research. Supports three research modes (quick/standard/extensive), deep content analysis, intelligent retrieval, and 242+ Fabric patterns. NOTE: For due diligence, OSINT, or background checks, use OSINT skill instead.
Create and manage AILANG eval benchmarks. Use when user asks to create benchmarks, fix benchmark issues, debug failing benchmarks, or analyze benchmark results.
Optimize and manage AILANG teaching prompts for maximum conciseness and accuracy. Use when user asks to create/update prompts, optimize prompt length, or verify prompt accuracy.
Authoritative templates and scaffolding for creating agent system prompts (primary agents and subagents). This skill should be used when creating new agents, reviewing existing agent prompts for template compliance, verifying agent structure, or extracting knowledge into agent prompts. Contains YAML templates with section-by-section instructions and scaffolding scripts for generating skeleton files.
Personal AI Infrastructure core. AUTO-LOADS at session start. The authoritative reference for how the PAI system works, how to use it, and all system-level configuration. USE WHEN any session begins, user asks about the system, identity, configuration, workflows, security, or any other question about how the PAI system operates.
