rohunvora

by rohunvora

Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when buildin...

by rohunvora

Design tools that agents can use effectively, including when to reduce tool complexity. Use when creating, optimizing, or reducing agent tool sets.

by rohunvora

Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpe...

by rohunvora

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks...

by rohunvora

Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity c...

by rohunvora

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-relate...

by rohunvora

Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvement...

by rohunvora

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Cla...

by rohunvora

Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost o...

by rohunvora

Build a design system from scratch using the Design Graph methodology. Use when starting a component library, creating design tokens, establishing ...

by rohunvora

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits...

by rohunvora

Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation ...

by rohunvora

This skill should be used when user wants to learn from their collected references, synthesize patterns across sources, or turn research into frame...

by rohunvora

This skill should be used to fix visual hierarchy when everything looks equally important, CTAs don't stand out, or users miss key information. App...

by rohunvora

This skill should be used when elements feel disconnected, cards float like islands, or groupings are unclear. Applies Law of Proximity, Law of Com...

by rohunvora

This skill should be used when building single-file browser applications, client-side utilities, or interactive tools that need no backend. Covers ...

by rohunvora

This skill should be used when users drop off mid-task, motivation fades, or experiences feel flat. Applies Peak-End Rule, Goal-Gradient Effect, an...

by rohunvora

Use this skill when writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts...

by rohunvora

Generate minimal HTML pages to review Claude Code output in a browser. Use when terminal output is hard to read, when reviewing lists/tables/drafts...

by rohunvora

This skill should be used when the user is stuck, obvious solutions aren't working, constraints feel impossible, or they keep circling back to bad ...

by rohunvora

Use when building anything non-trivial. Enforces a spec → plan → execute → verify loop that prevents "looks right" failures. Creates spec.md, todo....

by rohunvora

Structure an app around objects when starting a complex app from scratch, existing navigation feels messy, users can't find things, or the IA is ge...

by rohunvora

Analyze and improve UI density using Matt Ström's 4-dimensional framework. Use when interfaces feel too sparse, too cluttered, or when users compla...