Cut code review time & bugs in half Instantly.
Reviews for AI-powered teams who move fast (but don’t break things) ↗
home / skills / neolabhq / context-engineering-kit
neolabhq/context-engineering-kit
Handcrafted plugin marketplace focused on improving agent result quality. Supports Claude Code, OpenCode, Cursor, Windsurf, and Cline.
11 skills
GitHubSponsored
software-architecture
neolabhq/context-engineering-kit
342
Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.
subagent-driven-development
neolabhq/context-engineering-kit
342
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
context-engineering
neolabhq/context-engineering-kit
342
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
notes
neolabhq/context-engineering-kit
342
This skill adds non-invasive git notes to commits, enabling metadata tracking and review status without altering history.
kaizen
neolabhq/context-engineering-kit
342
This skill applies continuous improvement and error-proofing to code, architecture, and workflows, guiding small iterative changes that prevent errors and
prompt-engineering
neolabhq/context-engineering-kit
342
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.
test-driven-development
neolabhq/context-engineering-kit
342
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
multi-agent-patterns
neolabhq/context-engineering-kit
342
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
thought-based-reasoning
neolabhq/context-engineering-kit
342
This skill guides you through chain-of-thought prompting and related techniques to enhance complex reasoning with structured templates and decision matrices.
worktrees
neolabhq/context-engineering-kit
342
This skill helps you manage multiple git worktrees across branches, enabling context switching and isolated testing without stashing.