NeoLabHQOfficial·71 Agent Skills Included

context-engineering-kit

Make AI coding agents more accurate with proven context engineering

Improves AI coding agent accuracy through spec-driven development, multi-agent code review, test-driven development, and self-reflection workflows. Eliminates hallucinations, missed requirements, and sloppy code by adding judge agents, quality gates, and structured planning to every task. Installs as modular plugins so your agent loads only the techniques each project needs.

1,510|154

↗

npx skills add NeoLabHQ/context-engineering-kit --all -g -y

Available:

Tells the AI agent how the plugin marketplace is structured, which plugins exist, and the design rules (commands over skills, specialized agents, minimal tokens) to follow when working in this repository.

All Skills in This Repository (71)

Pure Emerald Level Indicators

📦 In Repo

NeoLabHQ

cause-and-effect

Analyzes problem causes across six Fishbone diagram categories to identify root causes.

why

Applies Five Whys root cause analysis to drill from symptoms to systemic causes.

plan-do-check-act

Guides iterative PDCA cycles for systematic experimentation and continuous process improvement.

root-cause-tracing

Traces bugs backward through call stacks to find original triggers.

analyse

Selects and applies Gemba Walk, Value Stream Mapping, or Muda analysis to codebases and workflows.

analyse-problem

Generates A3 one-page problem analyses with root cause analysis and action plans.

memorize

Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering.

reflect

Evaluates prior AI output against weighted rubrics and triggers iterative refinement until confidence thresholds are met.

critique

Reviews completed work using three parallel judge agents with debate and consensus reporting.

setup-context7-mcp

Configures the Context7 MCP server and registers technology documentation IDs in CLAUDE.md.

setup-codemap-cli

Installs and configures Codemap CLI for codebase visualization and navigation.

setup-serena-mcp

Guides installation and configuration of the Serena MCP server for semantic code retrieval.

Official

Intermediate

Frequently Asked Questions

FAQPage Schema

How to install Context Engineering Kit?▼

Run `npx skills add NeoLabHQ/context-engineering-kit --all -g -y` in your terminal to install all skills globally.

What is context engineering for AI agents?▼

It is the practice of carefully controlling what information an AI agent sees so it produces accurate results. This kit packages proven techniques like reflection, judging, and spec-driven development as ready-to-use plugins.

How does this kit reduce AI hallucinations in code?▼

It uses independent judge agents, self-critique loops, and per-phase code review gates that catch errors before code ships, raising accuracy on large tasks from under 30% to over 70%.

Does it work with Claude Code, Cursor, and other agents?▼

Yes. The skills follow the open agentskills.io standard and work with Claude Code, Cursor, Codex, OpenCode, Gemini CLI, and Antigravity.

Can I install only the plugins I need?▼

Yes. Each plugin (review, TDD, spec-driven development, git, docs, and more) is independent, so you can install only the ones relevant to your workflow.