# NeoLabHQ/context-engineering-kit

Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source alternative.

Repository: https://github.com/NeoLabHQ/context-engineering-kit
Canonical: https://ross.abutalabs.com/products/context-engineering-kit
Homepage: https://neolab.gitbook.io/cek
Language: TypeScript
License: GPL-3.0
License Family: copyleft
Topics: agent, ai, claude, llm, marketplace, cline, cursor, opencode, windsurf, coderabbit
Last push: 2026-08-26T12:58:58+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 20
- inputs: {"age_days": 293, "days_push": 7, "days_rel": 7, "gap_med": 2.0, "n_releases_24m": 45}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1405, forks 149 (observed 2026-08-28T04:04:37.188962+00:00)

## What it is
A hand-crafted collection of Claude Code Skills and plugins implementing context engineering techniques to improve AI coding agent output quality with minimal token usage. It works across multiple agent tools (Claude Code, OpenCode, Cursor, Gemini CLI, etc.) and includes an open-source CodeRabbit alternative.

## Use cases
- improve code quality from claude code agent
- reduce token usage in ai coding assistant
- add spec-driven development workflow to cursor
- automated code review without coderabbit
- install reusable skills for opencode
- make llm coding agent results more predictable

## When to choose
- you use Claude Code, Cursor, OpenCode, or similar AI coding agents and want better, more predictable results
- you want granular, token-efficient plugins based on benchmarked techniques
- you need an open-source alternative to CodeRabbit for code review

## When to avoid
- you don't use AI coding agents in your workflow
- you need a standalone application rather than agent skills/prompts
- you require a permissive license (GPL-3.0)

## Facets
- artifact type: plugin
- maturity: active
- function: prompt-engineering, agent-framework, code-review, developer-tools, documentation
- domain: developer-tools, large-language-models
- platform: cli, cross-platform
- tags: claude-code, context-engineering, cursor, opencode, skills-marketplace, agentskills, token-efficiency, spec-driven-development, coderabbit-alternative, ai-agents, automation, nodejs

## Member repositories
- NeoLabHQ/context-engineering-kit (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:37.188962+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:38:45.797844+00:00, confidence not recorded.
  - readme: https://github.com/NeoLabHQ/context-engineering-kit (fetched 2026-08-28T04:04:37.188962+00:00, sha 100e23d848ca)
  - homepage: https://neolab.gitbook.io/cek (fetched 2026-08-29T11:52:38.214714+00:00, sha 1d7859e474e5)
- Data as of 2026-08-30T08:39:29.467469+00:00.