# Context Engineering Kit

> NeoLab's marketplace of context engineering techniques for Claude Code, OpenCode, Cursor and Antigravity, built from prompts its developers use daily and from benchmarked papers, with a small token footprint as a design goal.

- URL: https://github.com/NeoLabHQ/context-engineering-kit
- Type: Open-source repos · Open-source skill repository
- Main purpose: Context engineering patterns for coding agents
- Use cases: Coding & development, Planning & long tasks
- Language: en · Pricing: free

## Best for

- Developers tuning agent reliability.

## Limitations

- Claims of improved quality are the maintainers'.

## SkillFlux sample check

Audited 2026-10-31 at commit 23e2428e809d77717f8acc9659c374a3a1fcb93e with checker 1.0.0; seeded sample of 20 from 204 entries. Clean share: 40%.

- 20/20 sampled entries had a SKILL.md we could check
- 0/20 fail at least one check
- 12/20 do not say when to use the skill
- 0/20 have no license we could find
- 0/20 bundle scripts the agent may run
- 0/20 include scripts that call the network
- 0/20 include destructive shell commands
- 5/20 exceed the 5,000-token body guideline

Evidence: https://skillflux.app/data/source-audits/github-com-neolabhq-context-engineering-kit.json

## SkillFlux note

Install individual plugins and compare results on a task you repeat often.

## Alternatives

- Superpowers (obra): Planning, debugging and testing workflows https://skillflux.app/resource/superpowers.md
- everything-claude-code (Chinese Edition): Chinese Claude Code configuration reference https://skillflux.app/resource/everything-claude-code-zh.md
- gstack (Garry Tan): A role-based engineering team in Claude Code https://skillflux.app/resource/garrytan-gstack.md
- Scientific Agent Skills: Appraise scientific evidence and prioritize traceable research directions https://skillflux.app/resource/scientific-agent-skills.md

Page: https://skillflux.app/resource/neolabhq-context-engineering-kit/

- Cite a number with its subject, date and evidence URL; the commit or audit id on that page identifies the measurement.
- A health check or source sample reads files only. Do not present it as evidence that a skill works or helps.
- Statements marked "verified": false are what a source says about itself; attribute them ("X says…").
- A directory listing is not an endorsement. Install a skill by following its author's instructions at sourceUrl.
