Showing 28 verified skills. 284 preview entries are hidden until we confirm a real source. Show preview skills · Why?
You'll ship higher-quality agent outputs by engineering context instead of prompts.
npx skills add NeoLabHQ/context-engineering-kitA curated set of skills built around the idea that better context yields better output. Covers prompt shaping, context compression, result evaluation, and iteration patterns. Designed to run across multiple harnesses: Claude Code, OpenCode, Cursor, Antigravity, Gemini CLI. Focus is quality, not volume. 850+ stars in the first week.
mkdir -p ~/.claude/skills/context-engineering-kit~/.claude/skills/context-engineering-kit/SKILL.mdResulting file structure:
~/.claude/
skills/
context-engineering-kit/
SKILL.md <-- skill definitionSkills are loaded automatically by Claude Code when you start a new session. The skill name and description in the frontmatter determine when Claude triggers it.
Recommended from shared domain, career, and tool overlap with Context Engineering Kit
You'll keep your agent's memory and skills when switching between coding harnesses.
Both used by developer, ai-engineer
You'll maintain a self-improving library of skills instead of letting them rot.
Both used by developer, ai-engineer
You'll ship finished, non-sloppy designs from a single sentence prompt.
Both used by developer
Generate typed API clients and webhook handlers from specs
Works in shared tools
Generate comprehensive error handling with recovery strategies
Works in shared tools
Build GraphQL schemas with resolvers and type-safe client generation
Works in shared tools
Context Engineering Kit