Context Engineering Kit
Marketplace Verifiziert AktivHand-crafted collection of advanced context engineering techniques and patterns with minimal token footprint focused on improving agent result quality.
To provide developers with a curated collection of high-quality plugins and techniques for improving AI agent result quality and predictability.
Funktionen
- Curated collection of advanced context engineering techniques
- Minimal token footprint for improved agent efficiency
- Focus on improving agent result quality and predictability
- Includes plugins for specialized development workflows (e.g., SADD, SDD)
- Based on scientifically proven techniques and patterns
Anwendungsfälle
- Improving the accuracy and reliability of AI agent outputs
- Reducing hallucinations and biases in AI-generated code or text
- Implementing advanced prompt engineering and context management strategies
- Leveraging specialized development workflows for complex tasks
Nicht-Ziele
- Providing a general-purpose collection of unrelated tools
- Bundling low-quality or unproven techniques
- Replacing the need for fundamental AI model capabilities
Installation
/plugin marketplace add NeoLabHQ/context-engineering-kitEnthält 13 Erweiterungen
Plugin (13)
Collection of commands that force LLM to reflect on previous response and output. Based on papers like Self-Refine and Reflexion. These techniques improve the output of large language models by introducing feedback and refinement loops.
Introduce codebase and PR review commands and skills using multiple specialized agents.
Introduces commands for commit and PRs creation, plus skills for git worktrees and notes.
Introduces commands for test-driven development, common anti-patterns and skills for testing using subagents.
Introduces skills for subagent-driven development, dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates.
Introduces command to update CLAUDE.md with best practices for domain-driven development, focused on quality of code, includes Clean Architecture, SOLID principles, and other design patterns.
Specification Driven Development workflow commands and agents, based on Github Spec Kit and OpenSpec. Uses specialized agents for effective context management and quality review.
Inspired by Japanese continuous improvement philosophy, Agile and Lean development practices. Introduces commands for analysis of root cause of issues and problems, including 5 Whys, Cause and Effect Analysis, and other techniques.
Commands and skills for writing and refining commands, hooks, skills for Claude Code, includes Anthropic Best Practices and Agent Persuasion Principles that can be useful for sub-agent workflows.
Commands for analysing project, writing and refining documentation.
Commands for setup or update of CLAUDE.md file with best practices for specific language or framework.
Commands for setup well known MCP server integration if needed and update CLAUDE.md file with requirement to use this MCP server for current project.
First Principles Framework (FPF) for structured reasoning using workflow command pattern. Implements ADI (Abduction-Deduction-Induction) cycle via propose-hypotheses workflow with fpf-agent for hypothesis generation, logical verification, empirical validation, and auditable decision-making. Includes utility commands for status, query, decay, actualize, and reset.