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.
Install
npx skills add NeoLabHQ/context-engineering-kitgh skill install NeoLabHQ/context-engineering-kitgit clone --depth 1 https://github.com/NeoLabHQ/context-engineering-kitSkills in this collection
- ActualizeNeoLabReconcile the project's FPF state with recent repository changes
- Add TaskNeoLabcreates draft task file in .specs/tasks/draft/ with original user intent
- Agent EvaluationNeoLabHQEvaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
- AnalyseNeoLabAuto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target
- Analyse ProblemNeoLabComprehensive A3 one-page problem analysis with root cause and action plan
- Analyze IssueNeoLabAnalyze a GitHub issue and create a detailed technical specification
- Apply Anthropic Skill Best PracticesNeoLabComprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
- Attach Review To PrNeoLabAdd line-specific review comments to pull requests using GitHub CLI API
- BrainstormNeoLabUse when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
- Build MCPNeoLabGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
- Cause And EffectNeoLabSystematic Fishbone analysis exploring problem causes across six categories
- CommitNeoLabCreate well-formatted commits with conventional commit messages and emoji
- Context EngineeringNeoLabHQUnderstand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
- Create AgentNeoLabComprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns
- Create CommandNeoLabInteractive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
- Create HookNeoLabCreate and configure git hooks with intelligent project analysis, suggestions, and automated testing
- Create IdeasNeoLabGenerate ideas in one shot using creative sampling
- Create PrNeoLabCreate pull requests using GitHub CLI with proper templates and formatting
- Create RuleNeoLabUse when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I should have done it differently." -> need create rule for this issue so it not appears again.
- Create SkillNeoLabGuide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
- Create Workflow CommandNeoLabCreate a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
- CritiqueNeoLabComprehensive multi-perspective review using specialized judges with debate and consensus building
- DecayNeoLabManage evidence freshness by identifying stale decisions and providing governance actions
- Design Testing StrategyNeoLabUse before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.
- Do And JudgeNeoLabExecute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
- Do CompetitivelyNeoLabExecute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
- Do In ParallelNeoLabRun independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verification. Use when tasks do not depend on each other and can run side by side.
- Do In StepsNeoLabExecute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results of earlier ones.
- Fix TestsNeoLabSystematically fix all failing tests after business logic changes or refactoring
- Git NotesNeoLabUse when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.
- Git WorktreesNeoLabUse when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktree commands and workflow patterns for parallel development with multiple working directories.
- Implement TaskNeoLabImplement a task step by step with automated LLM-as-Judge verification at the end of each phase
- JudgeNeoLabLaunch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation
- Judge With DebateNeoLabEvaluate solutions through multi-round debate between independent judges until consensus
- KaizenNeoLabUse when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.
- Launch Sub AgentNeoLabLaunch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification
- Load IssuesNeoLabLoad all open issues from GitHub and save them as markdown files
- Load Pr CommentsNeoLabUse to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.
- MemorizeNeoLabCurates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
- Multi Agent PatternsNeoLabHQDesign multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
- Plan Do Check ActNeoLabIterative PDCA cycle for systematic experimentation and continuous improvement
- Plan TaskNeoLabRefine a draft task specification into a fully planned, implementation-ready task with acceptance criteria, architecture, per-step sub-task files and verifiable phases
- Prompt EngineeringNeoLabHQUse this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.
- Propose HypothesesNeoLabExecute complete FPF cycle from hypothesis generation to decision
- QueryNeoLabSearch the FPF knowledge base and display hypothesis details with assurance information
- ReflectNeoLabReflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
- ResetNeoLabReset the FPF reasoning cycle to start fresh
- Resolve Fixed Pr CommentsNeoLabVerify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.