Context Engineering Kit 技能合集
通过结构化开发流程改善助手推理和软件交付。
NeoLabHQ 原生插件结合反思、审查、Git、测试驱动开发、规格、子助手协作、持续改进、文档、MCP 和第一性原理推理。
适用场景
- 依据规格规划并实现变更
- 通过专项助手和反馈审查代码
- 改进提示词、指令和项目知识
使用方法
安装完整原生插件套件以保留命令与助手集成，结合仓库背景使用相应流程；可移植技能副本本身不提供这些集成。
Skills
agent-evaluation
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
neolabhq/context-engineering-kitapply-anthropic-skill-best-practices
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
neolabhq/context-engineering-kitcontext-engineering
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
neolabhq/context-engineering-kitcreate-agent
Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns
neolabhq/context-engineering-kitcreate-command
Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
neolabhq/context-engineering-kitcreate-hook
Create and configure git hooks with intelligent project analysis, suggestions, and automated testing
neolabhq/context-engineering-kitcreate-rule
Use 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.
neolabhq/context-engineering-kitcreate-skill
Guide 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. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
neolabhq/context-engineering-kitcreate-workflow-command
Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
neolabhq/context-engineering-kitprompt-engineering
Use 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.
neolabhq/context-engineering-kittest-prompt
Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing
neolabhq/context-engineering-kittest-skill
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
neolabhq/context-engineering-kitthought-based-reasoning
Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting fails - provides comprehensive guide to Chain-of-Thought and related prompting techniques (Zero-shot CoT, Self-Consistency, Tree of Thoughts, Least-to-Most, ReAct, PAL, Reflexion) with templates, decision matrices, and research-backed patterns
neolabhq/context-engineering-kitupdate-docs
Update and maintain project documentation for local code changes using multi-agent workflow with tech-writer agents. Covers docs/, READMEs, JSDoc, and API documentation.
neolabhq/context-engineering-kitwrite-concisely
Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.
neolabhq/context-engineering-kitactualize
Reconcile the project's FPF state with recent repository changes
neolabhq/context-engineering-kitdecay
Manage evidence freshness by identifying stale decisions and providing governance actions
neolabhq/context-engineering-kitpropose-hypotheses
Execute complete FPF cycle from hypothesis generation to decision
neolabhq/context-engineering-kitquery
Search the FPF knowledge base and display hypothesis details with assurance information
neolabhq/context-engineering-kitreset
Reset the FPF reasoning cycle to start fresh
neolabhq/context-engineering-kitstatus
Display the current state of the FPF knowledge base
neolabhq/context-engineering-kitanalyze-issue
Analyze a GitHub issue and create a detailed technical specification
neolabhq/context-engineering-kitattach-review-to-pr
Add line-specific review comments to pull requests using GitHub CLI API
neolabhq/context-engineering-kitcommit
Create well-formatted commits with conventional commit messages and emoji
neolabhq/context-engineering-kitcreate-pr
Create pull requests using GitHub CLI with proper templates and formatting
neolabhq/context-engineering-kitgit-notes
Use 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.
neolabhq/context-engineering-kitgit-worktrees
Use 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.
neolabhq/context-engineering-kitload-issues
Load all open issues from GitHub and save them as markdown files
neolabhq/context-engineering-kitload-pr-comments
Use to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.
neolabhq/context-engineering-kitresolve-fixed-pr-comments
Verify 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.
neolabhq/context-engineering-kitanalyse-problem
Comprehensive A3 one-page problem analysis with root cause and action plan
neolabhq/context-engineering-kitanalyse
Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target
neolabhq/context-engineering-kitcause-and-effect
Systematic Fishbone analysis exploring problem causes across six categories
neolabhq/context-engineering-kitkaizen
Use 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.
neolabhq/context-engineering-kitplan-do-check-act
Iterative PDCA cycle for systematic experimentation and continuous improvement
neolabhq/context-engineering-kitroot-cause-tracing
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
neolabhq/context-engineering-kitwhy
Iterative Five Whys root cause analysis drilling from symptoms to fundamentals
neolabhq/context-engineering-kitbuild-mcp
Guide 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).
neolabhq/context-engineering-kitsetup-arxiv-mcp
Guide for setup arXiv paper search MCP server using Docker MCP
neolabhq/context-engineering-kitsetup-codemap-cli
Guide for setup Codemap CLI for intelligent codebase visualization and navigation
neolabhq/context-engineering-kitsetup-context7-mcp
Guide for setup Context7 MCP server to load documentation for specific technologies.
neolabhq/context-engineering-kitsetup-serena-mcp
Guide for setup Serena MCP server for semantic code retrieval and editing capabilities
neolabhq/context-engineering-kitcritique
Comprehensive multi-perspective review using specialized judges with debate and consensus building
neolabhq/context-engineering-kitmemorize
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
neolabhq/context-engineering-kitreflect
Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
neolabhq/context-engineering-kitreview-local-changes
Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.
neolabhq/context-engineering-kitreview-pr
Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working tree.
neolabhq/context-engineering-kittraiage-review
This skill should be used when need prioritize what changed code in repository human must review.
neolabhq/context-engineering-kitdo-and-judge
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
neolabhq/context-engineering-kitdo-competitively
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
neolabhq/context-engineering-kitdo-in-parallel
Run 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.
neolabhq/context-engineering-kitdo-in-steps
Execute 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.
neolabhq/context-engineering-kitjudge-with-debate
Evaluate solutions through multi-round debate between independent judges until consensus
neolabhq/context-engineering-kitjudge
Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation
neolabhq/context-engineering-kitlaunch-sub-agent
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification
neolabhq/context-engineering-kitmulti-agent-patterns
Design 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.
neolabhq/context-engineering-kitsubagent-driven-development
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
neolabhq/context-engineering-kittree-of-thoughts
Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation
neolabhq/context-engineering-kitadd-task
creates draft task file in .specs/tasks/draft/ with original user intent
neolabhq/context-engineering-kitbrainstorm
Use 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
neolabhq/context-engineering-kitcreate-ideas
Generate ideas in one shot using creative sampling
neolabhq/context-engineering-kitimplement-task
Implement a task step by step with automated LLM-as-Judge verification at the end of each phase
neolabhq/context-engineering-kitplan-task
Refine a draft task specification into a fully planned, implementation-ready task with acceptance criteria, architecture, per-step sub-task files and verifiable phases
neolabhq/context-engineering-kitdesign-testing-strategy
Use before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.
neolabhq/context-engineering-kitfix-tests
Systematically fix all failing tests after business logic changes or refactoring
neolabhq/context-engineering-kittest-coverage
Use after writing tests to assess coverage quality across structural, mutation, requirements, and API/integration dimensions; organized knowledge for choosing and interpreting coverage analyses.
neolabhq/context-engineering-kittest-driven-development
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
neolabhq/context-engineering-kitwrite-tests
Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if everything is committed). Use when you want write tests for new logic or increase test coverage.
neolabhq/context-engineering-kit