neolabhq/context-engineering-kit

1

prompt-engineering Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interac…

neolabhq/context-engineering-kit

1.3K

2

context-engineering Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or opti…

neolabhq/context-engineering-kit

1.2K

3

thought-based-reasoning Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning,…

neolabhq/context-engineering-kit

1.2K

4

brainstorm Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed …

neolabhq/context-engineering-kit

1.2K

5

multi-agent-patterns Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks dec…

neolabhq/context-engineering-kit

1.2K

6

reflect Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity …

neolabhq/context-engineering-kit

1.2K

7

update-docs Update and maintain project documentation for local code changes using multi-agent workflow with tech-writer agents. …

neolabhq/context-engineering-kit

1.2K

8

write-concisely Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more profes…

neolabhq/context-engineering-kit

1.2K

9

critique Comprehensive multi-perspective review using specialized judges with debate and consensus building

neolabhq/context-engineering-kit

1.1K

10

subagent-driven-development Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues…

neolabhq/context-engineering-kit

1.1K

11

judge-with-debate Evaluate solutions through multi-round debate between independent judges until consensus

neolabhq/context-engineering-kit

1.1K

12

root-cause-tracing Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically trac…

neolabhq/context-engineering-kit

1.1K

13

kaizen Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements,…

neolabhq/context-engineering-kit

1.1K

14

memorize Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering

neolabhq/context-engineering-kit

1.1K

15

plan-task Refine a draft task specification into a fully planned, implementation-ready task with acceptance criteria, architect…

neolabhq/context-engineering-kit

1.1K

16

test-driven-development Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail…

neolabhq/context-engineering-kit

1.1K

17

implement-task Implement a task step by step with automated LLM-as-Judge verification at the end of each phase

neolabhq/context-engineering-kit

1.1K

18

review-local-changes Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement …

neolabhq/context-engineering-kit

1.1K

19

do-in-steps Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, wi…

neolabhq/context-engineering-kit

1.1K

20

actualize Reconcile the project's FPF state with recent repository changes

neolabhq/context-engineering-kit

1.1K

21

add-task creates draft task file in .specs/tasks/draft/ with original user intent

neolabhq/context-engineering-kit

1.1K

22

agent-evaluation Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating cont…

neolabhq/context-engineering-kit

1.1K

23

analyse Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target

neolabhq/context-engineering-kit

1.1K

24

analyse-problem Comprehensive A3 one-page problem analysis with root cause and action plan

neolabhq/context-engineering-kit

1.1K

25

analyze-issue Analyze a GitHub issue and create a detailed technical specification

neolabhq/context-engineering-kit

1.1K

26

apply-anthropic-skill-best-practices Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requi…

neolabhq/context-engineering-kit

1.1K

27

cause-and-effect Systematic Fishbone analysis exploring problem causes across six categories

neolabhq/context-engineering-kit

1.1K

28

commit Create well-formatted commits with conventional commit messages and emoji

neolabhq/context-engineering-kit

1.1K

29

create-ideas Generate ideas in one shot using creative sampling

neolabhq/context-engineering-kit

1.1K

30

create-pr Create pull requests using GitHub CLI with proper templates and formatting

neolabhq/context-engineering-kit

1.1K

31

create-rule Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time whe…

neolabhq/context-engineering-kit

1.1K

32

create-skill Guide for creating effective skills. This command should be used when users want to create a new skill (or update an …

neolabhq/context-engineering-kit

1.1K

33

do-and-judge Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop

neolabhq/context-engineering-kit

1.1K

34

do-competitively Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation…

neolabhq/context-engineering-kit

1.1K

35

do-in-parallel Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model se…

neolabhq/context-engineering-kit

1.1K

36

fix-tests Systematically fix all failing tests after business logic changes or refactoring

neolabhq/context-engineering-kit

1.1K

37

judge Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation

neolabhq/context-engineering-kit

1.1K

38

launch-sub-agent Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, …

neolabhq/context-engineering-kit

1.1K

39

plan-do-check-act Iterative PDCA cycle for systematic experimentation and continuous improvement

neolabhq/context-engineering-kit

1.1K

40

review-pr Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an op…

neolabhq/context-engineering-kit

1.1K

41

setup-serena-mcp Guide for setup Serena MCP server for semantic code retrieval and editing capabilities

neolabhq/context-engineering-kit

1.1K

42

test-prompt Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desire…

neolabhq/context-engineering-kit

1.1K

43

test-skill Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization…

neolabhq/context-engineering-kit

1.1K

44

tree-of-thoughts Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-jud…

neolabhq/context-engineering-kit

1.1K

45

why Iterative Five Whys root cause analysis drilling from symptoms to fundamentals

neolabhq/context-engineering-kit

1.1K

46

write-tests Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked …

neolabhq/context-engineering-kit

1.1K

47

attach-review-to-pr Add line-specific review comments to pull requests using GitHub CLI API

neolabhq/context-engineering-kit

1K

48

build-mcp Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external servi…

neolabhq/context-engineering-kit

1K

49

create-agent Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and…

neolabhq/context-engineering-kit

1K

50

create-command Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration

neolabhq/context-engineering-kit

1K