NeoLabHQ/context-engineering-kit - 第 3 页

do-competitively

Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis

原文语言：英语

brainstorm

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

原文语言：英语

create-pr

Create pull requests using GitHub CLI with proper templates and formatting

原文语言：英语

judge

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

原文语言：英语

judge-with-debate

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

原文语言：英语

tree-of-thoughts

Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation

原文语言：英语

apply-anthropic-skill-best-practices

Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure

原文语言：英语

create-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

原文语言：英语

create-hook

Create and configure git hooks with intelligent project analysis, suggestions, and automated testing

原文语言：英语

create-workflow-command

Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts

原文语言：英语

update-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.

原文语言：英语

propose-hypotheses

Execute complete FPF cycle from hypothesis generation to decision

原文语言：英语

analyze-issue

Analyze a GitHub issue and create a detailed technical specification

原文语言：英语

attach-review-to-pr

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

原文语言：英语

commit

Create well-formatted commits with conventional commit messages and emoji

原文语言：英语

load-issues

Load all open issues from GitHub and save them as markdown files

原文语言：英语

analyse-problem

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

原文语言：英语

analyse

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

原文语言：英语

cause-and-effect

Systematic Fishbone analysis exploring problem causes across six categories

原文语言：英语

plan-do-check-act

Iterative PDCA cycle for systematic experimentation and continuous improvement

原文语言：英语

why

Iterative Five Whys root cause analysis drilling from symptoms to fundamentals

原文语言：英语

setup-arxiv-mcp

Guide for setup arXiv paper search MCP server using Docker MCP

原文语言：英语

setup-codemap-cli

Guide for setup Codemap CLI for intelligent codebase visualization and navigation

原文语言：英语

setup-context7-mcp

Guide for setup Context7 MCP server to load documentation for specific technologies.

原文语言：英语

setup-serena-mcp

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

原文语言：英语

critique

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

原文语言：英语

memorize

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

原文语言：英语

reflect

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

原文语言：英语

create-ideas

Generate ideas in one shot using creative sampling

原文语言：英语

fix-tests

Systematically fix all failing tests after business logic changes or refactoring

原文语言：英语