NeoLabHQ/context-engineering-kit

actualize

Reconcile the project's FPF state with recent repository changes

Langue du texte source : anglais

add-task

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

Langue du texte source : anglais

agent-evaluation

Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.

Langue du texte source : anglais

analyse-problem

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

Langue du texte source : anglais

analyse

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

Langue du texte source : anglais

analyze-issue

Analyze a GitHub issue and create a detailed technical specification

Langue du texte source : anglais

apply-anthropic-skill-best-practices

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

Langue du texte source : anglais

attach-review-to-pr

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

Langue du texte source : anglais

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

Langue du texte source : anglais

build-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…

Langue du texte source : anglais

cause-and-effect

Systematic Fishbone analysis exploring problem causes across six categories

Langue du texte source : anglais

commit

Create well-formatted commits with conventional commit messages and emoji

Langue du texte source : anglais

context-engineering

Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.

Langue du texte source : anglais

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

Langue du texte source : anglais

create-command

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

Langue du texte source : anglais

create-hook

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

Langue du texte source : anglais

create-ideas

Generate ideas in one shot using creative sampling

Langue du texte source : anglais

create-pr

Create pull requests using GitHub CLI with proper templates and formatting

Langue du texte source : anglais

create-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.

Langue du texte source : anglais

create-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,…

Langue du texte source : anglais

create-workflow-command

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

Langue du texte source : anglais

critique

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

Langue du texte source : anglais

decay

Manage evidence freshness by identifying stale decisions and providing governance actions

Langue du texte source : anglais

design-testing-strategy

Use before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.

Langue du texte source : anglais

do-and-judge

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

Langue du texte source : anglais

do-competitively

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

Langue du texte source : anglais

do-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.

Langue du texte source : anglais

do-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.

Langue du texte source : anglais

fix-tests

Systematically fix all failing tests after business logic changes or refactoring

Langue du texte source : anglais

git-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…

Langue du texte source : anglais

git-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…

Langue du texte source : anglais

implement-task

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

Langue du texte source : anglais

judge

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

Langue du texte source : anglais

judge-with-debate

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

Langue du texte source : anglais

kaizen

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.

Langue du texte source : anglais

launch-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

Langue du texte source : anglais

load-issues

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

Langue du texte source : anglais

load-pr-comments

Use to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.

Langue du texte source : anglais

memorize

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

Langue du texte source : anglais

multi-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.

Langue du texte source : anglais