notify
25Command
A command for configuring task notifications in Claude Code, including desktop alerts, sounds, and webhooks.
Command
A command for configuring task notifications in Claude Code, including desktop alerts, sounds, and webhooks.
Command
A command for reviewing whether a product or feature is worth building.
Command
A command for coordinating work across multiple isolated sessions or containers. It can run tasks in parallel, one after another, or according to a dependency graph, where a task waits for the tasks it depends on.
Command
A command that reviews project specification documents from both a business and a software-architecture perspective, then improves the documents. It uses separate reviewers for business concerns and technical concerns, followed by a product manager who combines their feedback.
Command
An agent that diagnoses software bugs, finds their underlying cause, makes a focused code fix, and checks it with a regression test.
Command
An optional motivational command that uses friendly competition to encourage someone after repeated failed attempts or when they are close to giving up. It does not use insults or belittle the user.
Command
A reporting-only command for systematic web-application quality checks. It explores a supplied or locally running website, detects relevant project details and tests, and produces a structured report with a health score and screenshots.
Command
A command that tests a web application, records evidence, fixes the bugs it finds, and tests the result again.
Command
A design and discussion command for RAG systems, which let an AI search a collection of documents before generating an answer. It covers workflows, document splitting, search methods, databases for document vectors, and monitoring tools.
Command
A persistent work loop that repeatedly executes a coding task, verifies the result, and fixes problems until an architecture check passes.
Command
A security-focused architecture review command that examines a system from an attacker’s point of view. It challenges assumptions, looks for weak points, and considers how failures could spread or make the system costly to run.
Command
A command that runs commands or coding-agent tasks inside an isolated Docker container. Docker containers are separated environments that can limit network access, file changes, users, and computer resources.
Command
A command for defining which files or directories a coding agent may modify, which must remain read-only, and which require a warning first.
Command
A project-architecture analysis based directly on the code and its folder structure. Software architecture describes how a system is divided into parts and how those parts work together.
Command
A command for forming a team of specialized agents to handle a complex task. It supports roles such as planning, implementation, verification, criticism, coordination, and supervision.
Command
A command that assembles three testing specialists and a senior programmer to test an application together.
Command
A quality-check command that repeats testing, result verification, and fixes until the stated quality target is reached.
Command
A command that breaks a large coding task into separate subtasks and runs them at the same time using multiple agents.
Command
A test-driven development workflow, where tests are written first, the smallest passing implementation is added, and the code is then improved.
Command
A testing-focused coding assistant that plans, writes, runs, and analyses tests. It covers unit tests for small pieces of code, integration tests for connected modules, and end-to-end tests for complete user flows.
Skill Claude CodeCodex
API contract testing: verify that API providers and consumers honor agreed-upon interfaces without running full integration. Use when building microservices, running Consumer-Driven Contract (CDC) tests, testing REST/GraphQL/Protobuf contracts, or ensuring frontend-backend API compatibility. Covers Pact, OpenAPI…
Skill Claude CodeCodex
Skill "api-reviewer" from an8079/take-skills, covering api-reviewer, 触发词, 概述, 核心审查维度 and 1. api 设计规范.
Skill Claude CodeCodex
Skill "autopilot" from an8079/take-skills, covering autopilot — ultrawork autonomous execution mode, name, description, when to activate and protocol.
Skill Claude CodeCodex
Chaos engineering for distributed systems: design and run chaos experiments to proactively discover weaknesses before they cause outages. Use when user mentions chaos, fault injection, resilience testing, GameDays, chaos monkey,LitmusChaos, Gremlin, steady-state hypothesis, or when building信頼性 into microservices.