kiro-ui
kiro-ui에는 guyon-it-consulting에서 수집한 skills 18개가 있으며, 저장소 수준 직업 범위와 사이트 내 skill 상세 페이지를 제공합니다.
이 저장소의 skills
Design clear, versioned, backward-compatible interfaces and contracts between units, services, and external consumers. Applies wherever interfaces/contracts are designed or reviewed.
Evaluate software architecture for sound boundaries, intentional coupling, explicit trade-offs, scalability, deployability, operability, and failure behaviour. Applies wherever architectural decisions are designed or reviewed.
Identify and define the core domain concepts of a system — components, entities, relationships, ownership boundaries, and the language the system speaks. Applies wherever domain structure, entity ownership, or business capability boundaries are designed or reviewed.
Apply disciplined implementation practices across backend, frontend, infrastructure, configuration, and tests: write-test-verify, repository convention matching, integration boundary control, and appropriate test strategy.
AI-DLC workspace kickoff. Handles the welcome banner and workspace setup — creating the intent directory, state file, and audit file. Read by the orchestrator at the start of every new intent.
AI-DLC workflow orchestrator. Activate whenever the user states a fresh development intent — building, creating, implementing, fixing, migrating, refactoring, or adding a feature to a codebase. Use this skill for any free-form development prompt such as "build X", "add feature Y", "migrate Z to W", "fix the bug in V", "refactor U", or "create a new service for T".
Elicit, decompose, and structure requirements from ambiguous human intent into verifiable, traceable specifications. Applies wherever requirements are discovered, refined, validated, or used to check downstream artifacts.
Evaluate product artifacts — requirements, user stories, personas, and wireframes — for clarity, value, testability, traceability, and scope discipline. Applies wherever product-facing work is reviewed before it moves downstream.
Systematically analyse an existing codebase — discovering its structure, architecture, APIs, data models, dependencies, and quality posture — and produce structured design artifacts that make the system understandable to downstream work.
AI-DLC stage execution. Defines how to drive each stage through its cycle — state transitions, persona invocation format, and rules. Read by the orchestrator when executing stages.
Reason about systems as wholes — how components interact, where complexity hides, what scales, what fails, and whether stated requirements are technically feasible within real-world constraints. Applies wherever system-level trade-offs, interactions, or feasibility are considered.
Decompose a system into well-bounded components or deployable units with clear responsibilities, explicit interfaces, and intentional dependency directions. Applies wherever system structure is split, grouped, or reviewed for coupling and ownership.
Think from the user's perspective — understanding goals, frustrations, workflows, and the context in which people interact with the system. Applies wherever user value, journeys, stories, screens, or acceptance criteria are shaped or reviewed.
The skill of breaking requirements into well-formed user stories and system stories. Covers story structure (As a/I want/So that), INVEST criteria, acceptance criteria (Given/When/Then), story sizing, and traceability back to requirements.
The skill of designing user interfaces — screen layouts, navigation flows, information architecture, and interaction patterns. Translates requirements and stories into visual structure that developers can implement.
AI-DLC workflow composition. Composes the adaptive workflow conversationally with the human — selecting stages, assigning personas, and handling artifact sourcing. Read by the orchestrator after kickoff.
The skill of weighing risk, outcome, and reward to determine what matters most. Applied when ordering requirements, stories, or design decisions. Every persona uses this to focus effort where it counts.
This skill describes how you work in each stage. As an owner, what are your tasks — plan, clarify, produce artifacts, refine based on feedback. As a reviewer, what are your tasks — read the artifact, write a review. Must be used to execute each stage. Defines what to produce at each step and ensures everything is persisted to disk per conventions.