aws-samples/sample-aidlc-decisions-driven-skill

aidlc-prototype

Build a throwaway spike to validate requirements. Demonstrates core user flows with minimal code — no architecture, no tests, no production concerns.

Langue du texte source : anglais

aidlc-deploy

CI/CD pipeline generation and deployment configuration. Produces pipeline configs, environment definitions, and deployment scripts for the target platform.

Langue du texte source : anglais

aidlc-build

Final integration build and test verification. Validates that implemented code compiles, passes all test suites, and meets quality gates before deployment.

Langue du texte source : anglais

aidlc-implement

Code generation and testing. Execute implementation tasks from design specs using standard, parallel, or autonomous modes.

Langue du texte source : anglais

aidlc-code-review

Review implemented code against design specs, coding standards, and best practices. Produces severity-classified findings with suggested fixes.

Langue du texte source : anglais

aidlc-decomposition

Decompose requirements into units of work with DDD concepts. Define system boundaries, dependencies, and development sequence.

Langue du texte source : anglais

aidlc-design

Technology decisions and architecture design. Generates D3 decision gate, validates choices, produces modular or compact design documents with components, data model, API spec, integration, implementation, correctness, and NFR specifications.

Langue du texte source : anglais

aidlc-requirements

Translate business needs into user stories with EARS acceptance criteria. Generates decision gate, personas, and requirements. Includes routing recommendation for next phase.

Langue du texte source : anglais

aidlc

AI-DLC workflow orchestrator. Reads manifest state, dispatches to phase skills, manages rollback and status. Executes phases by loading and following each skill's SKILL.md.

Langue du texte source : anglais

aidlc-tasks

Bridge design to implementation. Break design documents into concrete, sequenced, estimable tasks with execution waves for parallel dispatch.

Langue du texte source : anglais

aidlc-context

Scan workspace, assess project landscape, and generate context document, blueprints, and platform shim. First phase of the AI-DLC specification workflow.

Langue du texte source : anglais

aidlc-reverse-engineer

Deep brownfield codebase analysis. Extracts architecture, modules, data models, API surface, business rules, features, integrations, conventions, and technical debt.

Langue du texte source : anglais

aidlc-solutions-review

Cross-unit design review. Compares design documents across multiple units or modules for conflicts, inconsistencies, and alignment issues. Produces a severity-classified review report with resolution recommendations.

Langue du texte source : anglais