Menú
SkillsMP ha recopilado 22 skills de sddevelopment-be/quickstart_agent-augmented-development. Abre una skill para revisar su origen y sus detalles.
Mostrando 22 de 22 skills recopiladas.
Execute a complete iteration cycle: planning → batch execution → documentation → review setup. Follows file-based orchestration with TDD/ATDD, work logs, and quality gates.
Idioma del texto original: inglés
Delegate task to specialist agent when expertise required: Initialize as specialist (Planning Petra, Backend Benny, Architect Alphonso, etc.) OR spawn sub-agent if available. Use when task requires specialized knowledge in agent's core focus area.
Idioma del texto original: inglés
Test-first bug fixing: Write failing test that reproduces bug → Fix code → Test passes. Systematic, verifiable approach prevents regression and wastes no time on trial-and-error deployments.
Idioma del texto original: inglés
Architect Alphonso conducts rigorous code review and architecture-fit analysis: ADR compliance, test coverage, architectural patterns, security. Outputs review document with APPROVED/REDIRECT/BLOCKED status.
Idioma del texto original: inglés
Mid-execution self-monitoring checkpoint (Ralph Wiggum Loop): Detect warning signs (drift, confusion, gold-plating), course-correct before completion. Mandatory at 25% progress and before delegation.
Idioma del texto original: inglés
Create functional specification for complex features: detailed requirements, user scenarios, constraints, acceptance criteria. Bridges strategic intent and implementation with MoSCoW prioritization and Given/When/Then scenarios.
Idioma del texto original: inglés
Assess current implementation state: pending tasks, active work, progress metrics, blockers, and next recommended batch. Provides Planning Petra's executive view.
Idioma del texto original: inglés
Instead of a centralized lookup table, each agent profile documents its own observed handoff patterns. This approach: - Preserves agent autonomy - Requires zero implementation complexity - Remains...
Idioma del texto original: inglés
Prompt for Architect Alphonso to perform analysis and draft a Proposed ADR
Idioma del texto original: inglés
Prompt for DevOps Danny to generate an automation script based on requirements or direct prompt
Idioma del texto original: inglés
Prompt for Bootstrap Bill to bootstrap a cloned repository for local/project context
Idioma del texto original: inglés
Prompt for Curator Claire to audit and normalize a target directory
Idioma del texto original: inglés
"This approach describes how to systematically capture architectural decisions throughout the development lifecycle, integrating decision rationale with artifacts to preserve "why" knowledge for fut..."
Idioma del texto original: inglés
The C4 model (Context, Container, Component, Code) is a lightweight hierarchical technique for structuring software architecture diagrams. It favors progressive disclosure of technical detail so st...
Idioma del texto original: inglés
Prompt for Editor Eddy to revise a draft document using lexical analysis artifacts
Idioma del texto original: inglés
Prompt for Lexical Larry to perform a lexical style diagnostic and minimal diff pass
Idioma del texto original: inglés
Prompt to request creation of a new specialized agent (Manager Mike runs it)
Idioma del texto original: inglés
Translate the “Target Audience Personas” practice (see `work/notes/ideation/opinionated_platform/target_audience_personas.md`) into a repeatable workflow so every artifact intentionally addresses t...
Idioma del texto original: inglés
The Test Readability and Clarity Check is a dual-agent validation approach that assesses whether a test suite effectively documents system behavior by reconstructing system understanding purely fro...
Idioma del texto original: inglés
This approach describes best practices for setting up, configuring, and maintaining development tooling to support agent-augmented development. It provides a framework for tool selection, configura...
Idioma del texto original: inglés
Trunk-based development (TBD) is a branching strategy where all developers (agents and humans) commit frequently to a single shared branch (`main`), with short-lived feature branches (<24 hours) us...
Idioma del texto original: inglés
Provide a single, precise reference for the file-based asynchronous orchestration model that powers the `work/` directory. The approach keeps exploratory and operational work visible inside Git by ...
Idioma del texto original: inglés