en un clic
quickstart_agent-augmented-development
quickstart_agent-augmented-development contient 22 skills collectées depuis sddevelopment-be, avec une couverture métier par dépôt et des pages de détail sur le site.
Skills dans ce dépôt
Execute a complete iteration cycle: planning → batch execution → documentation → review setup. Follows file-based orchestration with TDD/ATDD, work logs, and quality gates.
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.
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.
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.
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.
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.
Assess current implementation state: pending tasks, active work, progress metrics, blockers, and next recommended batch. Provides Planning Petra's executive view.
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...
Prompt for Architect Alphonso to perform analysis and draft a Proposed ADR
Prompt for DevOps Danny to generate an automation script based on requirements or direct prompt
Prompt for Bootstrap Bill to bootstrap a cloned repository for local/project context
Prompt for Curator Claire to audit and normalize a target directory
"This approach describes how to systematically capture architectural decisions throughout the development lifecycle, integrating decision rationale with artifacts to preserve "why" knowledge for fut..."
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...
Prompt for Editor Eddy to revise a draft document using lexical analysis artifacts
Prompt for Lexical Larry to perform a lexical style diagnostic and minimal diff pass
Prompt to request creation of a new specialized agent (Manager Mike runs it)
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...
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...
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...
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...
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 ...