spec-driven-steroids

Shared protocols and templates for Spec-Driven phases. Auto-loaded by phase skills via references.

Use this skill when approved requirements and design need to be decomposed into tasks.md for Phase 3 of a Spec-Driven change. It creates atomic, traceable implementation and testing tasks, validates the plan, and should not be used to design architecture or write implementation code.

Use this skill when an approved Spec-Driven change has reached Phase 4 and the user wants a task, phase, or full feature implemented from .specs/changes/<slug>. It executes tasks in order, updates task status immediately, verifies each task before completion, and should not be used before implementation approval.

Unified auditing skill for AI agent workflows. Provides change-type-aware, artifact-adaptive auditing with self-fix capabilities. Works standalone or with spec-driven extensions. Three-layer architecture: core (always active), modules (per-type), extensions (auto-detected).

Use this skill when the user wants to start Phase 1 of a Spec-Driven change, define behavior, or turn a feature idea into a requirements.md file. It writes EARS-format requirements, validates them, and should not be used for design, task breakdown, or implementation.

Use this skill when approved requirements need to be translated into a design.md file for Phase 2 of a Spec-Driven change. It creates a traceable technical design with validator-safe Mermaid diagrams and should not be used for task breakdown or implementation.

Use this skill when the user makes a technical decision, establishes a new pattern, defines business rules, or explicitly asks to remember or save a guideline. Also use this skill when you are about to implement a feature, write code, plan an architecture, or make a technical decision - you MUST retrieve contextual memory first to follow established patterns. Acts as a Staff Engineer to extract, curate, and persist architectural decisions, business rules, and workflows into long-term memory using a JSON graph store.

Use this skill to grade code, specifications, or design documents across four quality dimensions using a 1-5 scoring scale. In grade-and-fix mode, the skill auto-improves artifacts scoring below 5 without prompting. Invoke when you want consistent quality assessment on design, implementation, or specification with actionable feedback and self-healing improvements.

Use this skill when the user wants repository guidance documents generated or refreshed, including AGENTS.md, CONTRIBUTING.md, STYLEGUIDE.md, TESTING.md, ARCHITECTURE.md, and SECURITY.md. It analyzes the repository, generates all six guideline files by default, prefers managed-section updates for existing files, and should not be used for feature specs or implementation.

Use this skill for rigorous, structured code review with a self-repair loop. Applies change-type-aware strategies (feat, fix, hotfix, refactor, migrate, docs). Findings are severity-classified, then auto-fixed where possible. Triggers on PR reviews, code review requests, or when reviewing any change set.

Use this skill when facing long-running or heavy work that must continue without user intervention, especially large task decomposition, multi-task implementation, complex debugging, migrations, or work where context/tool limits are likely. It turns work into durable checkpoints so the agent can keep making progress for hours and resume safely after interruption.