Loading...
Loading...
Found 2,000 Skills
Self-improving agent architecture using ChromaDB for continuous learning, self-evaluation, and improvement storage. Agents maintain separate memory collections for learned patterns, performance metrics, and self-assessments without modifying their static .md configuration.
Transform specifications into implementation plans with architecture design and dependency-ordered tasks. Use for spec-to-plan conversion, task breakdown, effort estimation. Skip if no spec exists.
Infrastructure and development cost estimation for technical projects. Use when planning budgets, evaluating build vs buy decisions, or projecting TCO for architecture choices.
Universal context reviewer: delegates arbitrary context (plans, decisions, documents, architecture proposals) to external agents (Codex + Gemini) for independent review with debate protocol. Context always passed via files.
Use when brainstorming, evaluating architecture choices, or comparing trade-offs where independent perspectives from different model families (Claude/Codex/Gemini) would surface blind spots
Architecture evaluation criteria and technology standards for the homelab. Preloaded into the designer agent to ground design decisions in established patterns and principles. Use when: (1) Evaluating a proposed technology addition, (2) Reviewing architecture decisions, (3) Assessing stack fit for a new component, (4) Comparing implementation approaches. Triggers: "architecture review", "evaluate technology", "stack fit", "should we use", "technology comparison", "design review", "architecture decision"
FuseCore Modular Architecture - Laravel 12 modular monolith with auto-discovery, React integration, and SOLID principles. Use when creating modules, understanding FuseCore structure, or implementing features in FuseCore projects.
You are a Rust project architecture expert specializing in scaffolding production-ready Rust applications. Generate complete project structures with cargo tooling, proper module organization, testing
SOLID principles for Java 21+. Files < 100 lines, interfaces separated, modular architecture. Modules MANDATORY.
Initialize or update project documentation. Use when setting up docs for a new project (`--init`) or syncing docs to current codebase and architecture changes (`--update`).
Orchestrate comprehensive code review across ~12 AI reviewers. 5 persona reviewers (Grug, Carmack, Ousterhout, Beck, Fowler) via Moonbridge, 4 domain specialists (security-sentinel MANDATORY, performance, data integrity, architecture) via Task, plus hindsight-reviewer and synthesis. Use when: code review, PR review, pre-merge quality check.
Evaluate and improve code modularization using the Balanced Coupling Model. Analyzes coupling strength, connascence types, and distance to identify refactoring opportunities and architectural improvements. Use when reviewing code architecture, refactoring modules, or designing new systems.