Ask OpenAI Codex questions about code to understand implementations, architecture, patterns, and debugging.
Iterative non-code discussion between the local agent and Codex CLI on any open-ended topic: diet, fitness, writing, decisions, strategy, study plans, life choices, brainstorming.
Use for Codex bug fixes, test fixes, PR cleanup, and small feature changes where scope creep, unrelated refactors, or unverifiable diffs are risks.
Reusable planner role for Codex orchestration. Use when a task needs architecture, sequencing, risk analysis, or a test plan before implementation. Default model: GPT-5.5.
Adversarial review of implementation plans or code using OpenAI Codex CLI - iterative loop with scoped review modes (bugs, architecture) until APPROVED or max rounds
Validate architecture/plan quality via claude-delegator (Plan Reviewer expert). Use after writing context.md for complex feature/refactor work. — from engineering/architecture
Validate architecture/plan quality via claude-delegator (Plan Reviewer expert). Use after writing context.md for complex feature/refactor work. — from engineering/architecture
Reviews Swift/iOS code for adherence to modern Swift idioms, Apple platform best practices, architecture patterns, and code quality standards.
Use when refactoring or reviewing Python code to enforce a strict data architecture - Pydantic models at every external boundary, typed models (never raw dicts) inside the app,…
Persistent memory management for Ai coding assistants using CogmemAi. Use when the user mentions "memory", "remember this", "save this for later", "what do you know about",…
Use when analyzing code repository behavior, understanding entry points, or documenting system architecture.
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.
Analyze and reduce cognitive load in code by identifying complex conditionals, deep nesting, shallow modules, excessive abstractions, and architectural over-engineering.
Unified memory system — multi-store architecture (episodic/semantic/procedural/core), knowledge graph, vector+BM25 retrieval, WAL protocol, memory palace, decay model, reflection,…
Map knowledge components and skill hierarchies for a cognitive tutoring system or adaptive learning platform.
Implement Cohere reference architecture with layered project layout for RAG and agents. Use when designing new Cohere integrations, reviewing project structure, or establishing…
Collaboration platform configuration methodology for legal matter sites. Site architecture, workflow identification, dashboard design, data quality governance, and user adoption…
Create and modify combat system components for SHINOBI WAY game following the dual-system architecture (CombatCalculationSystem + CombatWorkflowSystem).
Design CLI commands that work independently and compose well for automation. Orchestrator pattern coordinates, subcommands execute discrete tasks.
Migrate an Adobe Commerce App Builder project from the Integration Starter Kit or Checkout Starter Kit to the new App Management approach.
Generate and compare multiple architecture options (minimal, moderate, full modernization) with comprehensive trade-offs analysis across cost, timeline, risk, performance — from…
Generate and compare multiple architecture options (minimal, moderate, full modernization) with comprehensive trade-offs analysis across cost, timeline, risk, performance — from…
Use for questions about a codebase, its architecture, dependencies, history, change impact, or project artifacts—especially when compass-out exists or the user invokes /compass.
Use when behavior depends on combinations of operating system, shell, architecture, runtime, model/provider, API revision, application version, or optional dependency.
Competency Center and Business Intelligence knowledge for consulting engagements. Use when working on data architecture, KPI frameworks, dashboards, BI implementation, or…
Use when designing systems, architectures, or APIs, when multiple valid approaches exist with no single obvious answer, or when user explicitly requests parallel/competing…
Dispatch two competing reviewers (arch-reviewer and impl-reviewer) before deep analysis. Competition produces more thorough results.
Challenge unnecessary abstraction, dependencies, and indirection before adding them. Use when a solution adds modules, frameworks, queues, caches, state machines, agents,…
Maintain and improve code quality using PHPInsights without decreasing quality thresholds. Use when PHPInsights fails, cyclomatic complexity is too high, code quality drops, or…
Enterprise compliance architecture for SOC 2, HIPAA, GDPR, and PCI-DSS regulated systems. Use when designing compliant systems, preparing for audits, or implementing regulatory…
Run a TOGAF Architecture Compliance Assessment against any architecture document or implementation. Scores conformance across the 8 TOGAF compliance categories, identifies…
Structurer les composants React. Utiliser quand on organise des composants dans frontend/src/components/v3/.
Identify natural module and component boundaries for microservice extraction, modularization, or monolith decomposition using coupling analysis, cohesion.
Maps architectural components in a codebase and measures their size to identify what should be extracted first.
Guidelines for organizing React components in Shadow Master. Use when creating new components, deciding between single-file vs subfolder structure, or understanding the component…
Composable commerce on Salesforce: headless API layer, micro-frontends, BFF pattern, CDN strategy, third-party composability over B2C/B2B Commerce.
Expert knowledge for building event-driven systems with Composable Rust framework. Use when implementing reducers, designing state machines, working with effects, creating…
Expert knowledge for implementing event sourcing in Composable Rust. Use when implementing event-sourced aggregates, working with EventStore trait or PostgreSQL, designing event…
Captures durable knowledge after completing work so future sessions benefit. Activates during the ship phase — updates CLAUDE.md with architectural decisions and gotchas, writes…
Design, implement, and operate a self-improving AI Operating System for business with 9 components: Strategic Layer, Prioritization Engine, Knowledge Management, Central Ops,…
Structures technology diligence with architecture review, code quality assessment, scalability analysis, and technical debt evaluation.
Pre-implementation confidence assessment (≥90% required). Use before starting any implementation to verify readiness with duplicate check, architecture compliance, offici — from…
Drafts U.S. employment confidentiality and severance agreements combining separation compensation, broad claim releases, post-employment restrictions, and enforcement…
LiteLLM-RS Configuration Architecture. Covers YAML loading, environment variable override, validation patterns, type-safe config models, and hot reloading.
Expert guide for managing application configuration including environment variables, config files, secrets management, and multi-environment setups.
Provide structured config-sync system and directory overview. Use when config-sync architecture guidance is required.
Manage application configuration across environments with layered config loading, environment variables, secrets management, and validation.
Use when building a deciduous decision graph to capture design evolution, architecture history, or how a codebase's design changed over time.
Use when building a deciduous decision graph to capture design evolution, architecture history, or how a codebase's design changed over time.
HashiCorp Consul — service discovery, health checking, KV store, service mesh, intentions. Use when working with consul service mesh.
Establish comprehensive understanding of project structure, architecture, dependencies, and current state before conducting detailed code review. Use as the.
Audit and incrementally retrofit an existing codebase so its intent and behavior are equally legible to people and AI agents.
Build, repair, or maintain a concise project context base that lets fresh AI-agent sessions understand a repository quickly and accurately.
Break project context into a dependency graph of focused markdown files. Each agent reads only what its task requires — never a monolith dump.
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems.
Advanced context engineering management system that provides comprehensive context architecture design, memory management, knowledge engineering, and workflow orchestration…
Current state of Claude's memory, context, and Skills architecture as of late 2025. LOAD THIS when discussing context engineering, Skills, userMemories, memory management, context…
Load relevant design documents and project context before working on any task. Use when user asks about features, requests implementation, discusses functionality, analyzes…
Expert in managing the "Memory" of AI systems. Specializes in Vector Databases (RAG), Short/Long-term memory architectures, and Context Window optimization.
Use when allocating context-window budget across system, skill-injection, working, and output zones; monitoring context health; deciding when to compact; preserving state before…