Skill Claude CodeCodex
Top-level orchestrator for multi-domain tasks. Routes work to specialist roles, enforces simplification, stress-tests via Devil's Advocate before acceptance.
not rated 2
changed 3d ago A 33 tokens
original MIT
2Stars on the repository
75Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude Code
Metrics and measurement review: KPI definitions, telemetry instrumentation, A/B test design, dashboard hierarchy, and anomaly detection. Use when ensuring metrics are trustworthy enough for decisions.
not rated 2 3d ago A 39 tokens
original MIT
Skill Claude Code
Backend systems review: APIs, database access, concurrency, caching, and failure handling. Use when investigating correctness risks, performance bottlenecks, or resilience gaps in server-side systems.
not rated 2 3d ago A 42 tokens
original MIT
Skill Claude Code
Player behavior prediction through cognitive bias analysis: loss aversion, anchoring, FOMO, sunk cost, framing effects. Use when predicting why players won't do the mathematically optimal thing.
not rated 2 3d ago A 46 tokens
original MIT
Skill Claude Code
Brand voice, positioning, visual rules, and cross-surface consistency. Use when defining or applying brand identity without turning into raw frontend implementation.
not rated 2 3d ago A 34 tokens
original MIT
Skill Claude Code
Safe removal of dead, duplicate, or unnecessarily complex code. Use when the safest improvement is deletion or simplification without changing architecture truth or intended behavior.
not rated 2 3d ago A 37 tokens
original MIT
Skill Claude Code
Community health: contributor onboarding, governance, communication, ecosystem extensibility, and participation barriers. Use when diagnosing why a community is stagnant or hard to join.
not rated 2 3d ago A 36 tokens
original MIT
Skill Claude Code
Context window management: persisting critical state, checkpointing, and preventing context degradation in long sessions. Trigger at 60% context usage or before large tasks.
not rated 2 3d ago A 36 tokens
original MIT
Skill Claude Code
C++ code review: modern standards (C++17/20/23), RAII, memory safety, value semantics, const correctness, and GoogleTest patterns. Use when reviewing or writing C++ code.
not rated 2 3d ago A 48 tokens
original MIT
role-cto
10Skill Claude Code
Strategic technology decisions: build-vs-buy, platform bets, vendor evaluation, TCO analysis, and organizational readiness. Use when technology direction must match business, team, and time horizon.
not rated 2 3d ago A 42 tokens
original MIT
Skill Claude Code
Data pipeline review: schema contracts, freshness SLAs, ETL reliability, storage scaling, and data quality. Use when data systems need reliability-focused assessment.
not rated 2 3d ago A 36 tokens
original MIT
Skill Claude Code
Database review: schema design, query performance, indexing, migrations, and transactional integrity. Use when the database itself — not the pipeline or the service — is the risk.
not rated 2 3d ago A 40 tokens
original MIT
Skill Claude Code
Infrastructure and operations review: CI/CD pipelines, monitoring, incident readiness, rollback paths, and deployment safety. Use when evaluating whether a system can ship and recover safely.
not rated 2 3d ago A 39 tokens
original MIT
Skill Claude Code
Monetary health analysis: money supply, inflation/deflation, wealth distribution, liquidity, and fiscal policy levers. Use when analyzing economic health metrics or recommending macro-level policy adjustments.
not rated 2 3d ago A 43 tokens
original MIT
Skill Claude Code
Economy systems architecture: faucets, sinks, converters, resource flows, marketplace mechanics, and loop closure. Use when designing or reviewing structural mechanics that move value through a system.
not rated 2 3d ago A 42 tokens
original MIT
Skill Claude Code
Frontend systems review: components, state management, rendering performance, accessibility, bundle health, and network failure handling. Use when analyzing or designing frontend architecture.
not rated 2 3d ago A 36 tokens
original MIT
Skill Claude Code
Combat and progression balance: stat budgets, TTK/DPS, power curves, difficulty scaling, and competitive fairness. Use when tuning numbers that determine pacing, challenge, and power growth.
not rated 2 3d ago A 44 tokens
original MIT
Skill Claude Code
Gameplay systems review: core loops, progression, onboarding, failure states, and player motivation. Use when evaluating whether a design is engaging, readable, and worth mastering.
not rated 2 3d ago A 38 tokens
original MIT
Skill Claude Code
Go code review: idiomatic patterns, error handling, concurrency safety, interface design, and testing. Use when reviewing or writing Go code.
not rated 2 3d ago A 33 tokens
original MIT
Skill Claude Code
Godot 4 / GDScript engine review: scene-node architecture, signals and event buses, static typing, Resources, performance, and shaders/GDExtension. Use when reviewing or writing Godot game code.
not rated 2 3d ago A 51 tokens
original MIT
Skill Claude Code
Java code review: modern Java (14+), records, sealed classes, immutability, JUnit 5 + AssertJ patterns, and Spring Boot conventions. Use when reviewing or writing Java code.
not rated 2 3d ago A 46 tokens
original MIT
Skill Claude Code
Kotlin code review: null safety, immutability, coroutine patterns, sealed types, and testing with Kotest/Turbine. Use when reviewing or writing Kotlin code.
not rated 2 3d ago A 41 tokens
original MIT
Skill Claude Code
Level and content design review: spatial layout, encounter choreography, content sequencing, and moment-to-moment flow. Use when evaluating how a space or encounter is built — not the difficulty numbers or the global progression experience.
not rated 2 3d ago A 48 tokens
original MIT
Skill Claude Code
Live-service operations: incident triage, hotfix decisions, rollback criteria, player-impact assessment, and degradation strategies. Use when something is broken in production or when designing incident readiness.
not rated 2 3d ago A 42 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: