codebygarv/Ai-skills

A community-driven catalogue of 150+ reusable AI agent skills for Claude Code , Antigravity, Cursor Ai , kimi , deepseek ,Mimo — code review, security auditing, architecture review, and more. Install any skill with one npx command.

27Stars on the repository
120Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

adr-writer

01

codebygarv/Ai-skills

Skill Claude CodeCodex

Writes an Architecture Decision Record (ADR) documenting a decision, its context, the options considered, and its consequences. Use to record a decision that's already been made so future readers understand why.

not rated 27 1mo ago A 42 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Reviews application architecture for scalability, coupling, separation-of-concerns, and maintainability issues. Use for system-level review, not individual file/function-level code review.

not rated 27 1mo ago A 37 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Designs multi-tier caching architectures (CDN, Redis, memory), invalidation policies, and stampede mitigations.

not rated 27 1mo ago A 30 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Analyzes cloud infrastructure and architectures to identify wasted spend and right-sizing opportunities.

not rated 27 1mo ago A 22 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Designs Command Query Responsibility Segregation (CQRS) and Event Sourcing models with projection rebuilders.

not rated 27 1mo ago A 30 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Formulates RTO/RPO targets, cross-region failover, backup verification, and split-brain recovery procedures.

not rated 27 1mo ago A 30 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Designs event-driven systems with CloudEvents schemas, message brokers, idempotency keys, and dead-letter queues.

not rated 27 1mo ago A 28 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Establishes flag naming, fallback defaults, rollout rings, cleanup telemetry, and automated dead flag retirement.

not rated 27 1mo ago A 28 tokens original MIT

migration-planner

09

codebygarv/Ai-skills

Skill Claude CodeCodex

Plans a safe, incremental migration (framework, database, service, or platform) with rollback points and a dual-running strategy. Use when replacing something that's already in production and can't just be swapped in one step.

not rated 27 1mo ago A 46 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Architects database multi-tenancy models (Shared DB/Schema vs Separate Schema vs Separate Database) and tenant routing.

not rated 27 1mo ago A 30 tokens original MIT

project-planner

11

codebygarv/Ai-skills

Skill Claude CodeCodex

Converts an idea into a structured development plan with milestones, tasks, dependencies, and implementation phases. Use when an idea or feature needs to be broken into a plan before work starts.

not rated 27 1mo ago A 41 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Designs distributed token bucket, leaky bucket, and tiered rate limiting architectures to prevent abuse.

not rated 27 1mo ago A 27 tokens original MIT

tech-debt-assessor

13

codebygarv/Ai-skills

Skill Claude CodeCodex

Inventories technical debt across a codebase and prioritizes it by cost-of-delay versus effort, producing a ranked paydown list. Use when debt is accumulating but it's unclear what to fix first.

not rated 27 1mo ago A 45 tokens original MIT

api-designer

15

codebygarv/Ai-skills

Skill Claude CodeCodex

Helps design REST APIs - routes, request/response structures, validation, status codes, and conventions. Use when designing new endpoints or reviewing an existing API's design for consistency.

not rated 27 1mo ago A 40 tokens original MIT

bug-hunter

16

codebygarv/Ai-skills

Skill Claude CodeCodex

Searches code specifically for potential bugs, edge cases, race conditions, and incorrect assumptions rather than general style/quality. Use when the goal is finding what's broken, not improving what already works.

not rated 27 1mo ago A 43 tokens original MIT

code-reviewer

17

codebygarv/Ai-skills

Skill Claude CodeCodex

Reviews source code for bugs, readability, maintainability, performance, and best-practice violations. Use for general-purpose code review of a diff, file, or function, not tied to a specific language concern.

not rated 27 1mo ago A 46 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Identifies race conditions, mutex contention, unsafe shared state, and deadlocks in concurrent and async code.

not rated 27 1mo ago A 28 tokens original MIT

database-architect

19

codebygarv/Ai-skills

Skill Claude CodeCodex

Reviews database schemas, relationships, indexes, constraints, and data modeling decisions. Use when designing a new schema or reviewing an existing one for correctness and scalability.

not rated 27 1mo ago A 35 tokens original MIT

dependency-auditor

20

codebygarv/Ai-skills

Skill Claude CodeCodex

Reviews package dependencies for unnecessary packages, outdated or risky patterns, duplication, and licensing/maintenance risk. Use when a dependency manifest has grown unchecked or before adding a new dependency.

not rated 27 1mo ago A 40 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Designs structured error hierarchies, domain error mapping, and resilient fallback/retry mechanisms across applications.

not rated 27 1mo ago A 27 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Designs ergonomic, performant GraphQL schemas with Relay pagination, input validation, and N+1 prevention.

not rated 27 1mo ago A 26 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Formulates safe Mikado Method refactoring dependency graphs and Strangler Fig extraction paths for fragile legacy codebases.

not rated 27 1mo ago A 28 tokens original MIT

codebygarv/Ai-skills

Skill Claude CodeCodex

Identifies unclosed handles, event listener accumulation, retain cycles, and heap memory leak patterns.

not rated 27 1mo ago A 25 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: