AI agent skills for production grade applications
This repository also configures its own agents. See what ai-agent-skills tells them →
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and fallback handling.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Design stable, versioned, self-documenting APIs. Easy to use correctly, hard to use incorrectly. Apply Hyrum's Law from day one.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Automated quality gates from commit to production. Every merge to main is potentially shippable. No manual steps in the deployment path.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Get layered, context-aware explanations of unfamiliar code. Understand what it does, why it was written that way, and how to work with it safely.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Structured code review focusing on correctness, security, and maintainability. Correctness before style. Every reviewer comment must be actionable.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Load minimum necessary context into agent context windows. Prevents token bloat, reduces cost, and improves focus. Only load what the current task needs.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Systematic root cause analysis for production and development bugs. Hypothesis-driven debugging — never guess-and-check.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Document decisions, not just implementations. ADRs for architectural choices, inline docs for non-obvious code, and runbooks for operational knowledge.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Graceful degradation and meaningful error messages. Errors are first-class citizens, not afterthoughts. Every error path is designed, not discovered.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Accessible, performant, responsive UI patterns. Component design, state management discipline, and Core Web Vitals compliance.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Trunk-based development with atomic commits, clean history, and meaningful commit messages. Every commit should be deployable.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Transforms imperative instructions into declarative goals with verifiable success criteria. Enables autonomous looping until verified completion.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Detects and mitigates LLM hallucinations in production pipelines. Validates AI-generated facts, code, and decisions before they reach end users or downstream systems.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Converts vague ideas into concrete, testable specifications with acceptance criteria. No implementation begins without a spec.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Build in verifiable increments. Never implement more than can be tested right now. Ship partial working systems over complete broken ones.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Test real system boundaries, not mocks of mocks. Integration tests verify that components work together, not that they work in isolation.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Converts unstructured meeting notes into structured, assigned, time-bounded action items. Never leave a meeting without knowing who does what by when.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Designs and coordinates multi-agent pipelines where specialized agents collaborate to complete complex tasks. Includes communication protocols, failure handling, and state management.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Structured logging, distributed tracing, and alerting for AI systems and traditional services. You can't fix what you can't see.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Measure first, optimize second. Data-driven performance improvements with before/after benchmarks and production validation.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Zero-downtime deployments with pre-flight checks, staged rollouts, and rollback plans. Never ship to production without a verified rollback strategy.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Guards AI agents and LLM-powered applications against prompt injection attacks — both direct and indirect. Validates AI inputs and outputs at every trust boundary.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Patterns for Retrieval-Augmented Generation (RAG) and agent memory systems. Retrieves only relevant context, prevents context bloat, and maintains coherent state across sessions.
DevelopersGlobal/ai-agent-skills
Skill Claude CodeCodex
Safe, behavior-preserving code transformation backed by tests. Refactor with evidence, not instinct.
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: