vignesh2027/AI-AGENT-SKILLS

accessibility-engineering

Build UIs that work for all users including keyboard navigation, screen readers, and WCAG 2.2

agent-orchestration

Design multi-agent systems with robust tool interfaces, state management, and failure handling

ai-ml-engineering

Build ML systems with disciplined training, evaluation, deployment, and safety practices

api-and-interface-design

Design APIs that are stable, ergonomic, and evolvable

architecture-design

Design systems at the right scale with explicit trade-off documentation

backend-engineering

Design services that are reliable, observable, secure, and maintainable

ci-cd-and-automation

Design CI/CD pipelines with fast feedback, quality gates, and reliable deployments

code-review-and-quality

Conduct staff-engineer-level code reviews across correctness, security, performance, readability, and architecture

code-simplification

Remove accidental complexity without changing behavior — apply Chesterton's Fence

context-engineering

Manage what goes into the AI agent context window for maximum quality and minimum waste

data-pipeline-engineering

Build data pipelines with contracts, lineage, quality gates, and observability

database-design

Schema design, migrations, indexing, and query patterns for maintainable and performant databases

debugging-and-error-recovery

Systematic root-cause analysis — stop guessing, start isolating

deployment-strategy

Deploy with rollback plans, staged rollouts, and feature flags

documentation-and-adrs

Write documentation that stays accurate and decisions that stay recorded

doubt-driven-development

Challenge assumptions and hidden dependencies before they become bugs

frontend-engineering

Build UIs that are fast, accessible, maintainable, and tested

git-workflow-and-versioning

Branching strategy, commit discipline, PR hygiene, and semantic versioning

idea-refine

Sharpen a vague idea into a buildable, scoped proposal

incident-response

Structured incident response: detect, communicate, mitigate, resolve, and prevent recurrence

incremental-implementation

Ship working vertical slices instead of big-bang implementations

infrastructure-as-code

Manage infrastructure with version-controlled, reviewed, and tested IaC

llm-evaluation

Systematically evaluate LLM outputs, prevent regressions, and measure quality

microservices-design

Design service boundaries, contracts, and failure modes for distributed systems

mobile-development

Build iOS/Android apps that are performant, offline-capable, accessible, and battery-efficient

observability-and-monitoring

Design logging, metrics, tracing, and alerting that make systems debuggable in production

performance-optimization

Profile before optimizing; optimize with evidence, not intuition

planning-and-task-breakdown

Decompose work into atomic, independently verifiable tasks

prompt-engineering

Write prompts that are reliable, testable, versioned, and safe

rag-system-design

Design, evaluate, and operate retrieval-augmented generation systems

requirements-analysis

Extract, validate, and document requirements from raw input

risk-assessment

Identify and mitigate technical and delivery risk before it becomes an incident

security-and-hardening

Apply security controls, threat modeling, and hardening to code and infrastructure

source-driven-development

Ground implementation in authoritative sources — specs, RFC, official docs — not assumptions

spec-driven-development

Write a specification before writing any implementation code

test-driven-development

Write tests before implementation to drive design and prove correctness

using-agent-skills

Discover and compose skills from this framework to guide your work