developersglobal/ai-agent-skills
31 skills
$npx skills add developersglobal/ai-agent-skillsSkillInstalls
ai-output-validationValidates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems.api-designDesign stable, versioned, self-documenting APIs. Easy to use correctly, hard to use incorrectly. Apply Hyrum's Law from day one.ci-cd-pipelinesAutomated quality gates from commit to production. Every merge to main is potentially shippable. No manual steps in the deployment path.code-explanationGet layered, context-aware explanations of unfamiliar code. Understand what it does, why it was written that way, and how to work with it safely.code-reviewStructured code review focusing on correctness, security, and maintainability. Correctness before style. Every reviewer comment must be actionable.context-loadingLoad minimum necessary context into agent context windows. Prevents token bloat, reduces cost, and improves focus. Only load what the current task needs.debugging-methodologySystematic root cause analysis for production and development bugs. Hypothesis-driven debugging — never guess-and-check.documentationDocument decisions, not just implementations. ADRs for architectural choices, inline docs for non-obvious code, and runbooks for operational knowledge.error-handlingGraceful degradation and meaningful error messages. Errors are first-class citizens, not afterthoughts. Every error path is designed, not discovered.frontend-engineeringAccessible, performant, responsive UI patterns. Component design, state management discipline, and Core Web Vitals compliance.git-workflowTrunk-based development with atomic commits, clean history, and meaningful commit messages. Every commit should be deployable.goal-driven-executionTransforms imperative instructions into declarative goals with verifiable success criteria. Enables autonomous looping until verified completion.hallucination-preventionDetects and mitigates LLM hallucinations in production pipelines.idea-to-specConverts vague ideas into concrete, testable specifications with acceptance criteria. No implementation begins without a spec.incremental-codingBuild in verifiable increments. Never implement more than can be tested right now. Ship partial working systems over complete broken ones.integration-testingTest real system boundaries, not mocks of mocks. Integration tests verify that components work together, not that they work in isolation.meeting-notes-to-tasksConverts unstructured meeting notes into structured, assigned, time-bounded action items. Never leave a meeting without knowing who does what by when.multi-agent-orchestrationDesigns and coordinates multi-agent pipelines where specialized agents collaborate to complete complex tasks.observabilityStructured logging, distributed tracing, and alerting for AI systems and traditional services. You can't fix what you can't see.performance-optimizationMeasure first, optimize second. Data-driven performance improvements with before/after benchmarks and production validation.production-deploymentZero-downtime deployments with pre-flight checks, staged rollouts, and rollback plans. Never ship to production without a verified rollback strategy.prompt-injection-defenseGuards AI agents and LLM-powered applications against prompt injection attacks — both direct and indirect.rag-and-memoryPatterns for Retrieval-Augmented Generation (RAG) and agent memory systems.refactoringSafe, behavior-preserving code transformation backed by tests. Refactor with evidence, not instinct.research-and-summarizeDistill complex topics into layered, actionable summaries. Start with the key insight, layer in detail, end with recommended next action.security-hardeningApplies OWASP Top 10, secrets management, and least-privilege principles before any code ships. Security is a build step, not an afterthought.simplicity-firstPrevents overengineering by enforcing minimum viable code. No speculative features, no premature abstractions, no unnecessary complexity.surgical-changesEnforces minimal code modifications — touch only what you must. Prevents drive-by refactoring, comment deletions, and style changes unrelated to the task.task-decompositionBreaks features into atomic, independently verifiable tasks. No task should take more than 4 hours. Unblocks parallel work and reduces integration risk.test-driven-developmentRed-green-refactor cycle with meaningful coverage. Tests are written before implementation. Coverage is a side effect of good tests, not the goal.think-before-codingForces explicit reasoning before writing any code. Surfaces assumptions, manages confusion, and prevents hallucination by demanding clarity upfront.