Claude Skills by sharpdeveye

github.com/sharpdeveye

25 skillsA× 252 installs55 views

AccelerateAUse when the workflow is too slow, too expensive, or both and needs latency, cost, or token usage optimization.data-aigoperformanceVotes: 0GitHub stars: 415
Adapt WorkflowAUse when porting a workflow to a different AI provider, deployment environment, model tier, or organizational context.data-aigorailsVotes: 0GitHub stars: 415
Agent WorkflowAUse when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails.data-airustgoVotes: 0GitHub stars: 415
AmplifyAUse when the workflow works but needs to handle more complex cases or produce higher-quality output through better tools, context, prompts, or models.data-aigotestingVotes: 0GitHub stars: 415
CalibrateAUse when workflow components are inconsistent, naming conventions vary, or a new team member's work needs alignment to project standards.data-aigorefactoringVotes: 0GitHub stars: 415
CaptureACapture a session summary — what was done, what decisions were made, and what to do next.data-aigoapiVotes: 0GitHub stars: 415
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
ChainAUse when the workflow needs multi-step processing with sequential, parallel, or conditional tool compositions and proper data flow.data-aigoVotes: 0GitHub stars: 415
ComposeAUse when a single agent demonstrably cannot handle the task and multi-agent coordination is justified.data-aigoperformanceVotes: 0GitHub stars: 415
DiagnoseAUse when the user wants to find problems, audit workflow quality, or get a comprehensive health check on their AI workflow.data-aigoapiVotes: 0GitHub stars: 415
EnrichAUse when the agent needs access to information beyond its training data — knowledge sources, RAG pipelines, or grounding data.data-aigorailsVotes: 0GitHub stars: 415
EvaluateAUse when the user wants a quality review, interaction audit, or to test the workflow against realistic scenarios.data-aigotestingVotes: 0GitHub stars: 415
Extract PatternAUse when the user wants to create templates, extract reusable patterns, document solutions, or build a pattern library from working workflows.data-aigotestingVotes: 0GitHub stars: 415
FortifyAUse when the workflow lacks error handling, has been failing in production, or needs retry logic, fallback strategies, and circuit breakers.data-aigorailsVotes: 0GitHub stars: 415
GuardAUse when deploying to production, handling sensitive data, or the workflow needs safety constraints, input validation, and security boundaries.data-airustgoVotes: 0GitHub stars: 415
IterateAUse when the workflow needs to self-correct, improve over time, or establish feedback loops and evaluation cycles.data-aigotestingVotes: 0GitHub stars: 415
Onboard AgentAUse when starting a new project, adding a new agent to an existing system, or setting up workflow infrastructure from scratch.data-aigogitVotes: 0GitHub stars: 415
RecapAQuick summary of the last session — commands run, files changed, and what to do next.data-aigoVotes: 0GitHub stars: 415
RefineAUse when the workflow works but needs polish, or as the final step in a diagnose → fix → refine cycle before shipping.data-aigoVotes: 0GitHub stars: 415
ReflectAAnalyze command history to identify which skills work, which fail, and where to improve.data-aigoVotes: 0GitHub stars: 415
SpecializeAUse when the user wants to tailor a workflow for a specific industry, domain, or vertical with specialized expertise, terminology, and guardrails.data-aigorailsVotes: 0GitHub stars: 415
StreamlineAUse when the workflow feels too complex, has accumulated cruft, or has redundant steps and overlapping tools that need consolidation.data-aigorailsVotes: 0GitHub stars: 415
Teach MaestroAUse when starting a new project with Maestro or when no .maestro.md context file exists yet. Run once per project.data-aigoapiVotes: 0GitHub stars: 415
TemperAUse when the workflow feels over-engineered, has premature optimizations, unnecessary abstraction layers, or complexity beyond actual requirements.data-aigorailsVotes: 0GitHub stars: 415
TurbochargeAUse when the user wants to push past conventional workflow limits with advanced performance techniques like parallel orchestration, streaming pipelines, or adaptive routing.data-aigotestingVotes: 0GitHub stars: 415
Zero DefectAUse when you need maximum precision on a critical task — production deployments, security-sensitive code, financial calculations, or any work where mistakes are unacceptable.data-aigoexpressVotes: 0GitHub stars: 415