sharpdeveye
- 25 skills
- 0 followers
- 8 hours ago last updated
- ▌ Chain · sharpdeveyeUse when the workflow needs multi-step processing with sequential, parallel, or conditional tool compositions and proper data flow.
- ▌ Guard · sharpdeveyeUse when deploying to production, handling sensitive data, or the workflow needs safety constraints, input validation, and security boundaries.
- ▌ Recap · sharpdeveyeQuick summary of the last session — commands run, files changed, and what to do next.
- ▌ Enrich · sharpdeveyeUse when the agent needs access to information beyond its training data — knowledge sources, RAG pipelines, or grounding data.
- ▌ Refine · sharpdeveyeUse when the workflow works but needs polish, or as the final step in a diagnose → fix → refine cycle before shipping.
- ▌ Temper · sharpdeveyeUse when the workflow feels over-engineered, has premature optimizations, unnecessary abstraction layers, or complexity beyond actual requirements.
- ▌ Amplify · sharpdeveyeUse when the workflow works but needs to handle more complex cases or produce higher-quality output through better tools, context, prompts, or models.
- ▌ Capture · sharpdeveyeCapture a session summary — what was done, what decisions were made, and what to do next.
- ▌ Compose · sharpdeveyeUse when a single agent demonstrably cannot handle the task and multi-agent coordination is justified.
- ▌ Fortify · sharpdeveyeUse when the workflow lacks error handling, has been failing in production, or needs retry logic, fallback strategies, and circuit breakers.
- ▌ Iterate · sharpdeveyeUse when the workflow needs to self-correct, improve over time, or establish feedback loops and evaluation cycles.
- ▌ Reflect · sharpdeveyeAnalyze command history to identify which skills work, which fail, and where to improve.
- ▌ Diagnose · sharpdeveyeUse when the user wants to find problems, audit workflow quality, or get a comprehensive health check on their AI workflow.
- ▌ Evaluate · sharpdeveyeUse when the user wants a quality review, interaction audit, or to test the workflow against realistic scenarios.
- ▌ Calibrate · sharpdeveyeUse when workflow components are inconsistent, naming conventions vary, or a new team member's work needs alignment to project standards.
- ▌ Accelerate · sharpdeveyeUse when the workflow is too slow, too expensive, or both and needs latency, cost, or token usage optimization.
- ▌ Specialize · sharpdeveyeUse when the user wants to tailor a workflow for a specific industry, domain, or vertical with specialized expertise, terminology, and guardrails.
- ▌ Streamline · sharpdeveyeUse when the workflow feels too complex, has accumulated cruft, or has redundant steps and overlapping tools that need consolidation.
- ▌ Turbocharge · sharpdeveyeUse when the user wants to push past conventional workflow limits with advanced performance techniques like parallel orchestration, streaming pipelines, or adaptive routing.
- ▌ Zero Defect · sharpdeveyeUse when you need maximum precision on a critical task — production deployments, security-sensitive code, financial calculations, or any work where mistakes are unacceptable.
- ▌ Onboard Agent · sharpdeveyeUse when starting a new project, adding a new agent to an existing system, or setting up workflow infrastructure from scratch.
- ▌ Teach Maestro · sharpdeveyeUse when starting a new project with Maestro or when no .maestro.md context file exists yet. Run once per project.
- ▌ Adapt Workflow · sharpdeveyeUse when porting a workflow to a different AI provider, deployment environment, model tier, or organizational context.
- ▌ Agent Workflow · sharpdeveye bundleUse 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.
- ▌ Extract Pattern · sharpdeveyeUse when the user wants to create templates, extract reusable patterns, document solutions, or build a pattern library from working workflows.