Marketplace

Design voice assistant experiences: intent design, dialogue management, error recovery, and multi-modal handoff.

Optimize vector databases: index selection (HNSW, IVF), parameter tuning, metadata filtering, and cost-performance tradeoffs.

Use before restructuring working code across multiple files: produces a stepwise refactor plan with risk scores, verification, and rollback points.

Design reliable async job processing: queue selection, retry strategies, dead letter queues, and idempotency guarantees.

Design pricing strategies: value-based pricing, tier design, usage-based models, competitive positioning, and margin analysis.

Use when a rough feature idea or request needs to become a complete, testable PRD with scoped requirements, success metrics, and open questions.

Generate synthetic training data: schema preservation, distribution matching, privacy guarantees, and quality validation.

Audit software supply chain security: SBOM generation, dependency provenance, artifact signing, and CI/CD hardening.

Design real-time stream processing: windowing, watermarking, exactly-once semantics, and state management.

Write production SRE runbooks: alert response procedures, diagnostic steps, escalation paths, and post-action verification.

Diagnose slow SQL with execution-plan analysis and rewrite queries and indexes; use when a query is slow, times out, or burns database CPU.

Use when creating, improving, or reviewing an agent skill: scope one job, write routing-grade descriptions, and verify with fresh-agent tests.

Scan codebases for leaked credentials, API keys, and tokens: pattern matching, entropy analysis, and safe remediation.

Use when a prompt underperforms and needs systematic diagnosis, single-variable experiments, and A/B evidence instead of guess-and-check rewrites.

Audit systems for privacy compliance: data minimization, purpose limitation, consent management, GDPR/CCPA alignment.

Plan and scope penetration tests: attack surface mapping, test methodology selection, and finding documentation.

Plan and execute safe database schema migrations: dependency ordering, rollback strategies, zero-downtime patterns, and data backfill procedures.

Use when asked to build or review an MCP server wrapping an API, database, or CLI so agents can call it through well-designed, strictly typed tools.

Design Model Context Protocol resources and prompts that expose data and workflows to AI agents following the MCP specification.

Plan and execute LLM fine-tuning: dataset preparation, method selection (LoRA, QLoRA, full), evaluation, and deployment.

Systematically modernize legacy codebases: strangler fig pattern, incremental rewrites, and risk-minimized migration paths.

Build knowledge graphs from unstructured data for agent grounding: entity extraction, relation mapping, and graph-based retrieval.

Use when reviewing or writing Kubernetes manifests; audits workloads for reliability, security, and cost issues and produces ready-to-apply fixes.

Optimize model inference: quantization, distillation, batching, speculative decoding, and serving infrastructure tuning.