Marketplace

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

Deploy and run a SearXNG meta-search instance for AI agents to query the live web: Docker setup, engine configuration, API integration, and result parsing.

Implement search functionality: full-text search, faceted filtering, typo tolerance, relevance tuning, and search analytics.

Generate typed SDK clients from API specifications: language-specific patterns, auth handling, pagination, and error mapping.

Build outcome-driven product roadmaps: theme identification, dependency mapping, capacity planning, and stakeholder communication.

Systematically test layouts across viewports, breakpoints, zoom, and orientation, then fix breakage. Use before shipping UI or when a layout breaks on a device.

Use when a diff, commit log, or changelog must become polished release notes tailored to end users, developers, or internal stakeholders.

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

Design recommendation systems: collaborative filtering, content-based, hybrid approaches, cold start, and ranking.

Build retrieval-augmented generation pipelines: chunking strategies, embedding models, vector stores, and reranking for accurate grounding.

Use when a retrieval corpus has exact or near-duplicate docs/chunks inflating embedding cost or polluting top-k results, and you must detect and prune them.

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

Establish versioned prompt management: semantic versioning, A/B testing, rollback, and changelog practices for production prompt systems.

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

Use to adversarially test an LLM app, agent, or tool pipeline for prompt-injection/jailbreak weakness and produce a scored hardening report.

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

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.

Establish performance budgets: Core Web Vitals targets, bundle size limits, runtime budgets, and enforcement strategies.

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

Use to audit and cut an OVHcloud bill: right-size flavors, tier cold data to Cold Archive, kill idle volumes/IPs, pick commitments, compare vs hyperscalers.

Use when provisioning or cost-tuning OVHcloud: Public Cloud instances, MKS Kubernetes, Object Storage, vRack, Octavia LB, Terraform, EU data residency.

Design comprehensive observability: metrics, logs, traces, and profiles with SLO-driven alerting and dashboard design.

Design multi-region active-active and active-passive architectures: data replication, failover, DNS routing, and consistency.