sherlock-review
Evidence-based code review using Sherlock Holmes-style deductive reasoning to verify implementation claims, investigate bugs, and conduct root cause analysis.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
380 skills found
Evidence-based code review using Sherlock Holmes-style deductive reasoning to verify implementation claims, investigate bugs, and conduct root cause analysis.
Implement consumer-driven contract testing for microservices using Pact, schema validation, and API versioning to prevent breaking changes and ensure distributed team coordination.
Emergency recovery suite for Vercel-hosted projects. Manage deployment rollbacks, database migration reverts, cache invalidation, and health verification workflows.
Automated tool and MCP server discovery for Claude Code. Searches 17+ registries to find relevant skills, plugins, and tools before planning or when errors occur.
Stripe payment integration patterns for checkout, webhooks, and subscriptions. Ensures safe API usage, idempotency, signature verification, and testing compliance.
Troubleshoot and manage the GCP e2-micro VM running the eth-realtime-collector. Handle systemd failures, network connectivity issues, and real-time data stream monitoring for Ethereum network data.
A microworld operating system for LLM-based agent living memory, transforming filesystems into navigable rooms and code into habitable worlds.
A local RAG semantic memory system using Qdrant and Ollama. Ideal for recalling workspace files, notes, project decisions, and user preferences with high-relevance vector search.
Streamline technical documentation for BattleScope features, maintaining consistency across API, frontend, and architecture layers.
A specialized code review agent that performs multi-dimensional analysis covering security vulnerabilities, performance optimization, code quality, and maintainability standards.
Extract specific fields from YAML files efficiently without reading entire files, saving 80-95% of context window usage.
Apply reality-first coding standards: intentional naming, focused functions, guard clauses, and deterministic side effects, with no speculative features.