gitwalter
- 244 skills
- 0 followers
- last month last updated
- ▌ Applying Jpa Patterns 2 · gitwalter bundleJPA entity design (relationships, inheritance, embedded), Spring Data JPA repositories (derived queries, @Query, Specifications), Transaction management, N+1 query prevention (EntityGraph, JOIN FETCH), Auditing, Flyway/Liquibase migrations
- ▌ Optimizing Prompts 2 · gitwalterDSPy integration for declarative prompt optimization, prompt versioning, A/B testing, few-shot optimization, chain-of-thought patterns, prompt caching
- ▌ Developing Blazor Apps 2 · gitwalter bundleBlazor Server, WebAssembly, and Auto render modes, component lifecycle, state management, JavaScript interop, authentication
- ▌ Managing Vision Agents 2 · gitwalter bundleImage analysis with multi-modal LLMs (GPT-4V, Gemini Vision), object detection integration, image generation pipelines, and visual question answering
- ▌ Tracing With Langsmith 2 · gitwalter bundleDebugging and tracing LangChain/LangGraph with LangSmith MCP
- ▌ Streaming Realtime Data 2 · gitwalter bundleToken streaming from LLMs, event streaming with astream_events, WebSocket agent patterns, and real-time UI updates
- ▌ Managing Database Agents 2 · gitwalter bundleSQL generation with LLMs, schema understanding, query optimization, and text-to-SQL pipelines
- ▌ Applying Ef Core Patterns 2 · gitwalter bundleEntity Framework Core patterns for data access, migrations, and query optimization
- ▌ Managing Knowledge Graphs 2 · gitwalter bundleGraph RAG patterns, entity extraction with LLMs, relationship mapping, and Neo4j integration
- ▌ Processing Data Pipelines 2 · gitwalter bundleDataset preparation for ML, HuggingFace datasets, custom loaders, data validation with Great Expectations, feature engineering, data versioning with DVC, preprocessing pipelines
- ▌ Optimizing Langsmith Prompts 2 · gitwalter bundlePrompt management with LangSmith Hub - versioning, testing, and evaluation
- ▌ Managing Agentic Loops 2 · gitwalter bundleProcedural implementation of ReAct, Reflection, Planning, and Iterative Refinement patterns.
- ▌ Verifying With Strawberry 2 · gitwalter bundleFactual claim verification - the canonical profile of grounding-verification
- ▌ Orchestrating Crewai Workflows 2 · gitwalter bundleBuild multi-agent workflows using CrewAI patterns
- ▌ Browsing Web 2 · gitwalter bundleWeb scraping with agents, browser automation, content extraction, and ethical scraping practices
- ▌ Modeling Cds 2 · gitwalter bundleCDS view creation (basic, composite, consumption), associations, compositions, CDS annotations (semantic, UI, analytics), CDS access control (DCL)
- ▌ Selecting MCP 2 · gitwalter bundleGuide users through selecting appropriate MCP servers during project generation
- ▌ Processing Ocr 2 · gitwalter bundleImage-to-text with various engines (Tesseract, EasyOCR, cloud APIs), PDF text extraction, table recognition, and layout analysis
- ▌
- ▌ Integrating MCP 2 · gitwalter bundleModel Context Protocol overview, server creation, tool exposure, and common integrations
- ▌ Managing Memory 2 · gitwalterUnified management of episodic, semantic, procedural, and relational memory within the factory workspace.
- ▌ Processing Speech 2 · gitwalter bundleSpeech-to-text (Whisper, cloud APIs), text-to-speech synthesis, real-time transcription, and audio analysis
- ▌ Committing Releases 2 · gitwalterAutomated release management using semantic versioning and automated changelog maintenance.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Requesting Code Review · gitwalterUse when completing tasks, implementing major features, or before merging to verify work meets requirements. Dispatches the code-reviewer agent.
- ▌ Verifying Artifact Structures · gitwalterVerifying the structural integrity of knowledge JSON and workflow markdown files.
- ▌ Verification Before Completion · gitwalterUse when about to claim work is complete, fixed, or passing, before committing or creating PRs. Requires running verification commands and confirming output before making any success claims; evidence before assertions always.
- ▌ Orchestrating Subagents · gitwalter bundleSpawning subagents dynamically, parent-child agent communication, task delegation and result aggregation, resource management and cleanup
- ▌
- ▌ Managing Onboarding Flows · gitwalter bundleOnboard existing repositories into the Antigravity Agent Factory ecosystem
- ▌ Orchestrating Workshop To Pm · gitwalter bundleConvert team workshop outputs to project management artifacts
- ▌ Analyzing Statistics · gitwalterStatistical analysis, predictive modeling, and automated insight generation
- ▌ Programming Python Async · gitwalter bundleTactical Blueprint for high-performance Python Asyncio. Focuses on structured concurrency, resource safety, and resilient background processing.
- ▌ Mapping Dependencies · gitwalterMaps all upstream, downstream, data, and AI dependencies needed to implement the requirements. Produces a dependency graph with integration contracts and a risk register. Use when the user wants to understand what systems need to be connected, asks "what do we depend on", "what integrations are needed", "what could block us", or is preparing for architecture. Requires knowledge/prd.md or knowledge/prototype-brief.md. Writes to knowledge/dependencies.md.
- ▌ Managing Google Workspace · gitwalter bundleTactical Blueprint for managing Google Workspace (Drive, Gmail, Calendar). Focuses on prescriptive search, organization, and high-fidelity communication.
- ▌ Pre Completion Check · gitwalterUse when about to claim work is complete, fixed, or passing, before committing or closing tasks - requires running verification commands and confirming output before making any success claims.
- ▌ Smart Contract Audit · gitwalterSkills for performing security audits and gas optimization checks on smart contracts.
- ▌ Systematic Debugging · gitwalterUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
- ▌ Mastering Project Management · gitwalter bundleProcedural truth for orchestrating high-fidelity software delivery via Plane MCP server.
- ▌ Optimizing Langsmith Prompts · gitwalter bundlePrompt management with LangSmith Hub - versioning, testing, and evaluation
- ▌ Developing Trading Strategies · gitwalter bundleDesign and implement algorithmic trading strategies with entry/exit rules, position sizing, and risk parameters
- ▌ Evaluating Llms · gitwalter bundleRAGAS evaluation setup, DeepEval integration, LangSmith evaluation runs, custom metrics, retrieval quality metrics, regression testing for LLM outputs
- ▌ Synthesizing Knowledge · gitwalterStructured knowledge capture to extract team wisdom, lessons learned, and best practices for embedding in agent systems
- ▌ Documentation Generation · gitwalterGlobal documentation skill for generating code references, SDLC gate artifacts, and repository management files (README, Changelog, ADRs).
- ▌ Building Nextjs Enterprise · gitwalter bundleTactical Blueprint for production-grade Next.js 15+ applications. Focuses on procedural execution, tool-calling sequences, and idiomatic excellence.
- ▌ Building Spring Enterprise · gitwalter bundleTactical Blueprint for production-grade Spring Boot 3+ applications. Focuses on procedural execution, tool-calling sequences, and idiomatic excellence.
- ▌ Retrieving RAG Context Adv · gitwalterPatterns for using FAISS MCP tools to ingest documents and perform semantic retrieval.
- ▌ Reviewing Requirements · gitwalterConducts a multi-perspective adversarial review of knowledge/prd.md using a structured debate pattern. Activates three reviewer personas — Product Critic, AI Systems Engineer, and Security Auditor — to surface gaps, contradictions, missing edge cases, and AI-specific failure modes. Use when the user wants to validate requirements, check the PRD, find gaps, stress-test the spec, or says "review the requirements", "what are we missing", "is this complete", or "let's pressure-test this". Requires knowledge/prd.md. Writes findings to knowledge/review-findings.md.
- ▌ Building Fastapi Enterprise · gitwalter bundleTactical Blueprint for production-grade FastAPI applications. Focuses on procedural execution, tool-calling sequences, and idiomatic excellence.
- ▌ Dispatching Parallel Agents · gitwalterUse when facing 2+ independent tasks or failures that can be worked on without shared state or sequential dependencies.
- ▌ Orchestrating Crewai Agents · gitwalter bundleDetailed CrewAI agent design patterns - role design, backstories, collaboration, hierarchical vs sequential processes, tool integration
- ▌ Subagent Driven Development · gitwalterExecute plan by dispatching specialized subagents per task. Ensures isolated context and high precision.
- ▌ Experimental Interaction · gitwalterSkill for coordinating experimental interactions including agent-to-agent handoffs and voice-to-PRD workflows.
- ▌ Applying Sqlalchemy Patterns · gitwalter bundleSQLAlchemy 2.0 patterns (mapped_column, Mapped types), Async engine and sessions, Relationship patterns, Alembic migrations, Repository pattern, Query optimization, Connection pooling
- ▌ Checking Alignment · gitwalter bundleVerify understanding and alignment before major implementations
- ▌ Automated Code Generation · gitwalterUses the Factory project generation engine to create core file structures and basic implementation logic from parsed PRD requirements. Orchestrates the ProjectGenerator and uses builder agents for initial implementation.
- ▌ Building Dotnet Microservices · gitwalter bundleService decomposition, API Gateway with YARP, inter-service communication (gRPC, REST, message bus), distributed caching, health checks, circuit breakers
- ▌ Building Spring Microservices · gitwalter bundleSpring Cloud microservices patterns with gateway, discovery, and resilience
- ▌ Verifying Grounding · gitwalter bundleUniversal two-pass verification for LLM grounding using confidence delta comparison
- ▌
- ▌ Reviewing Clean Code · gitwalter bundleSystematic code quality review using SOLID principles, code smell detection, and refactoring patterns
- ▌ Subagent Driven Dev · gitwalterUse when executing implementation plans with independent tasks in the current session. Subagents follow a two-stage review loop.
- ▌ Optimizing Frontend Performance · gitwalter bundleCore Web Vitals optimization, code splitting, and React performance patterns
- ▌ Building Dotnet Backend · gitwalter bundleASP.NET Core Minimal APIs, Controllers, dependency injection, middleware, background services, options pattern, health checks
- ▌ Engineering RAG Systems · gitwalter bundleTactical Blueprint for Retrieval-Augmented Generation (RAG) systems. Focuses on document ingestion, semantic retrieval, reranking, and citation truth.
- ▌ Integrating Sap Systems · gitwalter bundleCPI iFlow design patterns (content-based routing, splitter, aggregator), Groovy script patterns, API Management policies, Event Mesh topic design, OData consumption
- ▌ Mastering Agentic Loops · gitwalter bundleTactical Blueprint for stateful AI agents and multi-agent systems. Focuses on LangGraph orchestration, state persistence, and procedural loop logic.
- ▌ Inspecting RAG Catalog · gitwalter bundleInspect and list the contents of the Qdrant RAG ebook library
- ▌
- ▌ Documentation Management · gitwalterCatalog generation, reference link verification, workshop documentation building, and knowledge gap analysis.
- ▌ Managing Google Calendar · gitwalter bundleManage calendar events using the Google Calendar MCP server.
- ▌
- ▌ Applying Anthropic Patterns · gitwalter bundleClaude agentic loop patterns - tool use until done, extended thinking for complex reasoning, safety and alignment patterns, LangChain ChatAnthropic integration
- ▌ Clustering Opportunities · gitwalterSynthesises all raw idea dumps in knowledge/ideas/raw/ into labelled opportunity clusters with themes, strength signals, and a prioritisation matrix. Use this skill after one or more brainstorming sessions, when the user wants to make sense of accumulated ideas, find patterns, or asks "what themes are emerging" or "which ideas are worth pursuing". Writes output to knowledge/opportunities.md.
- ▌ Containerizing Java Apps · gitwalter bundleDocker multi-stage builds for Java (JDK vs JRE), GraalVM native images, Jib for containerization, Kubernetes deployment (Deployment, Service, ConfigMap, Secrets), Helm charts, Health probes (liveness, readiness, startup), Resource limits
- ▌ Operating Ml Engineering · gitwalter bundleTactical Blueprint for ML Training, Deployment, and Monitoring. Focuses on production-grade PyTorch loops, distributed training, and MLOps observability.
- ▌ Generating Documentation · gitwalter bundleAutomated documentation generation from code including docstrings, API docs, and architecture diagrams
- ▌ Managing Database Agents · gitwalter bundleSQL generation with LLMs, schema understanding, query optimization, and text-to-SQL pipelines
- ▌ Verifying Communications · gitwalter bundleEnable verified, axiom-compliant communication between Factory agents
- ▌
- ▌ Using Git Worktrees · gitwalterUse when starting feature work that needs isolation from the current workspace - creates isolated git worktrees. Good for @Operator (PROPS).
- ▌ Applying RAG Patterns · gitwalter bundleDocument chunking strategies, hybrid retrieval (semantic + keyword), reranking patterns, and citation/attribution
- ▌
- ▌ Integrating Sap Cloud · gitwalter bundleTactical Blueprint for SAP Cloud Integration (CPI), Event Mesh, and API Management. Focuses on secure, observable, and resilient enterprise integration patterns.
- ▌ Observing Spring Apps · gitwalter bundleMicrometer metrics (counters, gauges, timers), Distributed tracing with Micrometer Tracing + Zipkin/Jaeger, Structured logging (Logback + JSON), Spring Boot Actuator endpoints, Prometheus + Grafana setup, Custom health indicators
- ▌ Using Prisma Database · gitwalter bundlePrisma schema design patterns, relations (1:1, 1:N, M:N), migrations workflow, Prisma Client queries (findMany, create, update, transactions), seeding, type-safe queries, and performance optimization.
- ▌ Prd Parsing Logic · gitwalterParses an Agentic PRD (knowledge/prd.md) to extract structured configuration for automated project generation. Extracts Epics, Stories (with JSON acceptance criteria), NFRs, and AI components. Use when initializing a project or feature implementation from a verified PRD.