yonatangross/orchestkit

1

observability-monitoring Use when adding logging, metrics, tracing, or alerting to applications. Observability & Monitoring covers structured …

yonatangross/orchestkit

16

2

outbox-pattern Transactional outbox pattern for reliable event publishing. Use when implementing atomic writes with event delivery, …

yonatangross/orchestkit

16

3

performance-testing Performance and load testing with k6 and Locust. Use when validating system performance under load, stress testing, i…

yonatangross/orchestkit

16

4

test-data-management Test data management with fixtures and factories. Use when creating test data strategies, implementing data factories…

yonatangross/orchestkit

16

5

type-safety-validation End-to-end type safety with Zod, tRPC, Prisma, and TypeScript 5.7+ patterns. Use when creating Zod schemas, setting u…

yonatangross/orchestkit

16

6

unit-testing Unit testing patterns and best practices. Use when writing isolated unit tests, implementing AAA pattern, designing t…

yonatangross/orchestkit

16

7

api-versioning API versioning strategies including URL path, header, and content negotiation. Use when migrating v1 to v2, handling …

yonatangross/orchestkit

15

8

cache-cost-tracking LLM cost tracking with Langfuse for cached responses. Use when monitoring cache effectiveness, tracking cost savings,…

yonatangross/orchestkit

15

9

contract-testing Consumer-driven contract testing with Pact for API compatibility. Use when testing microservice integrations, verifyi…

yonatangross/orchestkit

15

10

database-schema-designer SQL and NoSQL schema design with normalization, indexing, and migration patterns. Use when designing database schemas…

yonatangross/orchestkit

15

11

embeddings Text embeddings for semantic search and similarity. Use when converting text to vectors, choosing embedding models, i…

yonatangross/orchestkit

15

12

focus-management Keyboard focus management patterns for accessibility. Covers focus traps, roving tabindex, focus restore, skip links,…

yonatangross/orchestkit

15

13

high-performance-inference High-performance LLM inference with vLLM, quantization (AWQ, GPTQ, FP8), speculative decoding, and edge deployment. U…

yonatangross/orchestkit

15

14

langgraph-checkpoints LangGraph checkpointing and persistence. Use when implementing fault-tolerant workflows, resuming interrupted executi…

yonatangross/orchestkit

15

15

langgraph-functional LangGraph Functional API with @entrypoint and @task decorators. Use when building workflows with the modern LangGraph…

yonatangross/orchestkit

15

16

llm-testing Testing patterns for LLM-based applications. Use when testing AI/ML integrations, mocking LLM responses, testing asyn…

yonatangross/orchestkit

15

17

multimodal-rag CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document ch…

yonatangross/orchestkit

15

18

ork-verify Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a req…

yonatangross/orchestkit

15

19

performance optimization Use when application is slow, bundle is too large, or investigating performance issues. Performance optimization cove…

yonatangross/orchestkit

15

20

pgvector-search Production hybrid search combining PGVector HNSW with BM25 using Reciprocal Rank Fusion. Use when implementing hybrid…

yonatangross/orchestkit

15

21

run-tests Comprehensive test execution with parallel analysis and coverage reporting. Use when running test suites or troublesh…

yonatangross/orchestkit

15

22

saga-patterns Saga patterns for distributed transactions with orchestration and choreography approaches. Use when implementing mult…

yonatangross/orchestkit

15

23

semantic-caching Redis semantic caching for LLM applications. Use when implementing vector similarity caching, optimizing LLM costs th…

yonatangross/orchestkit

15

24

strawberry-graphql Strawberry GraphQL library for Python with FastAPI integration, type-safe resolvers, DataLoader patterns, and subscri…

yonatangross/orchestkit

15

25

add-golden Adds documents to golden dataset with validation. Use when curating test data or saving examples.

yonatangross/orchestkit

14

26

alternative-agent-frameworks Multi-agent frameworks beyond LangGraph. CrewAI crews, Microsoft Agent Framework, OpenAI Agents SDK, GPT-5.2-Codex. U…

yonatangross/orchestkit

14

27

assess-complexity Assesses task complexity with codebase metrics. Use when determining if a task needs breakdown.

yonatangross/orchestkit

14

28

cqrs-patterns CQRS (Command Query Responsibility Segregation) patterns for separating read and write models. Use when optimizing re…

yonatangross/orchestkit

14

29

design-system-starter Use this skill when creating or evolving design systems for applications. Provides design token structures, component…

yonatangross/orchestkit

14

30

fine-tuning-customization LLM fine-tuning with LoRA, QLoRA, DPO alignment, and synthetic data generation. Efficient training, preference learni…

yonatangross/orchestkit

14

31

golden-dataset-curation Use when creating or improving golden datasets for AI evaluation. Defines quality criteria, curation workflows, and m…

yonatangross/orchestkit

14

32

golden-dataset-management Use when backing up, restoring, or validating golden datasets. Prevents data loss and ensures test data integrity for…

yonatangross/orchestkit

14

33

golden-dataset-validation Use when validating golden dataset quality. Runs schema checks, duplicate detection, and coverage analysis to ensure …

yonatangross/orchestkit

14

34

llm-evaluation LLM output evaluation and quality assessment. Use when implementing LLM-as-judge patterns, quality gates for AI outpu…

yonatangross/orchestkit

14

35

ork-assess Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Us…

yonatangross/orchestkit

14

36

ork-brainstorm Compare plausible implementation, architecture, product, or operational approaches before committing to one. Use when…

yonatangross/orchestkit

14

37

ork-explore Map an unfamiliar codebase, feature, architecture, data flow, or operational path with file-backed evidence. Use when…

yonatangross/orchestkit

14

38

ork-review-pr Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use w…

yonatangross/orchestkit

14

39

prompt-caching Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching s…

yonatangross/orchestkit

14

40

query-decomposition Query decomposition for multi-concept retrieval. Use when handling complex queries spanning multiple topics, implemen…

yonatangross/orchestkit

14

41

release-notebook Creates a versioned NotebookLM notebook for the current OrchestKit release. Reads version from package.json, extracts…

yonatangross/orchestkit

14

42

reranking-patterns Reranking patterns for improving search precision. Use when implementing cross-encoder reranking, LLM-based relevance…

yonatangross/orchestkit

14

43

stacked-prs Multi-PR development for large features. Stack dependent PRs, manage rebases, and get faster reviews on smaller chang…

yonatangross/orchestkit

14

44

vcr-http-recording VCR.py HTTP recording for Python tests. Use when testing Python code making HTTP requests, recording API responses fo…

yonatangross/orchestkit

14

45

event-sourcing Event sourcing patterns for storing state as a sequence of events. Use when implementing event-driven architectures, …

yonatangross/orchestkit

13

46

property-based-testing Property-based testing with Hypothesis for discovering edge cases automatically. Use when testing invariants, finding…

yonatangross/orchestkit

13

47

webapp testing Use when testing web applications with AI-assisted Playwright. Webapp testing covers autonomous test agents for plann…

yonatangross/orchestkit

13

48

git-recovery Recovery from git mistakes. Use when you need to undo commits, recover branches, or fix history.

yonatangross/orchestkit

12

49

glyph Render an answer as ASCII art plus semantic emojis inline, right now, with no setup questions. Use for a fast visual …

yonatangross/orchestkit

12

50

load-context Auto-load relevant memories at session start from knowledge graph (always) and mem0 (if configured). Use when you nee…

yonatangross/orchestkit

11