Claude code plugins with skills for agentic development
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
Launch multi-agent code review covering architecture, security, testing, and consistency. Use when asked to "code review", "review code", "audit code", "multi-agent review", "architecture review", "security review", "testing review", "DRY review", "consistency review", "layering review", "launch review agents"…
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
Execute beads tasks through the full lifecycle using molecular workflow. Use when asked to "execute tasks", "mol-execute", "run molecular workflow", "cook formula", "execute beads tasks", "task execution", "bug triage", "run task pipeline", "walk the molecule", "atom-based execution". Auto-selects formula based on…
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
Write per-obligation behavioral tests with hard quality enforcement. Use when asked to "obligation test", "write obligation tests", "cover obligations", "obligation coverage", "behavioral test derivation", "per-obligation tests", "test from obligations", "fill obligation allowlist", "reduce obligation allowlist"…
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
Reclassify obligation layers (behavioral vs schema) to shrink the test obligation allowlist without writing integration tests. Use when asked to "reclassify obligations", "shrink allowlist", "reclassify schema obligations", "obligation layer reclassification", "reduce obligation allowlist", "move obligations to schema…
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
Fill test stubs in entity test suites systematically. Use when asked to "remediate tests", "fill test stubs", "convert stubs to tests", "entity remediation", "TDD batch", "implement test stubs", "fix entity test suite", "stub remediation", "batch test implementation". Works batch-by-batch with TDD: write failing tests…
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
Merge, consolidate, or integrate branches with per-file semantic conflict resolution and a behavior-level coherence gate. Use when asked to "semantic merge", "merge branches", "merge two branches", "consolidate branches", "integrate branches", "merge these PRs", "combine branches", "resolve merge conflicts"…
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks to "end session", "complete work", "landing the plane", "finish session", "git push workflow", "session checklist", "push to remote", "how do I finish my work", "commit and push workflow", "finish coding session", "save my work", "end my work session", or needs to properly…
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks to "use TDD", "test-driven development", "write tests first", "red green refactor", "never adjust tests to match code", "fix a bug with TDD", "refactor with tests", "how should I write tests", "test first development", "testing workflow", "write code with tests", "tests…
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
Audit non-obligation tests to classify each assertion's source of truth. Use when asked to "audit tests", "test audit", "classify test assertions", "test source of truth", "how do we know tests are correct", "test authority audit", "characterization test check", "verify test correctness", "audit test quality source".…
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "RAG", "retrieval augmented", "document retrieval", "vector store", "semantic search", "FAISS", "Chroma", "document QA", or needs guidance on implementing RAG patterns with LangGraph.
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "conditional routing", "branch logic", "dynamic routing", "decision edges", "addconditionaledges", "routing function", "state-based routing", "Command API", "Send API", or needs guidance on implementing conditional flow in LangGraph workflows.
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "LangGraph memory", "checkpointer", "InMemorySaver", "PostgresSaver", "thread persistence", "conversation history", "addmessages", "MessagesState", "getstate", "getstatehistory", "updatestate", "StateSnapshot", "time travel", "checkpoint metadata", "fault tolerance"…
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "CRAG", "corrective RAG", "document grading", "query rewriting", "RAG quality", "web search fallback", or needs guidance on implementing quality-aware RAG with LangGraph.
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "deploy LangGraph", "LangGraph Platform", "RemoteGraph client", "LangGraph Studio", "assistants", "cron jobs", "webhooks", "background runs", "task queues", "self-hosted deployment", "FastAPI", "production deployment", "checkpointing", "Docker deployment", or needs…
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "load documents", "text splitting", "chunking strategy", "document loader", "PDF processing", "RecursiveCharacterTextSplitter", or needs guidance on processing documents for RAG systems.
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "error handling", "error recovery", "fallback", "retry logic", "RetryPolicy", "checkpointing", "fault tolerance", "exception handling", or needs guidance on implementing robust error handling in LangGraph workflows.
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "create graph", "add nodes", "add edges", "compile graph", "LangGraph workflow", "StateGraph", "START node", "END node", "graph visualization", "streaming execution", "conditional edges based on output", or needs guidance on building LangGraph workflows.
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "human-in-the-loop", "interrupt", "interrupt()", "interruptbefore", "interruptafter", "breakpoints", "approval workflow", "human feedback", "review workflow", "wait for input", "pause execution", "resume execution", "Command API", "state editing", "human approval"…
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks to "add memory to my agent", "implement persistent knowledge", "store facts across conversations", "add semantic search to memory", "remember user preferences", "build a knowledge base", "implement episodic memory", "add semantic memory", or mentions "Store interface"…
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "multi-agent", "supervisor pattern", "agent coordination", "orchestrate agents", "agent routing", "multi-agent system", "LLM routing", "structured output routing", or needs guidance on coordinating multiple specialized agents in LangGraph.
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "parallel execution", "fan-out", "fan-in", "parallel nodes", "concurrent execution", "supersteps", "state reducers", "Send API", "deferred nodes", or needs guidance on executing multiple nodes simultaneously in LangGraph.
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "optimize performance", "caching", "cost tracking", "async execution", "reduce latency", "token optimization", or needs guidance on improving LangGraph application performance.
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "prompt template", "few-shot", "system prompt", "prompt engineering", "ChatPromptTemplate", "MessagesPlaceholder", "chat history", "format instructions", "LangGraph prompts", or needs guidance on crafting effective prompts for LangGraph workflows.
postindustria-tech/agentic-toolkit
Skill Claude CodeCodex
This skill should be used when the user asks about "ReAct agent", "reasoning agent", "thought action observation", "ReAct pattern", "agent loop", or needs guidance on building ReAct-style agents with LangGraph.