Companion repo for Agentic Graph RAG (O'Reilly, Anthony Alcaraz & Sam Julien) — 50 runnable skills + 8 pedagogical notebooks covering all eight chapters, on one moto-mocked AWS DevOps scenario
This repository also configures its own agents. See what agentic-graph-rag-skills tells them →
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Route an incoming request to the VERTICAL knowledge graph (what the agent knows — a single relationship/temporal traversal), the HORIZONTAL workflow graph (how the agent acts — a decomposed multi-step process), BOTH (a workflow whose nodes query the knowledge graph and write results back), or UNROUTABLE (neither fits…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Map an agentic-graph system's current capabilities across the eight pillars of Agentic GraphRAG Ch2 (knowledge representation, memory, reasoning, planning, tool orchestration, structured output, self-evolution, optimization), respect the chapter's layering (each pillar depends on the ones before it), flag dependency…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Split a workflow description into constrained harness nodes using the chapter's rule "nodes differ by tool surface, not by prompt." Given candidate operations each with a declared tool set, merge the ones whose tool surfaces overlap >= 80% (prompt variations of one role) and split the ones with distinct tool surfaces…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Score an agent configuration against Ch1's Agent Constraint Triangle — the three interconnected constraints (complexity management, tool orchestration, context utilization) that make agent design an inherently difficult operational problem. Given the agent's reasoning-chain length, tool-catalog size and disambiguity…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Classify an observed agent symptom into Ch1's context-failure taxonomy. Given a sentence describing what an agent did wrong, name the agent-level failure mode (action blindness / memory fragmentation / planning paralysis / context drift / tool chaos), the architectural root cause among the five fatal flaws, and the…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Score a proposed or deployed enterprise agent against the architectural requirements Ch1 argues are non-negotiable: absence of the five fatal flaws of naive vector RAG (context amnesia / relationship blindness / temporal ignorance / reasoning paralysis / tool chaos), calibration of the three agency dimensions…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Recommend VECTOR / GRAPH / HYBRID retrieval for a query workload, grounded in Ch1's BenchmarkQED evidence for where vector RAG succeeds and where it collapses. Classifies the workload on the BenchmarkQED scope x type axes (local/global, data/activity), weighs multi-hop / temporal / associativity needs, domain…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Place an AI system on Ch1's continuous workflow-agent spectrum instead of the false binary "is it an agent or not". Scores the three dimensions of agency (autonomy / action / authority) plus how predefined the execution path is, returns a spectrum position (0 = workflow, 1 = agent) and a band (WORKFLOW / BLENDED /…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Runtime authorization gate built on the Ch3 Capability Model Pattern — a self-aware agent represents its own capabilities, required resources/grants, authorization level, and quantitative limits as queryable structure, then checks at PLANNING time whether it may perform an action BEFORE attempting it. Returns allow…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Choose HOW to decide when two records are the same real-world entity — EVIDENCE-BASED resolution (deterministic feature-by-feature scoring with explainable evidence and culturally-robust rules) vs GENERALIZATION-BASED AI (LLM statistical similarity, nondeterministic, post-hoc rationalization) — per Ch3 "Entity…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Select a graph data model — labeled property graph (LPG) vs RDF vs hypergraph — by scoring REASONING REQUIREMENTS against five implementation features (formal reasoning, n-ary relations, performance, tool ecosystem, constraint expressiveness), per Ch3 "Evaluating Graph Models". Also models the n-ary -> hyperedge…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Homoiconic knowledge representation (Ch3) — code and data share the same representation so an agent can inspect and modify its own knowledge structures with the same machinery it uses for regular data. Two constructs: (1) meta- knowledge structures (Example 3-6) — validate an entity-type against the metaschema AND a…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Select a knowledge-graph EXTRACTION approach for a given source — structured database integration vs LLM-based triple extraction vs iText2KG (incremental) vs RAKG (document-level) — by scoring a SOURCE PROFILE against five features (handles unstructured text, incremental-friendly, document-level context, determinism…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Classify an organizational vocabulary onto the Ch3 knowledge-organization spectrum — pick list -> taxonomy -> thesaurus -> ontology — by the structural features the spec actually exhibits, walking bottom-up so a partial ontology does NOT over-claim. Also validates that something claiming to be an ontology carries the…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Select and validate the four agent schema design patterns from Ch3 — Event-Centric (temporal reasoning), Contextual-Boundary (scope/validity boundaries), Multi-Perspective (contradictory viewpoints with attribution and confidence), and Capability-Model (agent self-awareness of authority limits). Given a free-text…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Route an incoming record/fact into the correct graph of the Three-Graph Architecture (Ch3) — DOMAIN (trusted, entity-resolved single source of truth), LEXICAL (verbatim source text with provenance, the "retrieval" in RAG), or SUBJECT (LLM-extracted artifacts kept SEPARATE from domain until entity resolution links…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Bi-temporal edge primitive for agentic graph memory. Tracks two independent time dimensions per relationship: when the relationship was VALID in the domain (validfrom / validuntil) and when the system LEARNED about it (ingestedat). Enables point-in-time queries like "What was the EC2 instance type for…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Graphiti (Zep) incremental-update pattern (Ch4). When new content arrives, process only the new content — never re-process the entire graph. Pipeline: (1) extract entities from new episode, (2) entity-resolve against existing graph (dedupe by canonical name + alias + fuzzy match), (3) incremental- update — touch only…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Three-tier hierarchical memory (Letta / MemGPT pattern) — core / recall / archival. Core holds a small, fast, frequently-accessed working set (e.g. corelimit=2000 tokens). Recall holds raw interaction history for "what did we talk about yesterday" questions. Archival holds effectively unlimited overflow, still…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Classify facts into HINDSIGHT's 4 epistemic networks (Latimer et al. 2025, cited in Ch4): World (objective external facts), Experience (agent's own first-person actions), Opinion (subjective beliefs with confidence), and Observation (synthesized entity summaries). The separation enables traceability — when users ask…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Reviewer skill: diagnose an agent's memory architecture against the 8 Letta Leaderboard failure modes (Ch4). Takes a memory snapshot (or a description of the architecture) and reports which failure modes are present, with concrete evidence and recommended fixes. Use BEFORE shipping any memory implementation to…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Choose a memory consistency model PER agent-coordination operation — STRONG (linearizable), CAUSAL, READ-YOUR-WRITES, or EVENTUAL — by scoring the operation's requirements (shared authoritative state, conflict intolerance, staleness budget, collaboration, self-session continuity), per Ch4 "Memory consistency models…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Consolidation pipeline — turn noisy raw episodes into durable knowledge (Agentic GraphRAG Ch4, Example 4-5 + Example 4-13). Four steps: cluster related episodes by topic, summarize each cluster into one consolidated fact, create the consolidated node, and maintain a provenance chain back to the source episodes so "how…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Reciprocal Rank Fusion (RRF) hybrid retrieval across 4 parallel channels — semantic / keyword / graph-traversal / temporal — followed by cross-encoder rerank and token-budget filter (HINDSIGHT, Latimer et al. 2025, cited in Ch4). Rank-based fusion means scores don't need calibration across channels; absent items…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: