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…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Score a multi-model routing policy on cost versus quality using the two metrics that actually decide selective intelligence: cost per successful completion (not cost per token) and a per-node quality parity threshold with domain-specific failure weights. Wraps a NodeInvocation log, computes cost-per-success and p95…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Budget a specialist model fleet against the two production bottlenecks: KV-cache-bound concurrency and end-to-end latency. Computes how many concurrent users a GPU can host (peak KV per active user, not model size, is the binding constraint), proves that quantizing weights does not move that ceiling while KV…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Match model capability to task complexity across a horizontal workflow graph. Given a node, pick the cheapest model that meets its quality bar, using one of three routing strategies: static routing by node type, threshold-based cascading (FrugalGPT), or learned routing (RouteLLM / MixLLM). Re-derives the book's DevOps…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Keep a production knowledge graph healthy across schema evolution, node/edge lifecycle, incremental updates, and coordinated deployment. Emits N-1 compatible Neo4j-Migrations-style schema migrations, temporal-invalidation Cypher (bitemporal tvalid/tinvalid, invalidate-not-delete), LightRAG-style incremental merge from…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Scope what each agent persona can see in a knowledge graph. Generates Neo4j fine-grained GRANT/DENY policy (traverse on node labels + relationship types, read on properties) per persona role, enforces security transparency (out-of-scope nodes are invisible, not access-denied), handles PII via the UUID-separation…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Validate a generated plan against extracted domain constraints AND the agent's capability model before execution (Ch5 Constraint-guided planning, Example 5-14, plus the DevOps hypothesis-formation capability filter). Scores the plan 0..1, returns structured per-step feedback so a planning node can refine when the…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Dynamic-DAG construction for a planning node (Ch5 Example 5-15 + the DevOps "Constructing the Investigation DAG" section). Given hypotheses/tasks with dependency constraints, compute a topological-level decomposition: each level is a phase of tasks that can run concurrently, ordered within-phase by priority. The…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
The conditional-edge routing that turns a validate node into a bounded self-correcting loop (Ch5 Loop Pipeline + Error-handling strategies, Examples 5-6/5-9). Consumes a validation result, an error severity (correctable vs fundamental), and a retry budget, and returns exactly one of: proceed, refine (loop back with a…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Controlled-parallelism window for a tree pipeline (Ch5 Tree Pipeline + "The architecture of controlled parallelism" + state reducers, Examples 5-7/5-8/5-16). Dispatches independent branches that read different data and write to separate channels, isolates errors per-branch so one branch's failure neither cascades nor…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Treat pipeline-architecture choice as a routing decision inside a meta-pipeline (Ch5 Hybrid Architectures, Examples 5-10/5-11). A single analysis pass over task characteristics — complexity and answer-uncertainty — selects sequential (simple + certain), tree (high uncertainty, explore hypotheses), or loop (iterative…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Design the OUTPUT CONTRACT for a graph-agent node's seam, per Ch5 "Structured Generation: The Keystone of Reliable Communication" (Outlines). Most graph-agent failures are internode COMMUNICATION breakdowns, not bad reasoning — a node that emits free text is unreliable exactly where its output feeds the next node or a…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Locate a proposed self-evolution in the four-dimensional design space Gao et al. (2025) formalize: WHAT evolves (model / context / tool / architecture), WHEN it fires (intra-test-time within one request / inter-test-time between requests), HOW the agent learns (reward / imitation / population), and WHERE it applies…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Foundational Ch7 primitive: an immutable, queryable graph of every decision / retrieval / tool-call / LLM-call an agent made for a specific query. Nodes are atomic operations carrying input/output/timestamp/ latency/cost/tokens; edges are TRIGGERED relationships establishing the full causal lineage. Two-phase write …
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
The Multi-Layered Evaluation Framework as a sequential diagnostic cascade that STOPS at the first failing layer. Layer 0 is a zero-shot hallucination gate (NLI grounding, catches 60-70% of hallucinations at under 5% of full-judge compute). Layer 1 is a context evaluator (binary sufficient/not). Layer 2 is a cognitive…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
The Ch7 safety envelope for a self-evolving agent: the RPO spine (Recursion, Provenance, Optimization) plus the Graduated Validation Protocol that gates what reaches production. Assigns every candidate change a risk tier and applies the matching scrutiny: Tier 1 canary (1% traffic, automatic rollback), Tier 2 staging…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Ch7 self-evolution router: map a diagnostic report to exactly one intervention, deterministically and auditably, not as a per-engineer judgment call. Four branches in strict order: insufficient context -> RETRIEVALFIX, FORMATVIOLATION -> STRUCTURALCONSTRAINT, localized REASONING failure with intact knowledge ->…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Ch7 self-evolution primitive: attribute a failure to the node that actually caused it, then generate NEIGHBOR-AWARE textual feedback that flows backward through the execution graph from the point of failure. Adapts TextGrad's textual-gradient insight (feedback as a gradient signal) plus the chain rule: when generating…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Turn execution traces into knowledge that improves without retraining. Two Ch7 primitives compose: XSkill dual-stream extraction distills EXPERIENCES (action-level: what worked or failed for one tool call) and SKILLS (task-level: a multistep pattern that solves a category of task) from the execution graph. Cognee then…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Establish trust in a tool by verification, not by its self-description. Flags marketing-gamed tool descriptions ("industry-leading", "trusted by Fortune 500"), requires structured testable capabilities instead of free-text claims, tracks a performance-based trust score (neutral start, successes up, failures and slow…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Govern agent-configuration drift once tool orchestration scales from one developer to a team. Detects where independently-authored context configs (CLAUDE.md-style settings + installed skills) diverge, classifies the fragmentation stage, enforces a FEDERATED org base whose nonnegotiable settings (security…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Expose ONE orchestrator to the agent instead of thousands of tools. Classifies a query into a department domain (Sales / Finance / Operations); routes to that domain's orchestrator when confidence exceeds 0.8, else orchestrates cross-domain. Within a domain, clusters tools by FUNCTION so an overloaded or failing tool…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
A deterministic security-policy layer for chained tools. Does two things: (1) discovers tool dependency chains by matching one tool's output TYPE to another tool's input TYPE (the NESTFUL failure mode where LLMs miss that COVID stats need a country code first); (2) tracks data taint with FIDES-style TRUSTED/UNTRUSTED…
AnthonyAlcaraz/agentic-graph-rag-skills
Skill Claude CodeCodex
Gate agent tool calls by reversibility BEFORE execution: classify each action REVERSIBLE / SEMIREVERSIBLE / IRREVERSIBLE from its declared properties (side-effect scope, idempotency, destructiveness, compensating action), prescribe the matching delivery contract (idempotency key, retry policy, dry-run-first, human…