skills.rest
Raudbjorn
RaudbjornCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

decision-graph-analyzer

Query and analyze AI Counsel decision graphs for patterns and memory issues.

Updated Dec 14, 2025
Search Tags:#semantic search#SQLite#data analysis#AI memory#decision graph#context injection#deliberation history
One-click install
npx skills add https://github.com/Raudbjorn/cognitive-construct --skill decision-graph-analyzer-raudbjorn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: decision-graph-analyzer
Source: https://github.com/Raudbjorn/cognitive-construct/tree/main/rhetoric/scripts/ai-counsel/.claude/skills/decision-graph-analyzer
Command: npx skills add https://github.com/Raudbjorn/cognitive-construct --skill decision-graph-analyzer-raudbjorn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Understanding the history, patterns, and evolution of AI-driven decisions can be challenging without proper tools. This Skill provides comprehensive capabilities to query, analyze, and troubleshoot the AI Counsel decision graph, transforming past deliberations into actionable intelligence.

Core Features & Use Cases

  • Similar Decision Retrieval: Find past deliberations related to a new question using semantic similarity, providing valuable context for current debates.
  • Database Statistics & Health: Monitor the growth, check the integrity, and debug performance of the SQLite-based decision graph memory.
  • Cache Performance Analysis: Diagnose slow queries and optimize cache configuration for efficient context injection.
  • Tiered Context Formatting: Understand how context is dynamically formatted (strong, moderate, brief) to fit token budgets and maximize relevance.
  • Use Case: Before making a new architectural decision, query the decision graph to see if a similar topic has been debated before. Identify any contradictions in past advice or trace how opinions on a specific technology evolved over time, ensuring decisions are informed by historical context.

Quick Start

To find similar past decisions for a new question, use the integration: integration.get_context_for_deliberation("Should we adopt TypeScript for the project?")

Frequently Asked Questions about decision-graph-analyzer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find past AI decisions similar to a new question I'm facing?▼

Semantic search retrieves past deliberations from the decision graph by analyzing question similarity, returning relevant historical context to inform current decisions. Use integration.get_context_for_deliberation() with your new question to surface comparable past debates and advice.

What is a decision graph and how does it store AI deliberation history?▼

A decision graph is a SQLite-based memory system that records AI reasoning, decisions, and context. It enables retrieval of past deliberations, pattern detection across decisions, and analysis of how opinions on specific topics evolved over time.

How do I debug slow queries and cache performance in my decision graph?▼

Cache performance analysis identifies bottlenecks in context retrieval by examining query latency and two-tier cache hit rates. Monitor SQLite health checks and growth analytics to diagnose performance issues and optimize cache configuration for faster context injection.

Can I detect contradictions or inconsistencies in past AI decisions?▼

Yes. Query the decision graph to trace how recommendations on specific technologies or approaches have evolved or conflicted across past deliberations. Noise-floor filtering isolates significant pattern shifts from minor variations in reasoning.

What database maintenance and monitoring does the decision graph provide?▼

Built-in health checks, growth analytics, and CRUD operations on the SQLite backend track memory usage, cache efficiency, and data integrity. Maintenance tooling identifies stale entries and optimizes storage without manual intervention.

Related Skills

Explore More Data & Analytics Skills→
discountedcookiediscountedcookie

postgres-vectors

Store 384-dimensional embeddings in Postgres and query cosine similarity with pgvector.

Community
Advanced
henrique-simoeshenrique-simoes
13

nps-analysis

Compute Net Promoter Score and analyze survey data by segment and trend.

Community
Intermediate
techwavedevtechwavedev

qdrant-memory

Cache LLM responses and retrieve relevant context with Qdrant vector search.

Community
Advanced
FVossebeldFVossebeld

memory-systems

Store and retrieve structured memories with vector and graph search.

Community
Advanced