ai-analyst-lab/ai-analyst-plus

ai-analyst-lab/ai-analyst-plus

Hook Claude Code

Runs after a tool call finishes for mcp__snowflake__run_snowflake_query, Bash, Edit, Write, Read, NotebookEdit, MultiEdit, Glob, Grep, WebFetch and mcp__.* tool calls, executing log-snowflake-query.sh and log-action.sh (2 commands). From ai-analyst-lab/ai-analyst-plus.

ai-analyst-lab/ai-analyst-plus

Settings file Claude Code

Agent settings declaring 1 hook event (PostToolUse).

ai-analyst-lab/ai-analyst-plus

Skill Claude CodeCodex

Independently validate the current analysis with a second model (OpenAI Codex). Codex re-derives the same answer from the same data — blind to Claude's SQL and numbers — and the skill reports AGREE / DISAGREE / PARTIAL per finding. Use when the user types "/codex-review", or says "validate with codex", "codex review"…

ai-analyst-lab/ai-analyst-plus

Skill Claude CodeCodex

Run a comparison: ask one analytics question two ways, with a piece of context and without it, and measure what changed. Use when the user says "/compare", "run it with and without ", "does adding change the answer", "is this context worth it", or wants to see whether a metric definition (or any context) moves the…

ai-analyst-lab/ai-analyst-plus

Skill Claude CodeCodex

Run the held-out gold suite live against the analyst and score it. Use when the user types "/eval", or asks to "run the eval suite", "score the system", "run the train split", "check the test split", "what's our accuracy on the gold cases", or wants the system-level eval number (accuracy + query-similarity + cost).…

ai-analyst-lab/ai-analyst-plus

Skill Claude CodeCodex

Check whether an AI analysis answer is STABLE by running the same question several independent times and measuring what holds versus what drifts. Use when the user types "/reliability", or asks to "run this a few times", "is this answer stable / reliable", "check reliability of ", "does it give the same answer again"…

ai-analyst-lab/ai-analyst-plus

Skill Claude CodeCodex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

ai-analyst-lab/ai-analyst-plus

Agent Claude Code

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

ai-analyst-lab/ai-analyst-plus

Agent Claude Code

Compare two outputs WITHOUT knowing which skill produced them.

ai-analyst-lab/ai-analyst-plus

Agent Claude Code

Evaluate expectations against an execution transcript and outputs.

ai-analyst-lab/ai-analyst-plus

Skill Claude CodeCodex

Show the provenance trace — every reported number linked to the SQL that produced it, with a confidence badge. Use after an analysis when someone asks "where did that number come from?".

ai-analyst-lab/ai-analyst-plus

Instructions file

Instructions for ai-analyst-lab/ai-analyst-plus, covering claude.md, claude.md -- ai analyst plus, development, environment setup and running tests.

ai-analyst-lab/ai-analyst-plus

Agent

Every agent .md file MUST begin with a CONTRACT block -- a YAML declaration inside an HTML comment that describes the agent's interface. The OR-3 DAG walker reads these contracts to build the execution graph.

ai-analyst-lab/ai-analyst-plus

Agent

Agent "INDEX" from ai-analyst-lab/ai-analyst-plus, covering agent index, system variables (auto-resolved) and agents.

ai-analyst-lab/ai-analyst-plus

Agent

Agent "causal-analyzer" from ai-analyst-lab/ai-analyst-plus, covering agent: causal analyzer, purpose, inputs, method dispatch and pre-post analysis (prepost).

ai-analyst-lab/ai-analyst-plus

Agent

Agent "causal-assumption-checker" from ai-analyst-lab/ai-analyst-plus, covering agent: causal assumption checker, purpose, inputs, assumption registry and did assumptions.

ai-analyst-lab/ai-analyst-plus

Agent

Agent "causal-interpreter" from ai-analyst-lab/ai-analyst-plus, covering agent: causal interpreter, purpose, inputs, interpretation framework and step 1: place on confidence ladder.

ai-analyst-lab/ai-analyst-plus

Agent

Agent "causal-method-selector" from ai-analyst-lab/ai-analyst-plus, covering agent: causal method selector, purpose, inputs, decision tree and q1: can you randomize?.

ai-analyst-lab/ai-analyst-plus

Agent

Agent "causal-report-generator" from ai-analyst-lab/ai-analyst-plus, covering agent: causal report generator, purpose, inputs, report template (all 8 sections mandatory) and causal analysis report: [question].

ai-analyst-lab/ai-analyst-plus

Agent

Agent "causal-sensitivity" from ai-analyst-lab/ai-analyst-plus, covering agent: causal sensitivity analysis, purpose, inputs, sensitivity tests by method and for psm: rosenbaum bounds.

ai-analyst-lab/ai-analyst-plus

Agent

Agent "chart-maker" from ai-analyst-lab/ai-analyst-plus, covering agent: chart maker, purpose, inputs, workflow and step 0.5: apply fix report (when {{fixreport}} is provided).

ai-analyst-lab/ai-analyst-plus

Agent

Agent "cohort-analysis" from ai-analyst-lab/ai-analyst-plus, covering agent: cohort analysis, purpose, inputs, workflow and pre-flight checks.

ai-analyst-lab/ai-analyst-plus

Agent

Agent "comms-drafter" from ai-analyst-lab/ai-analyst-plus, covering agent: comms drafter, purpose, inputs, workflow and step 1: read preferences.

ai-analyst-lab/ai-analyst-plus

Agent

Agent "confound-scanner" from ai-analyst-lab/ai-analyst-plus, covering agent: confound scanner, purpose, inputs, output formatting rules and workflow.