Claude Skills by ai-analyst-lab

{{BLANK_2_WHEN_TO_FIRE}}

Ensure every analysis starts with a clear plan — what question it answers, what decision it informs, what data it needs, and what "done" looks like — before any queries are written or data is explored.

Retrieve proven SQL patterns, table cheatsheets, and join patterns from the query archaeology store so agents reuse validated work instead of writing SQL from scratch.

Run the multi-persona planning methodology to produce a master plan for a new project or feature.

Save a completed analysis to the knowledge system's analysis archive for future recall. Captures key findings, metrics used, agents invoked, and output file paths so that past work can be referenced in future sessions.

> Interactive browser for your organization's knowledge system. Explore terms, > products, metrics, objectives, and team structure.

Ensure every analysis that includes a recommendation ends with a clear follow-up plan — who decides, what metric tracks success, when to check back, and what to do if the expected outcome doesn't materialize.

Compare metrics, findings, and patterns across two or more connected datasets. Helps identify cross-dataset patterns (e.g., "conversion funnel behavior is similar across both product lines") and dataset-specific anomalies.

Guided wizard to connect a new dataset. Walks the user through selecting a connection type, configuring credentials, validating the connection, profiling the schema, and setting up the knowledge brain.

Show the active dataset's schema — tables, columns, row counts, and relationships. Optionally drill into a specific table.

Deep-profile the active dataset to understand schema structure, value distributions, temporal patterns, correlations, completeness gaps, and anomalies. Produces a comprehensive profile report that serves as the foundation for analysis planning and data quality assessment.

Validate data completeness, consistency, and coverage before any analysis begins, flagging issues with severity ratings so the analyst knows what blocks analysis vs. what to note as a caveat.

List all connected datasets with their status, table counts, and last analysis date.

Quick, interactive data exploration without the full pipeline. Lets users poke around the active dataset — preview tables, check distributions, spot patterns, and form hypotheses before committing to a formal analysis.

Export analysis results in different formats for different audiences. Converts pipeline outputs into ready-to-share deliverables.

Pre-router interceptor that runs BEFORE the Question Router on every user message. Detects correction signals, methodology learnings, and positive feedback, captures them to `.knowledge/`, then passes through to normal routing.

Provide an adaptive welcome experience based on setup state. Routes new users through `/setup` for guided onboarding. Welcomes returning users with context about their active dataset and quick actions.

Generate time-series forecasts for key metrics using the forecast_helpers library. Supports naive baselines, seasonality detection, and exponential smoothing — enough to answer "what should we expect next?" without complex modeling.

Ensure that every success metric is paired with at least one guardrail metric, and that positive findings are checked for trade-offs before being presented as wins.

Browse and search past analyses from the analysis archive. Helps users recall what they've analyzed before, find prior findings, and build on previous work.

Initialize all 7 knowledge subsystems for a new session. Loads setup state, dataset, user profile, integrations, org context, corrections, learnings, query archaeology, and analysis archive into working memory.

Record analyst mistakes and their fixes so future analyses learn from past errors. Manual counterpart to automatic feedback capture.

Define any metric clearly and completely using a standardized template so there is no ambiguity about what is being measured, how it's calculated, or how to interpret it.

Browse, search, and display metric definitions from the active dataset's metric dictionary. Provides quick access to how metrics are defined, computed, and validated.

> Crawls a Notion workspace to extract business terms, metrics, product docs, > and team structure. Populates the organization knowledge system.

Browse and search recurring patterns discovered across analyses. Patterns are auto-extracted after each analysis archive and represent behaviors that appear consistently in the data.

Generate slide decks that look professional, tell a coherent analytical story, and follow consistent theme standards matching the visualization patterns.

Structure analytical questions using the Question Ladder framework so every analysis starts with a clear decision context, measurable success criteria, and testable hypotheses.

Classify incoming user questions into complexity levels (L1-L5) and route them to the appropriate response path. This replaces the old "skip-step" logic with a structured classification that adapts the workflow depth to the question's actual needs.

Resume an interrupted analysis pipeline by reading `working/pipeline_state.json`, determining which agents completed, and continuing from the next READY agents using the DAG walker.

Single entry point for end-to-end analysis — from raw data to finished slide deck. Uses a DAG-based execution engine that reads agent dependencies from `agents/registry.yaml`, resolves execution order automatically, and supports parallel agent execution, resume from failure, and execution plan pruning.

Browse, inspect, compare, and clean up past pipeline runs. Each run is a self-contained directory under `working/runs/` with its own working files, outputs, and pipeline state.

Orchestrate the full 4-layer validation stack plus confidence scoring to produce a comprehensive data quality assessment for any analysis output.

> Standalone skill for teams integrating AI Analyst into development workflows. > Most users (PMs, execs, DS) never need this — only teams doing codebase integration.

Run a 4-phase conversational interview that populates the knowledge system from the user's real context. Turns a blank `.knowledge/` directory into a fully configured analytical environment.

Adapt analytical findings to the audience — same insight, different framing, detail level, and format depending on who will read it. Ensures that executives get the bottom line, PMs get the implications, engineers get the specifics, and data teams get the methodology.

Change the active dataset. Updates the active pointer, validates the target dataset exists, and confirms with a summary of what's now active.

Assess whether the data needed for an analysis actually exists, identify what's missing, and produce prioritized instrumentation requests for engineering when gaps are found.

Cross-reference analytical findings against multiple data sources, external benchmarks, and common sense to catch errors before they become bad decisions.

Ensure every chart Claude Code produces follows high-quality design standards with named themes, consistent styling, and clear data communication.