ai-analyst-lab

@ai-analyst-lab source repo

64 skills
0 followers
5 hours ago last updated

▌
Context Compare · ai-analyst-lab
Advanced: runs the same question under two configurations and diffs the results. Ask one analytics question with a piece of context and without it, and measure what changed. Trigger on "/context-compare", "run it with and without <the definition/context>", "does adding <X> change the answer", "is this context worth it".

0 installs
▌
Evaluate Grader · ai-analyst-lab
Compare a narrow model grader with frozen human labels and inspect disagreement, bias probes, and repeated scoring stability. Use when building or changing a model-based evaluator.

0 installs
▌
Improve Context · ai-analyst-lab
Diagnose a context-related analytical failure, propose the smallest relevant change, compare the same evaluation cases before and after, and produce an accept, revise, or revert receipt. Use when the user asks to improve context, fix a definition or example, test whether context helped, or invokes /improve-context.

0 installs
▌
Question Router · ai-analyst-lab
Classify every analytical request (anything about data, metrics, trends, segments, funnels, revenue, retention, experiments, or "why did X change") into complexity levels L1-L5 and route it before any analytical workflow starts, including follow-ups mid-analysis and chart requests. Simple lookups get a direct answer; investigations get the depth they need. Run this first even when the question looks simple.

0 installs
▌
Resume Pipeline · ai-analyst-lab
Resume a specifically identified analysis using its verified run-local artifacts and controller state.

0 installs
▌
Session Handoff · ai-analyst-lab
Preserve critical state when a session approaches context limits so the next session can pick up seamlessly. Use this skill whenever you're in a long, multi-step workflow, working with Google Workspace resources (Docs, Slides, Drive), creating external resources that have IDs you need to track, running multi-step pipelines that might need to be resumed, approaching context limits, or when the user says things like "save state", "let's pause", "I'll come back later", "save progress", "I need to stop for now", "bookmark this", "save my work", or when you detect that a workflow involves multiple phases and the user might return later. This skill is CRITICAL after creating Google Docs, Slides, or Drive files — those resource IDs are impossible to recover if lost. Also apply proactively during analysis pipelines after major phases complete (data exploration done, charts generated, narrative written, deck created) so users can resume at natural checkpoints. Write session state immediately after any external resourc

0 installs
▌
Setup Snowflake · ai-analyst-lab
First-time Snowflake setup wizard for the NATIVE ConnectionManager path (the connection the analyst actually queries through, with auto-logged provenance). Prompts for every connection field, stores the approved credential in .env, registers the dataset, and VERIFIES the session is live on the warehouse before declaring success. Use when the user says "set up snowflake", "connect to snowflake", "configure the warehouse", or is routed here from /connect-data. For day-to-day remote querying after setup, use connect-snowflake. An optional Snowflake MCP server (for interactive ad-hoc queries) is covered in the appendix.

0 installs
▌
Archive Analysis · ai-analyst-lab
Save completed analyses to the knowledge system's analysis archive for future reference. Use this skill after completing any L3+ analysis, when `/run-pipeline` completes, when the user explicitly says "save this analysis" or "archive this", or automatically at the end of Step 18 (Close the Loop) in the analysis workflow. This skill captures key findings, metrics used, agents invoked, and output file paths so past work can be referenced in future sessions. Trigger whenever you finish validation on a multi-step analysis, complete an analytical deck, wrap up a root cause investigation, finish an opportunity sizing exercise, or close any analysis that produced deliverables worth preserving. Also apply when the user mentions saving work, archiving results, preserving findings, or wants to ensure an analysis can be recalled later. This is your analytical memory system — use it proactively to build institutional knowledge.

0 installs
▌
Compare Datasets · ai-analyst-lab
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. Use this skill whenever the user wants to compare datasets, mentions phrases like "compare datasets", "is this pattern the same across", "how does X differ between datasets", "cross-dataset comparison", "analyze across product lines", "compare metrics between", or asks whether a finding is unique to one dataset or appears universally. Also trigger when the user has analyzed multiple datasets sequentially and might benefit from seeing commonalities and divergences side-by-side. If you've just finished analyzing dataset A and the user switches to dataset B to run similar queries, proactively offer to compare the two. This skill is valuable for identifying where business patterns are universal vs. dataset-specific, spotting metric definition inconsistencies, and finding opportunities to apply

0 installs
▌
Experiment Brief · ai-analyst-lab
Auto-generate a structured experiment brief when a user expresses intent to test something. Use this skill whenever users mention testing, experiments, A/B tests, or want to validate a product change with data. Trigger on phrases like "I want to test...", "Let's experiment with...", "Should we A/B test...", "Can we test whether...", "I think X will improve Y", "We should validate...", "Let's try...", or any request involving running an experiment or measuring the impact of a change. This skill is your "think before you design" safety net — it forces clarity on hypothesis, metrics, guardrails, success criteria, and feasibility BEFORE any statistical design work begins. Apply this skill automatically when experiment intent is detected, even if the user hasn't explicitly asked for a brief. The skill ensures every experiment starts with a clear hypothesis (what change, what metric, what mechanism), exactly ONE north star metric (force a choice if multiple metrics are mentioned), guardrail metrics (what must not b

0 installs
▌
Question Framing · ai-analyst-lab
Structure analytical questions with the Question Ladder (Goal, Decision, Metric, Hypothesis), then fill the 7-field Analysis Design Spec, before touching data. Trigger on "analyze", "investigate", "look into", "why did", "what's happening with", "what happened with", "figure out", "explore", "deep dive", "what caused", "compare", "breakdown", "root cause", "show me", "pull", "calculate". Framing first, analysis second.

0 installs
▌
Connect Snowflake · ai-analyst-lab
Query the live/remote Snowflake warehouse instead of the local practice copy. Use when the user says "connect to snowflake", "use the live data", "go remote", "query the warehouse", or asks "is this hitting snowflake or duckdb?". Assumes credentials already exist (first-time setup is /setup-snowflake); opts into remote via ConnectionManager and verifies the connection type before any query runs.

0 installs
▌
Google Doc Export · ai-analyst-lab
Create properly formatted Google Docs via the MCP API. This skill prevents common issues like text/image overlap, broken heading hierarchy, excessive whitespace, and inconsistent formatting. Use this skill automatically whenever you're building a Google Doc, calling any Google Docs MCP tool on the google-workspace server (create_doc, insert_doc_elements, insert_doc_image, batch_update_doc) or the google-docs server (upload_file_to_drive, write_formatted_content), designing a document structure, or when the google-doc-creator or google-doc-reviewer agent is running. This skill is essential for ANY workflow involving Google Docs creation, document formatting, analysis writeups in Google Docs, report generation to Docs, chart embedding in documents, or exporting analysis results to shareable Docs. Make sure to use this skill whenever the user wants to create a Doc, export to Google Docs, share analysis as a Doc, build a formatted document, or mentions Google Docs in any capacity.

0 installs
▌
Setup Dev Context · ai-analyst-lab
Configure AI Analyst to understand your development environment and codebase structure. Use this skill whenever developers need to integrate AI Analyst into their workflow, or when questions arise about database configuration, SQL conventions, schema naming patterns, dbt integration, warehouse connections, or team-specific data practices. Trigger this skill when users mention: "set up for our team", "configure for our codebase", "integrate with our database", "tell it about our SQL conventions", "set up dbt integration", "configure schema prefix", "set up warehouse connection", "integrate with our data stack", "configure for development", "set up team conventions", or any request about configuring AI Analyst to work with an existing development environment, data warehouse, or analytics infrastructure. This is ONLY for development teams integrating AI Analyst into their codebase. Most users (PMs, execs, data scientists doing ad-hoc analysis) should use `/setup` instead. Only invoke this when the user explicitl

0 installs
▌
Data Quality Check · ai-analyst-lab
Validate data completeness, consistency, and coverage before any analysis, flagging issues with severity ratings. Run at the start of every new analysis. Trigger on "check data quality", "is the data clean", "validate the data", "run a quality check", "what's the coverage", and on named-table questions: "tell me about the {table} table", "describe {table}", "what's in {table}"; pair schema answers with a minimum DQ probe.

0 installs
▌
Knowledge Bootstrap · ai-analyst-lab
Initialize session context, resolve the active dataset and context source, load resident instructions, and inventory the context available for question-specific selection. Run at the start of every session and again after /connect-data or /switch-dataset. Handles missing files gracefully, so running it when unsure is harmless.

0 installs
▌
Google Slides Export · ai-analyst-lab
Create properly formatted Google Slides presentations via the MCP API. Use this skill whenever you're building Google Slides decks, calling batch_update_presentation, designing slide layouts, or the google-slides-creator or google-slides-reviewer agents are running. This skill prevents common API errors (zero-weight outlines, short object IDs, oversized batches, text overflow) and ensures professional deck design with consistent brand styling, proper spacing, and no overlapping elements. Apply this automatically when any MCP Google Slides API calls are being made, when converting Marp decks to Google Slides, when creating presentation decks for analysis results, when building slide decks for stakeholders, or any time the user mentions "Google Slides", "export to slides", "create a presentation", or "share as slides". The skill provides a complete design system (color palette, layout zones, font hierarchy) and pre-validated slide type recipes (title slide, section divider, header + bullets, KPI cards, two-colu

0 installs
▌
Distribution Profiler · ai-analyst-lab bundle
Single-column distribution deep-dive. Profile the statistical distribution of a data column and produce an analytical playbook: distribution identification, valid summary stats, recommended tests, A/B guidance, traps. Trigger on "profile this column", "what distribution is this", "check the distribution", "is this normal", "what test should I use", "check assumptions before A/B test", "how is this data distributed".

0 installs
▌
Visualization Patterns · ai-analyst-lab
Apply whenever you generate any chart, graph, or data visualization — from SQL results, in the chart-maker agent, in decks, or on "make a chart / visualize / plot / dashboard" requests. Enforces Storytelling With Data: gray first, one focus color, action titles, direct labels, no pies, using the helpers in helpers/viz/chart_helpers.py.

0 installs
▌
Stakeholder Communication · ai-analyst-lab
Adapt analytical findings to the audience — same insight, different framing, detail level, and format depending on who will read it. Use this skill whenever producing a narrative, creating a deck, writing an executive summary, drafting a report, generating stakeholder communications, or whenever the user mentions an audience (executive, PM, engineer, data scientist, leadership team, stakeholders, decision-makers). Apply when users say things like "prepare this for leadership", "write this for the product team", "explain this to engineering", "create a deck for the VP", "draft a summary for stakeholders", "make this executive-friendly", "adapt this for data scientists", "what should I tell the CEO", "how do I present this", "tailor this for the audience", or any request involving communication, presentation, reporting, or sharing findings with others. Always apply when the Storytelling agent runs, when the Deck Creator agent runs, when drafting communications, when exporting results, or when the output will be

0 installs
▌
Monitor Evals · ai-analyst-lab
Review evaluation history, distinguish system, data, suite, and evaluator changes, and apply an operating response. Use for regressions, eval monitoring, release gates, or trend questions.

0 installs
▌
Notion Export · ai-analyst-lab
Publish an approved analysis as a Notion text page through the official hosted MCP. Use when the user asks to export, publish, create, share, put, or send analysis results to Notion.

0 installs
▌
Tracking Gaps · ai-analyst-lab
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. Use this skill whenever you're about to start an analysis, when a user asks about data availability, when you need to check if certain events or properties are tracked, when the Data Explorer agent finds incomplete data, when you're designing an analysis and need to verify data exists, when initial queries return nulls or missing values, when a user mentions "do we track...", "is there data for...", "can we measure...", when you're writing an instrumentation request, when you need to assess data completeness, when planning metrics or experiments that require specific tracking, when a user wants to know what data gaps exist, or any time you need to map analytical requirements to available data sources. This skill should be applied proactively before committing to an analytical approach to avoid wasted work on analyses that can't be comple

0 installs
▌
Triangulation · ai-analyst-lab
Analyze one decision through independent methods or sources, compare the paths, and reconcile disagreement. Use when a novel analysis needs corroboration and no single answer key is available.

0 installs
▌
Always Compare · ai-analyst-lab
Never present a metric or number in isolation; anchor every number to a comparison (prior period, benchmark, or another segment) or state that none is available. Use every time you show a number: rates, counts, revenue, averages, query results, chart labels, summary stats. Trigger on output containing "the rate is", "we saw", "total", "average", "conversion", "revenue", "users", "sessions", "churn", "AOV", "NPS", or any figure pulled from data.

0 installs
▌
Auth Preflight · ai-analyst-lab
Verify Google Workspace MCP authentication at the start of any session that needs Google APIs (Docs, Slides, Drive). This skill prevents auth failures mid-workflow by testing credentials upfront. Use this skill automatically at session start when the task involves Google Docs, Google Slides, Drive uploads, or any MCP Google Workspace tool. Also trigger when users mention "Google Doc", "Google Slides", "upload to Drive", "export to Google", "share on Drive", or any Google-related output format. Apply before running any Google Workspace agents (google-slides-creator, google-slides-reviewer) or calling any mcp__google-* tool. This skill detects the actual MCP configuration, checks stored credentials in all known locations, tests tokens with a lightweight API call using create operations instead of reads, handles re-authentication if needed, and reports auth status clearly so downstream work can proceed safely or fail fast with actionable guidance.

0 installs
▌
Chart To Drive · ai-analyst-lab
Standardized workflow for uploading local chart PNGs to Google Drive and making them available for insertion into Google Docs and Slides. Use this skill whenever you need to insert charts into Google Docs or Google Slides, when the google-doc-creator or google-slides-creator agents need chart URLs, when building presentations or reports with embedded visualizations, when user asks to "upload charts", "add images to the doc", "put charts in slides", "make charts available for Google", or any time you have chart PNG files that need to be referenced in Google Workspace documents. One standard flow for upload, permissions, and URL construction, with no public file hosts involved. Always use this skill before calling insert_doc_image or createImage APIs — those require public Drive URLs, which this skill produces. Also use when you see errors like "image URL not accessible" or "permission denied" during doc/slide creation — those usually mean charts weren't properly uploaded to Drive first.

0 installs
▌
Close The Loop · ai-analyst-lab
Ensure every analysis that includes a recommendation ends with a clear, actionable follow-up plan. CRITICAL RULE - Only use this skill AFTER a specific recommendation has been made. Use this skill at the end of ANY analysis that produces a recommendation, action item, suggested fix, proposed investment, or conclusion that says "we should do X." This skill is CRITICAL for turning analytical insights into actual business outcomes — without it, recommendations get forgotten and never evaluated. Apply this skill whenever you complete an analysis with findings that suggest a course of action, finish a root cause investigation that identifies a fix, complete an opportunity sizing that recommends an investment, produce a deck or report with recommendations, or any time the analysis concludes with "we should..." or "I recommend...". Even if the user doesn't explicitly ask for follow-up tracking, add the close-the-loop checklist automatically — it's a mandatory step for any analysis with recommendations. DO NOT USE th

0 installs
▌
Data Profiling · ai-analyst-lab
Deep-profile the active dataset: distributions, temporal patterns, correlations, completeness gaps, anomalies. Use after connecting a new dataset. Trigger on "profile this data", "deep-profile the dataset", "run a data profile", "check distributions", "find anomalies in the data", "how complete is this data". For a first-contact overview use data-map; for one column use distribution-profiler; for schema use data-inspect.

0 installs
▌
Log Correction · ai-analyst-lab
Record analyst mistakes, fixes, and reusable learnings so future analyses never repeat an error. Fires automatically when the user corrects work ("actually it's Y", "that's wrong") or teaches a rule ("always use X", "never include test users", "remember that our fiscal year starts in February"), and manually on "log a correction", "save this mistake", "record this lesson". Writes the .knowledge store per docs/KNOWLEDGE.md.

0 installs
▌
Score Analysis · ai-analyst-lab
Decide whether the evidence for one analysis supports acting, investigating, abstaining, or marking the review incomplete. Use after reliability, provenance, query, or triangulation checks.

0 installs
▌
Switch Dataset · ai-analyst-lab
Change the active dataset to switch between different data sources for analysis. Use this skill whenever the user wants to analyze a different dataset, switch to another database, change data sources, work with different tables, or explicitly invokes /switch-dataset. This skill handles the full switch workflow: validating the target dataset exists, checking for in-progress work that might be lost, updating the active pointer, and confirming the switch with a summary of the new dataset. Apply when users say things like "switch to sales data", "use the other dataset", "change to production database", "work with the marketing tables instead", "let's look at last month's data instead", "/switch-dataset analytics", or any request to change which dataset is currently being analyzed. Also trigger when starting a new analysis if the user mentions a dataset name that differs from the currently active one.

0 installs
▌
Trace Analysis · ai-analyst-lab
Trace an analytical claim to its receipt, source, query, result, and run evidence. Use when the user asks where a number came from, wants to verify a query, or needs to inspect provenance.

0 installs
▌
Analysis Design · ai-analyst-lab
Takes a vague analytical hunch, stakeholder request, or business question and produces a rigorous, stakeholder-ready analysis plan through a multi-stage pipeline. Use this skill whenever someone says "I think X caused Y", "help me investigate...", "design an analysis for...", "can you look into why...", "we need to figure out what's driving...", or presents any analytical question that needs methodological rigor before execution. This skill is essential when a PM has a hunch but no plan, when an analysis needs redesign after stakeholder feedback, or before starting any major investigation to prevent wasted work. The skill orchestrates hypothesis sharpening → confound scanning → investigation planning → V1 execution → feedback synthesis → V2 redesign. Apply this whenever the user is moving from vague intuition to structured investigation, when they're about to dive into data without a clear plan, when they need to validate an analytical approach before running queries, or when they're iterating on findings aft

0 installs
▌
Export · ai-analyst-lab
Export analysis results in different formats for different audiences — email summaries, Slack updates, decision briefs, Google Docs with embedded charts, Word documents, slide decks, or raw data CSVs. Use this skill whenever someone says `/export`, "export this as...", "send this to...", "share this analysis", "create a Google Doc", "make a Word document", "I need this as a deck", "export the data", "write an email summary", "draft a Slack update", "create a brief", or mentions needing analysis outputs in a specific format for stakeholders. Also trigger after completing an analysis when the user wants to share results, when they mention audience needs (VP, team channel, product team), or when they want multiple output formats at once. This skill handles the full export workflow — finding source material, generating the requested format with proper structure, managing Google Workspace auth and uploads, version tracking for re-exports, and fallback handling when external services fail.

0 installs
▌
Explore · ai-analyst-lab
Quick, interactive data exploration without the full pipeline. Use this skill whenever a user wants to explore data, understand what's in a dataset, browse tables or columns, check data distributions, spot patterns, or get familiar with data before analysis. Trigger on phrases like "/explore", "let me explore the data", "what's in this dataset?", "show me what data we have", "browse the data", "what tables are available?", "what columns does X have?", "show me a sample of the data", "what does the distribution look like?", "explore this table", or any request to understand data structure, contents, or patterns before diving into formal analysis. This is especially important after connecting a new dataset or when the user wants to poke around without committing to a specific analytical question yet. DISAMBIGUATION: this is interactive poke-around within an already-known dataset. For a first-contact dataset-wide overview ("let me poke around"), use `data-map`; for a plain schema/structure listing, use `/data` (

0 installs
▌
History · ai-analyst-lab
Browse and search past analyses from the knowledge system's analysis archive. Use this skill whenever the user invokes `/history` or variants like `/history search=X`, `/history {id}`, `/history --all`, `/history dataset=X`, or asks questions about their analytical work history such as "what have I analyzed before?", "what analyses have I run?", "show me past work", "show my history", "what have we looked at?", "what questions have I answered?", "can I see my analysis history?", "list my analyses", "what did I work on last week?", "have I analyzed X before?", "find analyses about Y", or mentions reviewing prior analyses, checking if similar work was already done, needing context on previous findings, or wants to build on past work. This skill also applies automatically at session start when you need context on the user's analytical history to inform current work. When displaying history, ALWAYS filter to the active dataset unless the user explicitly requests --all or dataset={id}.

0 installs
▌
Metrics · ai-analyst-lab
Browse, search, and display metric definitions from the active dataset's metric dictionary. This skill provides quick access to how metrics are defined, computed, and validated. Use this skill whenever the user wants to see metric definitions, understand how a metric is calculated, check what metrics are available, or verify a metric's specification before using it in analysis. Trigger on phrases like "/metrics", "show me the metrics", "what metrics do we track?", "how is [metric name] calculated?", "what's the definition of [metric]?", "list all metrics", "show me revenue metrics", "what metrics are in this dataset?", "define conversion rate", "how do we measure retention?", "what's in the metric dictionary?", "search for engagement metrics", "show me all KPIs", or any question about metric definitions, specifications, or formulas. Also use this skill during analysis when you need to confirm a metric's exact definition before computing it, or when the user references a metric name and you need to verify its

0 installs
▌
Business · ai-analyst-lab
Browse, search, and explore your organization's business context system — glossary terms, product catalog, metric definitions, OKRs/objectives, and team structure. This skill provides interactive access to all business knowledge stored in `.knowledge/organizations/`. Use this skill whenever the user wants to understand business terminology, look up metric definitions, explore what products exist, review company objectives, understand team structure, search for business terms, or generally wants to know "what business context do we have?" Trigger on phrases like "/business", "show me our glossary", "what metrics are defined?", "what products do we have?", "show me our OKRs", "who's on which team?", "look up [business term]", "search for [term] in our business knowledge", "what's the definition of [term]?", "show me our business context", "browse our company knowledge", "what teams do we have?", "find [term] in the knowledge base", or any request to view or search organizational knowledge. This skill is especia

0 installs
▌
Data Map · ai-analyst-lab
Produce a comprehensive cross-table data health map for the active dataset — the full payoff answer to open-ended "tell me about this data" questions. Run all tables, not just one: table inventory with row counts, PK uniqueness, date range per table, date alignment across tables, column completeness, foreign-key join-rate matrix, relationship diagram, and a thread-to-pull opening hypothesis. Use this skill whenever the user asks a **dataset-wide open question** — "tell me about this data", "tell me about the data", "tell me about this dataset", "what's in here", "what's in this data", "give me an overview", "give me the map", "map out the data", "what do I have", "what does this data look like", "show me what we've got", or any broad first-contact question about the active dataset as a whole (not scoped to one table). This skill is the curriculum payoff moment — students who just connected data get cross-table health, relationship mapping, and date alignment on the first broad question, not a schema dump and

0 installs
▌
Datasets · ai-analyst-lab
List all connected datasets with their status, table counts, and last analysis date. Use this skill whenever the user invokes `/datasets`, or asks questions like "what datasets do I have?", "show me my data sources", "list datasets", "which datasets are connected?", "what data is available?", "show all datasets", "what datasets can I analyze?", "view my datasets", "what data sources are set up?", or any request to see what datasets exist in the system. Also trigger when users mention "switch dataset", "change dataset", "use a different dataset", or "what's my active dataset?" since seeing the list helps them choose. This is a foundational command that should be offered proactively whenever users seem unsure about what data they're working with or when they need to understand what datasets are available before starting analysis.

0 installs
▌
Forecast · ai-analyst-lab
Generate time-series forecasts and projections for metrics over future time periods. Use this skill whenever the user asks about future values, predictions, or projections — phrases like "what will X look like next month?", "forecast DAU for Q2", "project revenue", "estimate future growth", "what should we expect?", "predict next quarter", "where are we headed?", "extrapolate this trend", or explicitly invokes "/forecast". This skill is essential after trend analysis when you need to quantify what comes next, when sizing opportunities that depend on future state, when planning capacity or resources based on anticipated volumes, or whenever turning historical patterns into forward-looking estimates. Always trigger this when users mention forecasting, predicting, projecting, estimating future values, or ask "what will happen if this continues?" — even if they don't explicitly say "forecast". The skill handles seasonality detection, model selection, confidence intervals, and validation against naive baselines to

0 installs
▌
Patterns · ai-analyst-lab
Browse, search, and leverage recurring analytical patterns discovered across past analyses. Use this skill when users want to see what patterns have emerged from previous work, check if a current finding matches a known pattern, search for patterns by keyword or metric, view pattern details, understand established behavioral patterns in their data, or get reminded of recurring observations at session start. This skill is especially valuable when users say things like "what patterns have we seen?", "have we seen this behavior before?", "show me recurring patterns", "what's consistent in our data?", "any known patterns about [metric/segment]?", "search patterns for [keyword]", or during exploratory analysis when you want to contextualize new findings against historical observations. The skill manages pattern extraction automatically after each analysis archive, incrementing occurrence counts when findings match existing patterns and creating new pattern entries when the same behavior appears across multiple ana

0 installs
▌
Srm Check · ai-analyst-lab
Automatically detect Sample Ratio Mismatch (SRM) in experiment or A/B test data before any analysis proceeds. SRM is a critical randomization integrity check — if the treatment/control split deviates significantly from the expected ratio, the experiment is compromised and results cannot be trusted. This skill acts as a safety gate that blocks analysis when randomization is broken. Use this skill whenever you detect experiment or A/B test data — look for columns like "variant", "group", "treatment", "control", "arm", "experiment_group", "test_group", "bucket", "condition", or any column with binary/small-cardinality values that suggest treatment assignment. Auto-fire on experiment data detection without waiting to be asked. Apply this skill when loading any experiment dataset, before calculating treatment effects, when starting any experiment analysis workflow, when users mention "A/B test", "experiment", "treatment vs control", "randomization", "test group", or when you see data that looks like it came from a

0 installs
▌
Experiment · ai-analyst-lab
The analysis and lifecycle owner for experiments. Full experiment lifecycle: design, power analysis, statistical analysis, interpretation, reporting, and monitoring of A/B tests. Invoke as /experiment. Trigger on "A/B test", "experiment", "treatment vs control", "sample size", "MDE", "statistical significance", "ship decision", "test readout", "is this result significant?". Runs the SRM gate first.

0 installs
▌
Guardrails · ai-analyst-lab
Ensure every success metric is paired with guardrail metrics and check for trade-offs before presenting improvements as wins. Guardrails protect against winning the metric game while losing the business game. Apply this skill whenever you define a metric, create a metric spec, document a KPI, report positive findings, present an improvement, analyze metric changes, investigate metric lifts, share good news about metrics, celebrate wins, or present results showing any metric increased. This skill is CRITICAL for preventing false wins where one metric improves at the expense of another (e.g., conversion rate up but average order value down, signup rate up but activation down, resolution time down but customer satisfaction down). Use this skill automatically when you see phrases like "X improved", "X is up", "X increased", "better performance on X", "we're seeing gains in X", or any analysis showing positive metric movement. Also apply when defining metrics alongside the metric-spec skill to ensure guardrails ar

0 installs
▌
Archaeology · ai-analyst-lab
Retrieve proven SQL patterns, table cheatsheets, and join patterns from .knowledge/query-archaeology/ so past work gets reused. Fire as a pre-flight step before writing ANY SQL. Also trigger on "do we have a known query for X", "how do we usually join these tables", "have we computed this metric before". If the store is empty or missing, exit silently. Also owns the writer convention: after a validated analysis, curate the final SQL here.

0 installs
▌
Metric Spec · ai-analyst-lab
Define any metric completely with a standardized template: calculation, denominator, time window, filters, interpretation. Trigger on "define this metric", "how should we measure X?", "what's the right way to calculate Y?", "document our metrics", "create a metric definition", "different teams are measuring this differently", or when a metric is used in analysis without a clear specification.

0 installs
▌
Reliability · ai-analyst-lab
Run one analytics task through several fresh trials to measure what repeats and what varies. Use for reliability, repeatability, variance, or repeated-run requests. This measures stability, not correctness.

0 installs
▌
Setup Slack · ai-analyst-lab
Connect a user's own AI Analyst Lab Slack identity through browser OAuth, store the personal user token locally, verify the workspace and target channel, and prepare one previewed Web API post. Use when the user asks to connect Slack, set up Slack, post to show-and-tell, or diagnose Slack.

0 installs
▌
Stress Test · ai-analyst-lab
Pressure-test any analysis plan or investigation design for methodological flaws before execution — wrong baselines, survivorship bias, missing segments, uncontrolled confounds, absent kill criteria. Use on `/stress-test`, "review / gut-check / stress test my analysis plan", or before committing significant time to a plan from any source. Produces a 7-point PASS/WARNING/FAIL diagnostic with an A-F grade.

0 installs
▌
Analyst Core · ai-analyst-lab
Operating rules for every data analysis. Apply for ANY data-analysis intent: "analyze", "investigate", "why did X change", "compare", "report on", "dashboard", "metrics", "funnel", "retention", "revenue", "conversion", "trend", "segment", "forecast", "how are we doing", "dig into", "break down", or any question about data, a metric, a CSV, or a table. Sets the method and routes to the other skills; load before any analytical question.

0 installs
▌
Codex Review · ai-analyst-lab
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", "second opinion from codex", "have the other model check this", "independently verify this analysis", "does codex agree", "cross-check this with gpt/codex", or wants a different model to confirm a result before acting on it. This is multi-model validation: a real independent re-analysis, not a critique of Claude's work. If the Codex plugin or CLI isn't installed, this skill detects that and walks the user through setup first.

0 installs
▌
Connect Data · ai-analyst-lab
Guided wizard to connect a new dataset to the AI Analyst system. Use this skill whenever the user wants to add a new data source, connect a database, set up data access, or configure a new dataset for analysis. This skill handles the full connection workflow: choosing connection type (CSV, DuckDB, PostgreSQL, Snowflake, BigQuery, Databricks, Redshift, SQL Server, MySQL), collecting credentials, validating connectivity, profiling schema, and setting up the knowledge brain. Trigger this skill when users say things like "/connect-data", "connect my database", "add a new dataset", "set up my data", "I have a database I want to analyze", "can you connect to my Postgres/BigQuery/Snowflake", "I need to add CSV files", "how do I get my data into this system", or "connect to my warehouse". Also trigger after first-run welcome when users need to set up their first dataset, or after /switch-dataset when the target dataset doesn't exist yet. This is the primary entry point for all new data connections — always offer this

0 installs
▌
Data Inspect · ai-analyst-lab
Show the active dataset's schema — tables, columns, row counts, and relationships. Optionally drill into a specific table. Use this skill whenever the user invokes `/data` or `/data {table}`, or asks questions like "what tables do I have?", "show me the schema", "what's in this dataset?", "what columns are in the users table?", "show me table structure", "list tables", "describe the data", "what's in my database?", or any request to inspect, browse, or understand the structure of the active dataset. Also trigger when users mention "schema", "columns", "tables", "data dictionary", "data structure", or when they need to understand what data they're working with before starting an analysis. This is a foundational command that should be offered proactively when users seem unsure about available data or table structure. DISAMBIGUATION: this is the `/data` SCHEMA inspector (structure — tables, columns, types, row counts). For a dataset-wide health + relationships overview ("tell me about this data"), use `data-map`

0 installs
▌
Run Pipeline · ai-analyst-lab bundle
Plan and run coordinated analysis using explicit input bindings, isolated workers, run-local artifacts, and the Python workflow controller.

0 installs
▌
Setup Notion · ai-analyst-lab
Connect Claude Code to Notion's official hosted MCP, complete OAuth, verify the intended workspace with a read, and stop before any write. Use when the user asks to connect Notion, set up Notion, export to Notion, or diagnose an unavailable Notion connection.

0 installs
▌
Context Trace · ai-analyst-lab
Show which context the AI analyst would receive for a question, why each item was selected, how it is delivered, and which conflicts, stale items, or omissions need attention. Use when the user asks what context was loaded, why a definition did or did not reach an analysis, what the analyst knows about a question, or invokes /context-trace.

0 installs
▌
Eval · ai-analyst-lab
Evaluate a named AI Analyst configuration across a frozen suite. Use when the user asks to run an eval suite, compare a change, inspect system accuracy, or run working or heldout capability and regression cases.

0 installs
▌
Pace · ai-analyst-lab
Change how visibly Claude surfaces analytical work during L3+ analyses. Three modes — guided (announce each phase and pause for /continue), narrated (announce each phase and run end-to-end), autopilot (silent end-to-end, final output only). Use this skill whenever the user invokes `/pace`, `/pace guided`, `/pace narrated`, `/pace autopilot`, or says things like "slow down and walk me through", "pause between steps", "just run it silently", "narrate each step", "don't stop to ask me", "stop narrating". Pace is orthogonal to complexity level — it changes surfacing, not which agents run. Full spec and phase-banner format live in the question-router skill. This skill is the write-side: it persists the user's explicit pace choice to `working/session_state.yaml` so it survives across phases, across `/resume-pipeline`, and across sessions.

0 installs
▌
Runs · ai-analyst-lab
Browse, inspect, compare, and clean up past pipeline runs. This skill is your window into analysis history — every `/run-pipeline` execution creates a tracked run with its own working directory, outputs, and state. Use this skill whenever the user wants to see what analyses have been executed, review past work, compare different approaches to the same problem, or clean up old runs. Trigger on phrases like "/runs", "show me my past analyses", "what pipeline runs do I have?", "list my pipeline runs", "show run history", "what did we analyze last week?", "compare these two analyses", "clean up old runs", "show me the latest run", "what was that analysis we did on [dataset]?", "review past work", "show me completed analyses", or any mention of viewing, listing, comparing, or managing previous pipeline executions. Also trigger when users reference a specific analysis by date or dataset name and want to see its details. This skill provides critical context for iterative analytical work — users often need to revisit

0 installs
▌
Setup · ai-analyst-lab
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. Use this skill whenever the user wants to set up the AI Analyst, configure their environment, get started with the tool, onboard themselves, connect their data for the first time, initialize their profile, or set up the system. Also trigger when users say things like "let's get started", "I'm new here", "configure the analyst", "set up my environment", "onboard me", "connect my data", "initialize", "first time setup", "get this working", "how do I begin", or invoke `/setup`. This skill handles both fresh setup (no existing profile) and resuming partial setup (picking up where they left off). It's especially important to use this skill when you detect the user has no `.knowledge/user/profile.md` or when they explicitly want to reconfigure their settings.

0 installs
▌
Trace · ai-analyst-lab
Show the provenance trace, linking every reported number to the SQL that produced it with a confidence badge. Use after an analysis when someone asks "where did that number come from?"

0 installs
▌
Causal · ai-analyst-lab
Causal inference toolkit for when experiments are not possible: estimate treatment effects from observational data with assumption checks and mandatory caveats. Invoke as /causal. Trigger on "causal", "caused", "impact of", "effect of", "attribution", "counterfactual", "difference-in-differences", "DiD", "propensity matching", "pre-post". If randomization IS possible, route to /experiment design instead.

0 installs

64 published skills