AI Agent Workflow Collection

Use this skill after data discovery and before any headline query is written. Required whenever you're about to compute a number that will inform a decision — segmentation choices, time windows, comparison structure, validation queries, and confounds must be named in writing first. Trigger on phrases like "let's compute", "the analysis is", "I'll segment by", or any move from question to query. The plan exists because most analytical bugs are choice-bugs (wrong segmentation, wrong window, wrong baseline) rather than syntax bugs, and choices made silently are choices that can't be audited.

Use this skill after multiverse and sensitivity analysis are complete, before producing any writeup or summary. Final pass against known analytical pitfalls — Simpson's paradox, base-rate fallacy, leakage, p-hacking, ecological fallacy, survivorship bias, falsification. The "what would change my mind" statement from framing-the-question is now compared against the actual results. Required before any analytical output is presented as a finding. Trigger before any conclusion, writeup, dashboard, or summary is delivered.

Use this skill after the headline query has run and reconciled, before drawing any conclusion. Run an explicit checklist of plausible confounders — selection effects, calendar effects, concurrent campaigns, ETL changes, holidays, weather, competing interventions, regulatory changes, market shifts. The confound list seeded in analytical-planning gets walked through one by one; new confounds that emerge during analysis get added. Required for medium and high-stakes analyses. Trigger on any move from "got the number" to "the number means X" — that move is what this skill gates.

Use this skill after the question is framed and BEFORE any analytical planning or querying. Required whenever you're about to write SQL, build a metric, or trust data you haven't personally inspected for this analysis. Discover and document schema, grain, freshness, provenance, and known data hygiene issues for every table the analysis will touch. Trigger on phrases like "let me query", "I'll pull from", or any move toward data access — even when working with a database you've used before, because schemas drift, ETL jobs change, and the table you used last quarter may not be the right one today.

Use this skill during writeup, summary, or any time numbers leave the analytical workspace and enter a document, email, slide, dashboard, or chat message. Every number must trace to a re-runnable artifact — a saved query, a logged prediction, a reconciled source. No narrated stats. No LLM-generated approximations. No "around 14%" without the artifact behind it. Trigger any time you're about to produce text that contains a numerical claim about data.

Use this skill at the start of EVERY rigorous analytical request — when the user has asked for a metric, comparison, lift estimate, segmentation, dashboard, report, A/B read, attribution claim, or any number-producing analysis AND has not explicitly opted into ad-hoc mode. This skill REFUSES to proceed to data discovery or querying until the question is operationalized (specific, measurable), the decision the answer informs is named, "what would change my mind" is written down, and stakes are flagged. The question doc is logged to the methodology DB. Trigger on phrases like "how is X doing", "is Y working", "compare A and B", "what's the impact of", "did we hit", "is there a difference", "show me", or any analytical framing — even casual ones. Most analytical requests arrive vague; this skill makes them sharp before any data is touched.

Use this skill after confound-audit and before any conclusion is drawn from the analysis. Required for medium and high-stakes analyses; recommended always. Addresses the garden-of-forking-paths problem — every analytical choice (segmentation, outlier rule, time window, transformation, model) could have plausibly gone differently, and a result that holds on only one path is fragile. Logs every choice with rationale and alternatives considered, runs alternative paths where feasible, and flags fragile results that don't hold up across the multiverse. Trigger any time conclusions are being drawn from a single analytical path.

KEYSTONE skill for the analytics-skills methodology. MUST trigger EVERY TIME a headline analytical query is about to be run — that is, the query whose result will appear in the writeup or inform the decision. This skill REFUSES to run the headline query until a written prediction (point estimate, range, reasoning, confidence, surprise condition) has been logged to the methodology DB via the CLI. After the query runs, this skill compares predicted vs. actual; if actual is OUTOFRANGE, it forces a stop-and-investigate before the result is trusted. Catches the LLM-native failure mode of hallucinated-but-plausible numbers, calibrates analyst priors over time, and creates an auditable record. Trigger any time SQL is about to be written, a headline metric is about to be computed, or "let's run the numbers" is in scope.

Use when the analytical metric has an authoritative version that exists outside the query — general ledger totals, audited reports, regulatory filings, vendor reports, previously-trusted dashboards, or any source-of-truth at any grain. Required for high-stakes analyses; recommended for medium-stakes whenever an authoritative version is plausibly available. The new query must tie out to the authoritative source at some grain (day, month, by-segment) before the result is trusted. Trigger on metrics involving revenue, headcount, billed amounts, refunds, regulatory totals, or any number that has been counted by something other than your query.

Use this skill after multiverse-analysis and before self-review. Identifies which parameters and assumptions, if changed within plausible ranges, would move the answer enough to change the decision. Differs from multiverse — multiverse varies analytical paths; sensitivity varies parameters within a fixed path. Trigger when results are about to be summarized for decision-making, especially when assumptions are non-obvious (discount rates, lookback windows, attribution windows, threshold cutoffs, smoothing parameters).

Use when authoring a new skill for the analytics-skills framework, modifying an existing one, or adding domain-specific extensions (vertical packs like e-commerce-analytics, healthcare-analytics, or fintech-analytics). Provides conventions for SKILL.md authoring, integration with the methodology DB, handoff patterns between skills, and the principle of one-skill-one-gate. Trigger on phrases like "add a skill", "extend the framework", "write a new skill", "improve the [skill-name] skill", or any meta-work on the framework itself.