d5sd5s
Data & analytics playbook

Validate the evidence before a decision depends on it.

Check lineage, methods, calculations, bias, visualizations, and whether the stated conclusion actually follows from the available evidence.

Data Validation
Reviewed · high risk

What this playbook provides

This skill gives analytical workflows a repeatable quality gate. The agent records source lineage, tests the calculation and methodology, surfaces missing evidence, and clearly separates supported conclusions from unresolved assumptions before a report reaches an accountable reviewer.

  • A lineage and methodology check
  • Recalculated figures and explicit assumptions
  • A clear supported-versus-uncertain conclusion

Example compositions using this skill

Where useful, a skill adds reusable method to a composition built primarily from connectors, agent instructions, a deliverable, and an approval boundary.

Uses Sentry, Cloudflare Developer Platform, Slack, NotionDaily at 07:00

Morning operations brief

Review overnight incidents, group recurring signals, check the approved runbook, and deliver a source-linked morning handover.

See the workflow
Uses Airtable, Google Drive, Outlook, SlackEvery Friday

Vendor SLA review

Collect service evidence, compare it with documented commitments, and prepare a review packet that clearly separates facts from assumptions.

See the workflow
Uses Sentry, GitHub, Linear, Cloudflare Developer PlatformWhen a qualifying alert fires

Incident triage

Trace a production error, identify the likely change, and prepare a triage issue without giving the agent authority to modify production.

See the workflow
Uses Stripe, Google Drive, Airtable, SlackAt each month-end

Month-end close review

Reconcile payout activity against the approved close records, explain mismatches, and prepare a review packet for qualified sign-off.

See the workflow
Uses Google Drive, Airtable, Outlook, SlackWeekly and when an approved agreement is added

Contract obligation tracker

Extract documented dates and obligations, reconcile them with the approved tracker, and flag ambiguity or missing ownership for legal review.

See the workflow
Uses Slack, PostHog, Mixpanel, AirtableEvery Thursday

Customer feedback brief

Group recurring customer feedback, compare it with product behavior, and prepare a source-linked brief without overstating anecdotal evidence.

See the workflow
Uses PostHog, Mixpanel, Ahrefs, CanvaEvery Monday

Campaign performance brief

Reconcile campaign and journey data, identify supported drivers, and draft a performance brief with explicit caveats and next actions.

See the workflow
Uses GitHub, Sentry, LinearWeekly

Dependency risk review

Read declared dependencies and recent runtime errors, identify the ones that are stale or already failing, and prepare a prioritized upgrade list.

See the workflow
Uses GitHub, Slack, NotionMonthly

Access review

Read current access across approved systems, compare it against the recorded roster, and prepare a review list of accounts that no longer match.

See the workflow
Uses Notion, GitHub, SlackWeekly

Runbook drift check

Compare approved runbooks against the systems they describe, flag steps that reference something that has since changed, and prepare a correction list.

See the workflow

Apply the data validation playbook to recurring work.

Each one arrives with a persona, standing instructions, a wake-up schedule, and its connectors chosen. Nothing runs until you add it.

Browse the agents