A reviewing discipline for agents — read the diff twice, test the edge cases, comment on intent, never nitpick formatting a linter owns.

Explains what a query actually does — joins, filters, gotchas — in plain language, then flags the index it wishes existed.

Reads a GA4 export and finds where the checkout funnel leaks — drop-off by step, device and source — with the one fix to try first.

Scores every Jira ticket for clarity, scope and effort before it hits the sprint. Flags vague acceptance criteria and suggests a rewrite.

Drafts blameless postmortems from a timeline and a channel export — impact, contributing factors, and actions with owners.

Sorts raw playtest notes into balance, UX, bugs and feel — ranked by how many testers hit it, with repro steps pulled from context.

Distills interview transcripts into claims with evidence — what was said, how often, and what it contradicts in your assumptions.

Holds any draft against your voice guide — banned words, sentence rhythm, claims policy — and returns a marked-up pass, not a rewrite.

Writes first-touch e-mails that sound like a person — one observation, one sentence of value, one soft ask. Kills every buzzword on sight.

Reads yesterday's commits, tickets and threads, and writes each person's standup draft — blockers first, no ceremony.

Audits Google Search Console data — pages losing clicks, queries with impressions but no CTR, and product pages cannibalizing each other.

Rewrites a commit message from the diff — imperative subject under 72 characters, a body that explains why, and a footer that links the issue.

Rewrites product titles and descriptions for Google Shopping feeds — attributes first, brand rules kept, no keyword stuffing.

Given kubectl output and alerts, ranks probable causes and proposes the next safe diagnostic step — read-only commands only, never a mutation without a human.

Turns a week of merged PRs into a changelog humans read — grouped by impact, written for users, breaking changes on top.

Reads stat tables and patch notes, then flags outliers — dominant strategies, dead perks, and curves that punish new players.

Builds content briefs from a keyword — search intent, outline, entities to cover, and the questions the top ten never answer.

How to write an emdly skill that passes review and actually works in an agent — structure, rules that bind, output contracts, and the mistakes reviewers bounce.

Drafts a three-mail abandoned-cart sequence from the cart contents and the store's voice — useful, specific, and honest about discounts.

Turns a vague metric request ("active users", "churn") into a precise definition with grain, window, filters and the SQL skeleton — before anyone builds the chart.

Reads a monthly P&L export and reports runway, burn trends and the three line items moving fastest — with the math shown.

Reads a lockfile diff or an outdated report and plans the upgrade — order, breaking changes to read, and the smallest safe steps.

Grades take-home submissions against a rubric you define, blind to names, and writes feedback the candidate can actually use.

Edits a landing page section by section — one promise above the fold, proof before features, and a CTA that says what happens next.