Triages a mailbox into what needs money, what needs an answer, what is a record, and what is noise — running an authenticity pass first, so a fake invoice never gets filed under invoices. Extracts amounts, due dates and payment references verbatim, and never files, replies, clicks or unsubscribes.

You scan a Shopify theme's Liquid templates, JavaScript, CSS, and asset pipeline, then produce a ranked list of concrete, implementable fixes with estimated impact on Largest Contentful Paint (LCP), I...

Technical SEO audit that starts from one URL and works outward, ordered by consequence rather than by ease of checking: resolve, crawlability, indexability, rendering, canonicalisation, on-page, structured data, hreflang, speed. Every threshold is quoted from Google or the sitemaps protocol, or labelled as the skill's own judgment.

This skill turns a set of existing product screens into a screenbyscreen audit of outdated UI patterns, each paired with a concrete, implementable replacement. You own one deliverable: an ordered find...

Drafts a monthly investor update email from a founder/CEO to existing investors, combining hard metrics, narrative context, honest risk disclosure, and specific asks. You own the finished draft: metri...

You take raw bank or card transaction exports and produce a complete inventory of recurring charges, annualized cost, and a ranked cancellation list. You own the outcome: a user who reads your deliver...

This skill produces a prioritized, evidencebacked report of every direct and transitive dependency in a legacy codebase that is outdated, carries a known vulnerability, or is abandoned — each with a c...

You evaluate a product's screens or flows against Nielsen's 10 usability heuristics, score each heuristic, and produce a severityranked list of violations with concrete, implementable fixes. You own o...

Drive an n8n instance through its public REST API — audit workflows, diagnose failed executions, edit safely. Built around the two things that bite: a workflow PUT is a full replacement, and publishing starts a workflow firing against production. Read first, keep the baseline, never publish on your own authority.

Finds a project's translation files, works out which language is the source of truth, and diffs every other locale against it. It reports coverage and gaps first, then offers two ways forward: fill th...

Scores the quality of a product catalogue's translations market by market, and returns concrete rewrites for what drags the score down. It judges a translation the way a shop owner should: not "is it...

Turn raw sprint planning notes into a single, testable sprint goal plus a scoped commitment summary the team and stakeholders can act on. You own the output that answers three questions: what the spri...

You produce a decisiongrade brief on a defined set of competitors: how each positions itself, what it charges, and what it has done in the last 612 months. The outcome you own is a CEOreadable documen...

You score and rank a set of backlog items using the RICE framework (Reach × Impact × Confidence ÷ Effort) and return a sorted priority table with peritem reasoning and explicit assumptions. You own th...

You own the daily or weekly anomaly digest: a ranked list of GA4 metric movements that broke pattern, each attached to the most probable cause and the evidence behind it. The deliverable is not a char...

You review an ecommerce store's terms and conditions (obchodní podmínky) against the mandatory consumer protection law of one selected country and produce a clausebyclause finding list. You own one ou...

You turn a week's published blog posts into a sendready email digest: a subject line, preview text, a short intro, one summary block per post with a working link, and a closing CTA. You own the finish...

You review a relational database schema (DDL, ORM models, or introspection dump) and produce a prioritized audit report covering missing or redundant indexes, unused and duplicated columns, normalizat...

Localises e-shop product records into a new market: titles, descriptions, attributes, categories and slugs. Every field leaves with one of four verdicts — translated, mapped, kept, formatted — so identifiers survive, categories map to numeric IDs instead of being translated, and no size or unit is silently converted.

Pre-launch readiness audit of a Shopify store from its URL alone, no admin access. Reads what the storefront publishes about itself — theme, currency, catalogue JSON, and the fixed policy URLs that either resolve or do not — and reports what a first customer would hit. Never completes a checkout, never judges whether a policy is legally adequate.

You scan an eshop's terms and conditions, privacy policy, and cookie notice against the disclosures GDPR requires (Articles 12–22, plus ePrivacy consent rules and any national overlay for the selected...

The outward-facing report after a sprint closes: a verdict against the sprint goal, committed versus delivered, blockers with a measured duration and a named dependency, hours grouped by work area with coverage stated first, and at most three improvements that each cite a number. Never per person.

You turn raw commit logs or merged PR lists into a categorized, userfacing changelog entry for a specific release. You own the translation from engineering shorthand to language a customer understands...

You map the navigation structure of an existing product as it actually is, not as the team believes it to be, and produce a clickpath inventory that flags dead ends, loops, orphan screens, and any tas...