A stack is one job’s working setup: the servers and skills that do it, known to work together, priced and permissioned up front. Or assemble your own.
40 stacks · 142 distinct servers · 181 skills · all free · every figure derived from the listings
Tools to inspect code changes, run checks and prepare a pull request review.
Read a merge request and its diff on GitLab and leave the review as comments, rather than as a chat message somebody has to copy across.
Tools to investigate a bug report and work toward a reproducible test case.
Pull the error, its stack trace and its frequency out of Sentry, and say how many people it reached.
Tools to investigate alerts, check recent changes and follow the runbook.
Read the alert and the metric behind it in Datadog or Prometheus, and say what the series looked like before it fired.
Tools to prepare database changes and review their effects before rollout.
Open a Neon branch, run the migration there, and throw the branch away when the answer is no.
Designs the endpoint, wires the auth and the payment, and reviews the shape before it is public and permanent.
Review a REST design against security, resilience and operational rules while it is still a document.
Takes a green branch to a running deployment, and keeps the DNS, the cluster and the access list honest on the way.
Create and read deploys on Vercel or Netlify and say which commit is actually live.
Reviews the code, the identities and the exposure of one service, and writes down what it found rather than a score.
Scan an MCP server's own source for secrets, injection risk and misconfiguration before it is added to anything.
Drives the real interface, keeps the end-to-end suite current, and checks the things a screenshot does not show.
Walk a user flow in a real browser and report where it stops, with the screenshot and the console attached.
Finds the sources, keeps what it read, and answers with a citation that still opens next quarter.
Search the live web through Tavily and Perplexity, and keep a dated copy of the pages worth citing with the Crawl4AI skill.
Researches the keyword, writes the piece, publishes it, and audits what the page actually ships.
Research keywords and search intent through Semrush and Ahrefs before the brief is written rather than after.
Researches the account, writes the sequence, keeps the CRM current, and books the meeting without four tabs.
Read and update accounts, contacts and opportunities in Salesforce, and note what was said instead of remembering it.
Reads the ticket, finds whether it is a bug or a billing question, and drafts the reply in your own voice.
Search and update tickets and Help Center articles in Zendesk or Freshdesk, end to end.
Answers the funnel question with the query it ran, the caveat attached, and the readout already written.
Ask Metabase for an existing question rather than writing a new query that disagrees with it.
Gets the data out, trains or fine-tunes the model, and evaluates it before anybody calls it an improvement.
Load a CSV or an Excel file, profile the columns and say what is missing before any modelling starts.
Reads the Figma file, builds the component, and ships the page without redrawing the design in CSS by eye.
Read design context, tokens and variables out of Figma instead of measuring screenshots.
Turns the ticket, the thread and the source into a page somebody can follow, in the words your product already uses.
Read the Jira issue and the Confluence page behind a change and write the update from both.
Runs the shop's day: catalogue, prices, campaigns, and the tickets that follow them.
Read and update products, inventory and orders through the Shopify Admin GraphQL API.
Reconciles what the ledger says with what the payment processor did, and writes the invoice at the end of it.
Read the ledger in QuickBooks or Xero and the revenue in Stripe, and name the difference between them.
One place for the notes, the tasks, the calendar and the inbox, with a memory that survives the session.
Capture into Notion or Obsidian, and turn the capture into a Todoist task with a date rather than a note about a task.
Makes the video, the images and the audio, and understands the footage it already has.
Transcode and assemble video through an API rather than a local render queue.
Runs a React Native or Expo app on a simulator, reads what it is doing, and takes it through an SDK upgrade and a store release.
Run a flow on an iOS simulator or Android emulator through agent-device and keep the screenshots, instead of describing what the screen ought to do.
Inspects the cluster and its Helm releases, and writes the manifests, charts and policies that go through Git rather than around it.
Read pods, events and logs in the namespaces you allow and name the workload that keeps restarting, with the Kubernetes server started read-only.