The skills leaderboard.

Write the weekly update from what actually happened (merged work, moved tickets, tracked figures) in the same shape as last week.

Sort a mailbox, channel or queue into what needs a person today, this week, or never, with a reason and a suggested action for each.

Answer a research question with a sourced brief: the answer first, then the evidence, how confident it is, and what could not be found.

Write a commit message from a diff: a subject line that states what was found, then prose explaining why the change was made.

Triage a red CI run: find the first real failure, attribute it to a change, and say whether the code is wrong or the runner was.

Review a change for what a linter cannot see: whether it is correct, what it breaks elsewhere, and which parallel list it forgot to update.

Write a pull request description from the diff: why it exists, what changed, how it was tested, and where a reviewer should look first.

Write a blameless postmortem from an incident's alerts, logs and chat: timeline, impact, root cause, and actions with owners.

Fix a bug by reproducing it first: turn the report into a failing test or script, shrink it, make the smallest fix, and show the test pass.

Split a spec, plan or thread into small tickets that each ship on their own, with order, dependencies and a check for done. Shown before anything is filed.

Review a change or repository for security holes (leaked secrets, injection, missing permission checks, unsafe input handling) with a real attack for each finding.

Find statements in the docs that the code now contradicts: quote the doc, show the code, and say which of the two is wrong.

Draw how a system fits together — components, data flow, a request's path, a data model — as a Mermaid diagram with a short note on what it shows.

Turn merged work, or a thread about it, into release notes written for the person installing the version rather than the person who built it.

Draft a blog post from a brief or notes: one argument, a concrete opening, a source for every claim, and a headline that says what the reader gets.

Write a one-page decision memo: the decision needed, the real options and their trade-offs, a recommendation, and what would change it.

Turn a request, thread or idea into a one-to-two page feature spec: the problem, who it is for, scope, non-goals, acceptance checks and open questions.

Read a long document (contract, report, policy, proposal) and hand back what it commits you to: money, dates, obligations and risks, each with a page reference.

Clean a messy spreadsheet or CSV (headers, types, duplicates, blanks, inconsistent values) into a tidy copy, with a log of every change.

Write an onboarding guide for someone new from the existing docs, repos and chat: day-one setup, who to ask, and a first real task.

Turn a task someone does by hand into a runbook: exact steps and commands, a check after each, what to do when one fails, and how to undo it.

Run a named checklist on a schedule, compare with the last run, and report only what changed or failed. Never fixes anything on its own.

Turn a meeting transcript or rough notes into decisions, owned actions with dates, and open questions, and nothing else.

Draft a reply to a customer that answers what they actually asked, in their register, with the next step clear. Left unsent for review.

Write down the state of a piece of work so another bot or person can pick it up cold: goal, done, in progress, decisions and why, next step, and traps.

Compare named competitors on what matters to a decision (price, audience, features, recent moves) from their own public pages.

Question a plan or design one point at a time, biggest risk first, until every open point is decided or deliberately parked, then hand back the decisions.

Fact-check a draft: pull out every checkable claim, check each against the source closest to it, and mark it confirmed, wrong (with the fix) or unverified.

Group customer feedback (tickets, reviews, survey answers, call notes) into themes, each with a count, a word-for-word quote and the decision it bears on.

Check named web pages against the last visit and report only real changes (price, wording, availability, broken parts), quoting before and after.

Answer a question from a database or table: read the schema, write a read-only query, sanity-check the result, and answer with the query shown.

Audit named pages for how well search engines and AI answers can find and understand them: titles, headings, meta, links, structured data and speed. Ranked fixes.

Turn one article, launch or update into a set of posts for each social platform, in the house voice, each with its own hook and link, left as drafts.

Draft a 3 to 5 email sequence (onboarding, nurture or win-back) with one goal, the timing, and a single ask per email. Drafts only; never sends.

Build a one-page brief on a company or contact from public sources: what they do, recent news, likely priorities, fit, and who to talk to. Every line sourced.

Draft a short first email to someone new from real research, with one specific reason for writing now and an easy way to say no. Draft only.

Summarise revenue for a period (new, expansion, churn, refunds, failed payments) against the last period, with a chart. Read-only.

Review a card or bank export: categorise every line, flag duplicates, new subscriptions and price rises, and total spend against last month.

List overdue invoices by age and amount, and draft a reminder for each customer in a tone that fits how late it is. Sends nothing and promises nothing.

Turn a dataset or export into a report: the working spreadsheet with formulas, and a short document with charts that says what the numbers mean.

Design a brand kit for a company or product — logo and wordmark, palette, type, voice, and the brand in use — as a multi-page design file.

Design a one-page overview — a product sheet, a company profile, an event or offer summary — that someone can read in a minute and print.

Design a poster or flyer for an event, launch, sale or announcement, readable from across a room, as print-ready PDF and PNG.

Design a set of social post images (square, story and link-preview sizes) that share one look, each with its caption drafted beside it.

Build a pitch or proposal deck — problem, solution, proof, plan, ask — as an editable PowerPoint file and a PDF, from real facts.

Read the receipt Lobstack returns on every model call — cost_usd, savings_usd, baseline_reason — and report cost from it instead of estimating.

Choose the cheapest model tier that can actually do the task instead of defaulting to a flagship, and verify the choice before spending on it.

Hold an agent, job or run inside a hard dollar budget using the per-call cost the Gateway returns, and handle the 402 when an allowance runs out.

Write or review a system prompt that does not quietly multiply the bill — bounded output, no re-sent bulk, tool schemas counted as the input tokens they are.

Diagnose a Lobstack Gateway failure from its status and error class and decide whether retrying can possibly help.

Move existing OpenAI or Anthropic SDK code onto the Lobstack Gateway by changing the base URL and the key, and verify it actually routed.

Route Cursor, Aider, Continue or any OpenAI-compatible tool through the Lobstack Gateway with a local proxy, and see a cost line per request.

Find model calls that bypass the gateway and therefore appear on no bill anyone reads, and detect the opposite fault of counting one call twice.

Answer what an organisation spent, on which models and keys, and what failed, from the Lobstack usage API rather than by estimating.

Write a SKILL.md an agent will actually load and follow — trigger-shaped description, valid frontmatter, progressive disclosure, no credentials.