Skills your agents follow, step by step.
A skill is a SKILL.md: instructions for one kind of work. 71 ship with the app, and 10 open-source files are for developers. Read every one in full.
The copy is the install. A skill is text you can read and edit.
A connector grants access to a service. A skill teaches a method, so it needs no account and no key.
01 · From the library
Skills › Library › Add
Pick a shelf, add the skill, then give it to the agents that do that kind of work.
02 · Your own
Skills › Add a skill
Paste a SKILL.md or drop its folder. It is only text: no account and no key.
03 · In Claude Code
mkdir -p .claude/skills/<id>
Paste the file into that folder and start a new session. A skill works on every engine.
71 skills that ship with the app, on 19 shelves.
Each one opens in full on its own page. Add it in Lobstack from Skills › Library, or copy the SKILL.md from its page.
- OperationsFeatured
Weekly status report
Write the weekly update from what actually happened (merged work, moved tickets, tracked figures) in the same shape as last week.
SKILL.md · App - PersonalFeatured
Inbox triage
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.
SKILL.md · App - ResearchFeatured
Research brief
Answer a research question with a sourced brief: the answer first, then the evidence, how confident it is, and what could not be found.
SKILL.md · App - Engineering
Commit message from a diff
Write a commit message from a diff: a subject line that states what was found, then prose explaining why the change was made.
SKILL.md · App - Engineering
Triage a failing build
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.
SKILL.md · App - Engineering
Review what a linter cannot
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.
SKILL.md · App - Writing
Release notes from merged work
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.
SKILL.md · App - Personal
Meeting notes to action items
Turn a meeting transcript or rough notes into decisions, owned actions with dates, and open questions, and nothing else.
SKILL.md · App - Research
Competitor scan
Compare named competitors on what matters to a decision (price, audience, features, recent moves) from their own public pages.
SKILL.md · App - Engineering
Pull request description
Write a pull request description from the diff: why it exists, what changed, how it was tested, and where a reviewer should look first.
SKILL.md · App - Engineering
Incident postmortem
Write a blameless postmortem from an incident's alerts, logs and chat: timeline, impact, root cause, and actions with owners.
SKILL.md · App - Support
Customer reply
Draft a reply to a customer that answers what they actually asked, in their register, with the next step clear. Left unsent for review.
SKILL.md · App
Nothing matches. Try another word, or pick All.
10 open-source SKILL.md files for building on the API.
Official and MIT-licensed. They teach a coding agent to read a receipt, stay inside a budget and debug a refusal. How skills work.
- Cost
Read a Lobstack receipt
Read the receipt Lobstack returns on every model call — cost_usd, savings_usd, baseline_reason — and report cost from it instead of estimating.
SKILL.md · MIT - Migration
Migrate an SDK call to the Gateway
Move existing OpenAI or Anthropic SDK code onto the Lobstack Gateway by changing the base URL and the key, and verify it actually routed.
SKILL.md · MIT - Cost
Pick a model tier, not a flagship
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.
SKILL.md · MIT - Cost
Keep an agent inside a budget
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.
SKILL.md · MIT - Cost
Write a cost-aware system prompt
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.
SKILL.md · MIT - Observability
Audit a codebase for unmetered model calls
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.
SKILL.md · MIT - Migration
Put Cursor or Aider behind the Gateway
Route Cursor, Aider, Continue or any OpenAI-compatible tool through the Lobstack Gateway with a local proxy, and see a cost line per request.
SKILL.md · MIT - Gateway
Debug a Gateway 400, 402 or 429
Diagnose a Lobstack Gateway failure from its status and error class and decide whether retrying can possibly help.
SKILL.md · MIT - Observability
Report spend from the usage API
Answer what an organisation spent, on which models and keys, and what failed, from the Lobstack usage API rather than by estimating.
SKILL.md · MIT - Authoring
Author an Agent Skill
Write a SKILL.md an agent will actually load and follow — trigger-shaped description, valid frontmatter, progressive disclosure, no credentials.
SKILL.md · MIT
Nothing matches. Try another word, or pick All.
Questions, answered.
A folder with a SKILL.md in it: instructions for one kind of work, written as steps. Give it to an agent in that agent’s settings, and it follows those steps when the work comes up.
A connector grants access to a service, like GitHub or Slack, and needs your account there. A skill teaches a method, and is only text. One grants access; the other teaches.
No. Nothing in a skill calls the Lobstack API, so it works on every engine, including GitHub Copilot and your own key. The file is the whole thing.
Yes. In the app, open Skills › Add a skill and paste the file. The skills docs show the format, and the Author an Agent Skill file walks through it.
Yes. A SKILL.md is plain Markdown. Copy one into .claude/skills in Claude Code, or into any agent that reads skill files, and start a new session.
Skills your agents follow. Text you can read.
Free to start. $5 of credit, once, for 30 days after you verify. No card.