# DigiNomads > Agent workflows for people who work from anywhere A free, dated reference for digital nomads who work with AI agents: copy-ready prompt templates by scenario, curated skill packs, plain-English harness comparisons, and an intake channel for agents. ## Pages - [AI agents for work that travels](/index.md): Copy-ready prompt templates by scenario, curated skill packs and plain-English harness comparisons for digital nomads and remote workers. Free, dated and written for people who work from anywhere. - [About this site, and what it refuses to write](/about.md): How the library is made: source rules, how AI is used, review dates, correction policy and why there are no rankings or affiliate links. - [Agent help desk](/agent-help.md): Send a question, a correction or a missing scenario. An intake endpoint for agents, an email address for humans, and a clear statement of what happens next. - [Changelog](/changelog.md): What changed in the library, when it changed, and which pages were reviewed. The short version of the site's memory. - [AI agent harnesses compared](/harnesses.md): Eight agent harnesses compared on surface, model access, local models, guardrails and portability — with vendor docs, no benchmark leaderboard. - [Harness glossary](/harnesses/glossary.md): The words that decide an agent setup: model, harness, agent, tool, skill, MCP, context window, sandbox, approval policy and headless mode. - [How to test a harness in 45 minutes](/harnesses/how-to-test-a-harness.md): A three-task bake-off with a scorecard for setup time, permission friction, diff quality, recovery and cost — run it on your own repository, not a benchmark. - [A portable agent setup](/harnesses/portable-agent-setup.md): Keep the instructions, skills, prompts and tool configuration in plain files so a harness change is a swap, not a rewrite. - [Terms, privacy and disclaimer](/legal.md): The terms for using the library, what data is and is not collected, and the limits of general information about AI agents and remote work. - [Life off the clock](/life.md): The small part of this site about the human side of working from anywhere: rhythm, reset and the habits that keep the work sustainable. - [The 20-minute reset between cities](/life/reset-between-cities.md): A short checklist for the day after arrival: money, files, body clock, local ritual and the one person you should message. - [A workweek that survives time zones](/life/rhythm-for-a-moving-workweek.md): Three anchors, one deep block and a shutdown that ends the day — a weekly shape for remote work when the office keeps moving. - [Prompt templates for the work that travels](/prompts.md): Eighteen copy-ready prompts for client work, sales, research, writing, admin, coding, agent operations and learning — each with inputs, an output contract and the checks before you trust it. - [Audit an agent workflow before you automate it](/prompts/audit-an-agent-workflow.md): Map a workflow step by step, separate what the agent can draft from what it can decide, and put human checkpoints where a wrong output is expensive and hard to detect. - [Build a travel admin checklist from a booking](/prompts/booking-admin-checklist.md): Extract every deadline, document, dependency and buffer from a booking confirmation, then assign an owner and a latest-start date. - [Build a city brief from official sources](/prompts/city-research-brief.md): Price a city from statistics offices, fee schedules and tax authorities, with a cost floor, a newcomer premium and a confidence column instead of a copied average. - [Design a fallback path for a flaky tool](/prompts/design-a-fallback-path.md): Classify how a dependency fails, decide what retries and what escalates, and write the runbook before the tool goes down at the wrong moment. - [Follow up after a proposal without chasing](/prompts/follow-up-after-proposal.md): Write a short follow-up that names the decision, offers a clear next step and leaves room for a no — without discounts, fake urgency or another attachment. - [Learn a tool by building a tiny artifact](/prompts/learn-a-tool-by-building.md): A five-session curriculum where each session ends in a small working thing, a test of understanding and one source to read — no tutorial collecting. - [Turn notes into a publishable article](/prompts/notes-to-article.md): Extract claims, separate fact from opinion, build an outline with evidence slots, then draft without inventing a source or a number. - [Qualify a lead before you write a proposal](/prompts/qualify-a-lead.md): Extract the problem, urgency, budget signal and decision process from a lead, then decide whether to pursue, nurture or decline before spending a day on a proposal. - [Turn receipts into a bookkeeping-ready log](/prompts/receipt-log.md): Normalise dates, merchants, currencies and tax notes into a CSV, with an explicit unknown column and a duplicate check instead of guessed data. - [Red-team a plan before you commit](/prompts/red-team-a-plan.md): List the assumptions, the failure modes and the cheapest test that would change your mind, then write the kill criteria before you start. - [Reproduce a bug before fixing it](/prompts/reproduce-a-bug.md): Make the agent write the failing test first, isolate the smallest cause and only then patch — with the command that proves it. - [Review a diff for operational risk](/prompts/review-a-diff.md): Review changed behaviour, failure modes, rollback, secrets and tests. Findings only, ordered by severity, with file and line references. - [Rewrite a draft for one named reader](/prompts/rewrite-for-a-reader.md): Cut the throat-clearing, keep the claim and the caveat, and produce a version a specific person can act on without a second read. - [Scope a client project from a messy call](/prompts/scope-a-project-from-a-call.md): Turn a rambling discovery call into a one-page scope: outcomes, deliverables, exclusions, assumptions, dependencies and open questions — before you quote. - [Turn a repeated prompt into a skill](/prompts/turn-a-prompt-into-a-skill.md): Convert the prompt you paste every week into an Agent Skills folder with a specific trigger, an output contract, a guardrail and two pass tests. - [Compare visa routes in a decision matrix](/prompts/visa-route-matrix.md): Turn marketing pages into a criteria matrix: what the permit grants, who may hold it, which income counts, what it costs and which questions need a professional. - [Write a weekly update that prevents scope creep](/prompts/weekly-client-update.md): A status update that separates done, next, blocked and decisions needed — and makes any change to the plan visible before it becomes unpaid work. - [Write the project brief your agent actually reads](/prompts/write-agents-md.md): Turn the commands, boundaries and review path of a repository into a short AGENTS.md that an agent can follow without a long preamble in every chat. - [Skill packs that keep the workflow, not the chat](/skills.md): Six small Agent Skills packs for research, client work, writing, development, agent operations and sales — each with triggers, output contracts, install steps and tests. - [Agent ops](/skills/agent-ops.md): Four skills for running agents on real work: a project brief, a workflow audit, a prompt-to-skill conversion and a fallback plan. - [Client room](/skills/client-room.md): Four skills that keep a client engagement legible: call-to-scope, weekly updates, decision logs and handoff packs. - [Dev loop](/skills/dev-loop.md): Four skills for agent-assisted development: reproduce, review the diff, write the release note and check the dependency. - [Research desk](/skills/research-desk.md): Four skills for source-checked research: a source ledger, a claim checker, a comparison matrix and a freshness scan. - [Sales room](/skills/sales-room.md): Four skills for independent consultants: qualify a lead, follow up on a proposal, keep an objection log and hand the deal to delivery without losing the context. - [Writing room](/skills/writing-room.md): Four skills for drafting in public: a reader brief, voice matching, a claim check and a repurposing kit. ## Delivery and payment - Everything on this site is free to read. There is no checkout, account, subscription or paid download. - Questions and corrections go through the agent help desk or hello@diginomads.win. ## Agent help - Submit a question or correction: `POST https://deliver.diginomads.win/api/requests` - Schema, status vocabulary and limits: `GET https://deliver.diginomads.win/requests.md` - Free, rate limited, no account. Do not send secrets or private customer data. ## Contact - hello@diginomads.win ## Optional - [Full site text](/llms-full.txt): every public page and product body in one file. - [Agent capabilities](/skill.md): capability table, boundaries and contact. - [Discovery metadata](/.well-known/ard.json): ARD entry for this site. - Markdown negotiation: send `Accept: text/markdown` to any page URL to receive its Markdown mirror.