How do I install the Jobber skill?

Run npx skillmds@latest add danielgwilson/jobber in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Jobber safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Jobber?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Jobber free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Jobber?

danielgwilson (@danielgwilson) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Jobber by danielgwilson — Agent Skill

Name: Jobber
Rating: 4.2 (5 reviews)
Author: danielgwilson

Jobber

Use this skill whenever you need to inspect or operate Jobber through the local jobber CLI. Covers auth checks, current user and account identity, discovered operation browsing, and raw GraphQL against Jobber's private web API.

danielgwilson 6f8a5b4 4 files · 4.4 KB Updated Sep 17, 2026

File contents

Jobber CLI Skill

Use this skill when you need to inspect or operate Jobber through the local jobber CLI.

Command

Important naming detail:

npm package name: jobber-cli
CLI binary name: jobber

Prefer an installed binary:

jobber --help

For one-off package use after publication:

npx -y jobber-cli --help

For a source checkout:

npm install
npm run build
node dist/cli.js --help

Do not guess alternate package names unless they are explicitly published later.

Safety Rules

This is an unofficial private-surface adapter and is fragile by definition.
Prefer read operations before mutations.
Prefer --json for machine-readable output.
Do not print, paste, store in repo, or commit Jobber cookie headers.
Keep raw browser captures, traces, cookies, storage state, and full upstream JSON exports out of the repo.
operations list is a discovered inventory, not a guarantee that every operation has a recovered query document.
Use graphql run to prototype unsupported workflows before adding typed commands.

First Checks

jobber auth status --json
jobber doctor --json
jobber whoami --json

If auth is missing, import from a live logged-in agent-browser session or attached browser on the same machine:

jobber auth import-agent-browser

Manual cookie-header auth is supported, but avoid putting cookie values in shell history, logs, or chat:

printf '%s' "$JOBBER_COOKIE_HEADER" | jobber auth set-cookie-header --stdin

Common Reads

jobber operations list --json
jobber operations list --search client --json
jobber operations inspect ClientDefaults --json
jobber graphql run --operation-name CurrentAccount --query 'query CurrentAccount { account { id name inTrial industry } }' --json
jobber graphql run --query-file ./query.graphql --variables-file ./vars.json --json

---name: jobberdescription: Use this skill whenever you need to inspect or operate Jobber through the local jobber CLI. Covers auth checks, current user and account identity, discovered operation browsing, and raw GraphQL against Jobber's private web API.---# Jobber CLI SkillUse this skill when you need to inspect or operate Jobber through the local`jobber` CLI.## CommandImportant naming detail:- npm package name: `jobber-cli`- CLI binary name: `jobber`Prefer an installed binary:```bashjobber --help```For one-off package use after publication:```bashnpx -y jobber-cli --help```For a source checkout:```bashnpm installnpm run buildnode dist/cli.js --help```Do not guess alternate package names unless they are explicitly published later.## Safety Rules- This is an unofficial private-surface adapter and is fragile by definition.- Prefer read operations before mutations.- Prefer `--json` for machine-readable output.- Do not print, paste, store in repo, or commit Jobber cookie headers.- Keep raw browser captures, traces, cookies, storage state, and full upstream JSON exports out of the repo.- `operations list` is a discovered inventory, not a guarantee that every operation has a recovered query document.- Use `graphql run` to prototype unsupported workflows before adding typed commands.## First Checks```bashjobber auth status --jsonjobber doctor --jsonjobber whoami --json```If auth is missing, import from a live logged-in `agent-browser` session orattached browser on the same machine:```bashjobber auth import-agent-browser```Manual cookie-header auth is supported, but avoid putting cookie values inshell history, logs, or chat:```bashprintf '%s' "$JOBBER_COOKIE_HEADER" | jobber auth set-cookie-header --stdin```## Common Reads```bashjobber operations list --jsonjobber operations list --search client --jsonjobber operations inspect ClientDefaults --jsonjobber graphql run --operation-name CurrentAccount --query 'query CurrentAccount { account { id name inTrial industry } }' --jsonjobber graphql run --query-file ./query.graphql --variables-file ./vars.json --json```

Frequently asked questions