From auto-mobile
Runs package.json scripts via `bun run` from repo root, preferring existing ones like lint, build, test. Writes inspectable output to scratch/ as needed.
How this command is triggered — by the user, by Claude, or both
Slash command
/auto-mobile:SKILLbun-tasks/The summary Claude sees in its command listing — used to decide when to auto-load this command
# Bun Tasks Use `package.json` scripts through Bun instead of ad hoc root commands. - Check `package.json` first for an existing script. - Run repo tasks with `bun run <script>`. - Prefer existing scripts such as `lint`, `build`, `test`, `benchmark-context`, and `validate:yaml`. - When a Bun command emits output you need to inspect later, write it to `scratch/` and summarize the result. - Treat this as a helper for `validate`, `test`, `check-ci`, or `dead-code`, not as the main workflow when the user asks for a higher-level task.
Use package.json scripts through Bun instead of ad hoc root commands.
package.json first for an existing script.bun run <script>.lint, build, test, benchmark-context, and validate:yaml.scratch/ and summarize the result.validate, test, check-ci, or dead-code, not as the main workflow when the user asks for a higher-level task.npx claudepluginhub kaeawc/auto-mobile --plugin auto-mobile/scaffoldScaffolds bash scripts for git workflows, testing, linting, coverage, and CI from claude-commands repo into project root and scripts/ directory, then verifies setup.
/bun-upgradeGuides safe upgrade of Bun runtime and/or project dependencies via optional target (bun, deps, all). Outputs bash commands, breaking change checks, tests, builds, git backups, rollbacks, and audits.
/auditAudits tech stack and sets up one dev tooling bundle per run (formatting, linting, types, tests, observability, git hooks, database), installing/validating/remediating monorepo-aware.
/SKILLResolves GitHub issue via isolated worktree, TDD workflow, and auto-closing PR creation.
/SKILLCreates conventional git commit from conversation intent using git-agent and pushes to remote. Accepts optional Claude model name for co-author.
/SKILLSurfaces current session task from state file, evaluates clarity (prompts for clarification if needed), assesses completion, and verifies if fully done.