How do I install the Run Tasks skill?

Run npx skillmds@latest add zenobi-us/run-tasks 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 Run Tasks safe to use?

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

Which AI agents work with Run Tasks?

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 Run Tasks free to use?

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

Who published Run Tasks?

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

Run Tasks by zenobi-us — Agent Skill

Name: Run Tasks
Author: zenobi-us

File contents

Moonrepo Run Tasks

Overview

Use this skill for routine execution of moonrepo tasks by project and target, with selector-driven filtering and failure triage.

When to Use

Running one project target quickly.
Running affected subsets instead of whole repo.
Diagnosing common moon task execution failures.
Running tasks in CI

Core Command Patterns

Single project target
```
moon run app:build
moon run api:test
```

Multiple targets/projects

moon run :lint
moon run app:build api:test

Affected/scope workflows

moon run :test --affected
moon run :lint --projects app,api

Inspect before running

moon query projects
moon query tasks app

Running Commands in CI

when running tasks in CI, use ci instead of run.

moon ci :lint
moon ci app:build api:test

moon query projects
moon query tasks app

Triage Flow

Unknown target/project
- Run moon query projects and moon query tasks <project>.
Unexpected dependencies or task fan-out
- Re-run with explicit project/target pair.
- Inspect task config and inheritance in .moon/ + project configs.
Tool/runtime mismatch
- Confirm runtime versions via project toolchain manager before retry.
Cache confusion
- Capture run output first, then compare with clean run (--updateCache only when needed by your policy).

Caveats

Prefer selectors over broad moon run :target when repo is large.
Avoid “just run everything” in CI-like local checks; it hides dependency problems.
Always verify project and target names from query commands; don’t guess.

Quick Examples

# validate only one changed app
moon run app:test --affected

# lint two projects only
moon run :lint --projects app,dashboard

---name: run-tasksdescription: Runs moonrepo tasks with project/target selectors and troubleshooting flow, when daily execution needs predictable scoped runs, resulting in faster feedback and fewer ad hoc command mistakes.---# Moonrepo Run Tasks## OverviewUse this skill for routine execution of moonrepo tasks by project and target, with selector-driven filtering and failure triage.## When to Use- Running one project target quickly.- Running affected subsets instead of whole repo.- Diagnosing common moon task execution failures.- Running tasks in CI## Core Command Patterns1. **Single project target** ```bash moon run app:build moon run api:test ```2. **Multiple targets/projects** ```bash moon run :lint moon run app:build api:test ```3. **Affected/scope workflows** ```bash moon run :test --affected moon run :lint --projects app,api ```4. **Inspect before running** ```bash moon query projects moon query tasks app ```## Running Commands in CIwhen running tasks in CI, use `ci` instead of `run`.```bashmoon ci :lintmoon ci app:build api:testmoon query projectsmoon query tasks app```## Triage Flow1. **Unknown target/project** - Run `moon query projects` and `moon query tasks <project>`.2. **Unexpected dependencies or task fan-out** - Re-run with explicit project/target pair. - Inspect task config and inheritance in `.moon/` + project configs.3. **Tool/runtime mismatch** - Confirm runtime versions via project toolchain manager before retry.4. **Cache confusion** - Capture run output first, then compare with clean run (`--updateCache` only when needed by your policy).## Caveats- Prefer selectors over broad `moon run :target` when repo is large.- Avoid “just run everything” in CI-like local checks; it hides dependency problems.- Always verify project and target names from query commands; don’t guess.## Quick Examples```bash# validate only one changed appmoon run app:test --affected# lint two projects onlymoon run :lint --projects app,dashboard```

Frequently asked questions

Run Tasks