Agent skill

Atmos Workflows

by cloudposse in cloudposse/atmos

Workflow automation: native step types, multi-step workflows, parallel/matrix/wait/container/emulator steps, when: conditions (CEL), require/assert preconditions, output steps, retries…

Apache-2.0Auto-check passedProductivity & Automation

Install Atmos Workflows

skills CLI
$ npx skills add cloudposse/atmos --skill atmos-workflows -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cloudposse/atmos atmos-workflows --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cloudposse/atmos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent-skills/skills/atmos-workflows .claude/skills/atmos-workflows && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
atmos-workflows
GitHub stars
1.4k
Token cost
~1.3k tokens
SKILL.md length
449 words
Files
2 (incl. references)
Skills in repo
70
Repo updated
First seen
Licence
Apache-2.0

At a glance

Workflow automation: native step types, multi-step workflows, parallel/matrix/wait/container/emulator steps, when: conditions (CEL), require/assert preconditions, output steps, retries…

  • Tasks that involve Workflow automation
  • SKILL.md covers Quick Shape, Discovery, Step Type Guidance and Conditions, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Atmos Workflows is an agent skill from cloudposse/atmos. Workflow automation: native step types, multi-step workflows, parallel/matrix/wait/container/emulator steps, when: conditions (CEL), require/assert preconditions, output steps, retries, dependencies, and cross-component orchestration

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/workflow-syntax.md`).

It sits in Productivity & Automation, covering Workflow automation. The repository describes itself as: Atmos is the open-source runtime for infrastructure — it builds, authenticates, and ships Terraform, OpenTofu, Packer, Ansible, Kubernetes, Helm, and containers the same way on… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Workflow automation

Example prompts

  • “/atmos-workflows”

What it can do on your machine

Read from SKILL.md and the folder at commit bbe58a6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml and bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Atmos Workflows loads about 1.3k tokens when it runs, and up to ~4.1k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 449 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cloudposse/atmos at commit bbe58a6, republished under its Apache-2.0 licence (© cloudposse). 449 words, ~1,319 tokens.

Download SKILL.mdSave it as .claude/skills/atmos-workflows/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
atmos-workflows
description
Workflow automation: native step types, multi-step workflows, parallel/matrix/wait/container/emulator steps, when: conditions (CEL), require/assert preconditions, output steps, retries, dependencies, and cross-component orchestration
metadata.copyright
Copyright Cloud Posse, LLC 2026
metadata.version
1.0.0
metadata.category
ci-automation
references
references/workflow-syntax.md

Atmos Workflows

Use this skill for reusable orchestration in workflows: files: multi-step deployment flows, parallel or matrix execution, cross-component operations, preconditions, retries, typed UI/output steps, container/emulator steps, and workflow-level dependencies.

When a task is primarily about shared step fields (type, working_directory, env, output, retry, script, workdir, or hook with: payloads), also load atmos-steps.

For full workflow syntax, read references/workflow-syntax.md.

Quick Shape

yaml
workflows:
  deploy-network:
    description: Deploy network components
    stack: plat-ue2-dev
    steps:
      - type: atmos
        command: terraform deploy vpc
      - type: atmos
        command: terraform deploy dns
shell
atmos workflow deploy-network
atmos workflow deploy-network --stack plat-ue2-prod

Discovery

Workflow files live under workflows.base_path in atmos.yaml.

yaml
workflows:
  base_path: stacks/workflows

When --file is omitted, Atmos scans workflow files and runs the workflow if exactly one match is found. Use --file for ambiguous workflow names.

Step Type Guidance

Use native step types when they express the intent directly:

NeedPrefer
Run Atmostype: atmos
Shell/process executionshell or exec
Concurrent executionparallel, matrix
Background services and waitsbackground: true, wait, wait-all
Preconditionsrequire / assert
Retry transient failuresretry
Containers and emulatorscontainer, emulator
HTTP callshttp
User-facing outputsay, toast, markdown, table, pager, format, spin, stage
Workflow recordingscast, simulate via atmos-cast

Shell is appropriate for short glue, terminal-native tools, or checked-in scripts. Large inline shell blocks with loops, sleeps, formatting, CI metadata, or hand-rolled parallelism should usually be replaced by native workflow steps.

Conditions

when uses built-in predicates or CEL expressions:

yaml
steps:
  - name: prod-only
    type: shell
    command: ./scripts/check-prod.sh
    when: !cel 'stack == "prod" && ci'

Built-in predicate keywords include ci, local, always, never, success, and failure. Use !cel when a condition should be evaluated as CEL rather than treated as a predicate keyword.

when: manual is not an Atmos workflow predicate. For approvals, use a plan/apply split and CI environment protection rules.

Preconditions

require and assert verify required tools, files, dirs, environment variables, commands, or HTTP resources before continuing. They do not install anything.

yaml
steps:
  - type: require
    tools:
      - terraform
    files:
      - atmos.yaml

Route tool installation to atmos-toolchain.

Show full SKILL.md (175 more words)Show less

Parallel and Matrix

Use parallel for independent steps:

yaml
steps:
  - type: parallel
    max_concurrency: 4
    fail:
      mode: wait_all
    steps:
      - type: atmos
        command: terraform plan vpc
      - type: atmos
        command: terraform plan dns

Use matrix when the workflow expands axes into repeated steps.

Dependencies

Declare workflow tool dependencies in the workflow or step context:

yaml
workflows:
  scan:
    dependencies:
      tools:
        checkov: "latest"
    steps:
      - type: shell
        command: checkov --directory .

Atmos toolchain installs and exposes declared tools for the workflow execution context.

Auth

Use identity on a workflow or step when a command needs Atmos Auth credentials:

yaml
steps:
  - type: shell
    identity: prod-readonly
    command: aws sts get-caller-identity

Route provider, identity, OIDC, assume role/root, and profile details to atmos-auth and atmos-profiles.

Routing

NeedSkill
Complete workflow schema and examplesreferences/workflow-syntax.md
Custom CLI commands under commandsatmos-custom-commands
Shared step fields and step typesatmos-steps
Smoke tests, integration tests, and test groupsatmos-tests
Cast/simulate workflow recordingsatmos-cast
Tool installation and PATH behavioratmos-toolchain
Auth identities and providersatmos-auth
Component dependencies and deployment orderatmos-components, atmos-terraform
CI approvals, matrices, outputsatmos-ci

Guardrails

  • Keep reusable orchestration in workflows, not ad hoc scripts.
  • Prefer atmos terraform deploy for deployment steps so dependencies can be honored.
  • Do not use sleeps for readiness if a wait, health check, or require step can express it.
  • Avoid hidden state between steps; pass explicit outputs or files.

© cloudposse, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in agent-skills/skills/atmos-workflows of cloudposse/atmos.

  • SKILL.md
  • references/workflow-syntax.md

Open the folder on GitHubat commit bbe58a6

Compare with similar skills

Atmos Workflows next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Atmos Workflows compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Atmos Workflows this skillcloudposse/atmos1.4k—~1.3kAutomated safety check: PassApache-2.0
Workflow Automationruvnet/ruflo74k2 repos~440Automated safety check: PassMIT
Schedule Recipemohitagw15856/pm-claude-skills1.4k—~1.1kAutomated safety check: PassMIT
Home Assistant Managerkomal-SkyNET/claude-skill-homeassistant965—~1.8kAutomated safety check: WarnMIT
Campaign Postmortemzapier/gtm-cheat-codes342—~438Automated safety check: PassMIT
Cicd Automation Workflow Automateaiskillstore/marketplace4306 repos~557Automated safety check: PassNone

Similar skills

  • Workflow creation, execution, and template management. An agent skill from ruvnet/ruflo.

    74k GitHub starsUsed in 2 repos~440 tokens
    Productivity & AutomationAuto-check passed
  • Schedule Recipe

    mohitagw15856/pm-claude-skills

    Turn 'run this every Friday at 4pm' into a working, copy-paste schedule on the user's actual runner.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Home Assistant Manager

    komal-SkyNET/claude-skill-homeassistant

    Edits, validates, deploys and verifies Home Assistant YAML configuration over SSH, hass-cli or MCP, including automations and Lovelace dashboards.

    965 GitHub stars~1.8k tokensUpdated 3 mo ago
    Productivity & AutomationAuto-check: warnings
  • Campaign Postmortem

    zapier/gtm-cheat-codes

    Official

    Build sourced campaign retrospectives from goals, launch context, performance data, team feedback, and follow-up actions.

    342 GitHub stars~438 tokensUpdated 2 mo ago
    DevOps & CloudAuto-check passed
  • Cicd Automation Workflow Automate

    aiskillstore/marketplace

    You are a workflow automation expert specializing in creating efficient CI/CD pipelines, GitHub Actions workflows, and automated development processes.

    430 GitHub starsUsed in 6 repos~557 tokens
    DevOps & CloudAuto-check passed
  • Uipath Aops

    UiPath/skills

    UiPath StudioAdmin AOps (uip aops) — SourceControl discovery plus CICD pipelines.

    166 GitHub stars~6.3k tokensUpdated today
    Productivity & AutomationAuto-check: notes

More from cloudposse/atmos

All 70 skills in this repo
  • Fix Log

    cloudposse/atmos

    A skill your agent uses when implementing, finishing, documenting, or reviewing a fix, repair, remediation, bug fix, debug-and-fix task, workflow fix, infrastructure fix, or any change that should…

    1.4k GitHub stars~685 tokensUpdated today
    Auto-check passed
  • Atmos Lint

    cloudposse/atmos

    Atmos Terraform linting with TFLint: standalone atmos terraform lint, component-aware config discovery and toolchain versions, TFLint rule configuration, and lifecycle hooks/CI findings.

    1.4k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Changelog

    cloudposse/atmos

    Blog post authoring for Atmos: MDX template, frontmatter, website/blog/tags.yml and authors.yml rules, problem-first framing, backtick-opening ban, optional cast embeds, and no-Go-internals leakage.

    1.4k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Editions

    cloudposse/atmos

    Decide whether a PR's new or changed default needs edition-journal handling (pkg/edition, docs/prd/editions.md), and do the mechanical work if so: journal entries, the four-layer default check…

    1.4k GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Atmos Migration

    cloudposse/atmos

    Migrate to Atmos from native Terraform, Terraform Workspaces, Terramate, Terragrunt, Make, Just, or Task; migrate tool versions from mise or Aqua CLI; migrate AWS/GCP/Azure CLI configs, Leapp…

    1.4k GitHub stars~5.1k tokensUpdated today
    Auto-check: warnings
  • PR Maintenance Loop

    cloudposse/atmos

    Start an hourly background loop that keeps the current branch's PR rebased, its addressed CodeRabbit threads resolved, its CI checks passing, its lint clean, its tests passing with adequate patch…

    1.4k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Questions about Atmos Workflows

What does Atmos Workflows do?

Workflow automation: native step types, multi-step workflows, parallel/matrix/wait/container/emulator steps, when: conditions (CEL), require/assert preconditions, output steps, retries…. Atmos Workflows is an agent skill from cloudposse/atmos.

When should I use Atmos Workflows?

Atmos Workflows fits situations like: tasks that involve Workflow automation.

How do I install Atmos Workflows in Claude Code?

Run `npx skills add cloudposse/atmos --skill atmos-workflows -a claude-code`. Or copy the skill folder (agent-skills/skills/atmos-workflows in cloudposse/atmos) into .claude/skills/atmos-workflows in your project. Claude Code loads it when a task matches its description.

How do I install Atmos Workflows in Codex?

Run `npx skills add cloudposse/atmos --skill atmos-workflows -a codex`. Or copy the skill folder (agent-skills/skills/atmos-workflows in cloudposse/atmos) into .agents/skills/atmos-workflows in your project. Codex loads it when a task matches its description.

Can I use Atmos Workflows in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cloudposse/atmos --skill atmos-workflows -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/atmos-workflows, .gemini/skills/atmos-workflows, .github/skills/atmos-workflows and .opencode/skills/atmos-workflows in your project.

What does Atmos Workflows need to run?

SKILL.md names no scripts, command-line tools or credentials: Atmos Workflows is instructions for the agent only.

Does Atmos Workflows access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Atmos Workflows safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Atmos Workflows use?

Atmos Workflows is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Atmos Workflows use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.8k tokens, read only when the agent opens those files.

What are the alternatives to Atmos Workflows?

Skills that share tags, products or a category with Atmos Workflows: Workflow Automation (ruvnet/ruflo, 74k stars), Schedule Recipe (mohitagw15856/pm-claude-skills, 1.4k stars), Home Assistant Manager (komal-SkyNET/claude-skill-homeassistant, 965 stars) and Campaign Postmortem (zapier/gtm-cheat-codes, 342 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Atmos Workflows?

cloudposse (a GitHub organization) maintains it in cloudposse/atmos, which has 1,395 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 7, 2026.

Source: cloudposse/atmos on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.