Agent skill

Atmos Asciicast

by cloudposse in cloudposse/atmos

Create and update Atmos repository asciicast demos for internal documentation, website publishing, and CastPlayer/CastEmbed embeds.

Apache-2.0Auto-check: notesDevOps & Cloud

Install Atmos Asciicast

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

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

GitHub CLI
$ gh skill install cloudposse/atmos atmos-asciicast --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/.claude/skills/atmos-asciicast .claude/skills/atmos-asciicast && 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-asciicast
GitHub stars
1.4k
Token cost
~1.6k tokens
SKILL.md length
828 words
Files
1
Skills in repo
70
Repo updated
First seen
Licence
Apache-2.0

At a glance

Create and update Atmos repository asciicast demos for internal documentation, website publishing, and CastPlayer/CastEmbed embeds.

  • Works in 6 steps: Define the user-facing story before… → Add or update the workflow/custom… → Regenerate the .cast into… → …
  • DevOps & Cloud work in your project
  • SKILL.md covers Intent, Defaults, Fixture Policy and Workflow Patterns, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Atmos Asciicast is an agent skill from cloudposse/atmos. Create and update Atmos repository asciicast demos for internal documentation, website publishing, and CastPlayer/CastEmbed embeds.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud. 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

  • DevOps & Cloud work in your project

Example prompts

  • “/atmos-asciicast”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Define the user-facing story before editing YAML: what feature is being proven, what command should the user remember, and what output…
  2. Add or update the workflow/custom command that regenerates the cast.
  3. Regenerate the .cast into website/static/casts.
  4. Review the cast as plain text for secrets, local paths, unstable timestamps, noisy logs, and shell complexity that distracts from Atmos.
  5. Embed it with the website CastPlayer component when the corresponding docs page can show it usefully, and in the feature's changelog blog…
  6. Commit only .cast files: the website renders them client-side, so no display derivatives are needed. Commit GIF/MP4/PNG/JPEG derivatives…

What it can do on your machine

Read from SKILL.md and the folder at commit 110e139. 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 mdx).

    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 Asciicast loads about 1.6k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 828 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:30
    env: !include cast-defaults.yaml .env.recording

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 110e139, republished under its Apache-2.0 licence (© cloudposse). 828 words, ~1,607 tokens.

Download SKILL.mdSave it as .claude/skills/atmos-asciicast/SKILL.md (or your agent's skills folder).
name
atmos-asciicast
description
Create and update Atmos repository asciicast demos for internal documentation, website publishing, and CastPlayer/CastEmbed embeds.

Atmos Asciicast Development Skill

Use this Claude skill when creating or updating committed .cast recordings inside the Atmos repository.

This is an internal Atmos development skill. It is intentionally separate from distributed Agent Skills. Do not symlink it to agent-skills, copy internal website assumptions into Agent Skills, or treat Claude skills and Agent Skills as synchronized artifacts.

Intent

Atmos casts are product demos, regression evidence, and documentation examples at the same time. They should show users that Atmos workflows are simple to follow and that the feature being demonstrated works in a realistic project.

  • Tell a small story a user can follow: inspect context, run the Atmos command, show the result.
  • Prefer Atmos-native commands and workflow features over clever shell expressions.
  • Keep recorded steps light. A visible step should usually be one command with one teaching purpose.
  • Use hidden setup, cleanup, and fixture preparation only to make the recorded story deterministic.
  • Treat each cast as evidence for a feature: include the command output that proves the behavior, then validate the committed .cast.

Defaults

  • Use shared cast defaults when available instead of repeating terminal settings on each cast step:

    yaml
    defaults:
      cast: !include cast-defaults.yaml .cast
      simulate: !include cast-defaults.yaml .simulate
    env: !include cast-defaults.yaml .env.recording
  • Keep common recording settings in cast-defaults.yaml under cast, simulate, and env (env.command for command setup, env.recording for the recorded process).

  • Write curated Atmos docs casts under website/static/casts/...; they are served from /casts/....

  • Use type: cast with mode: steps for deterministic command demos that need exit-code propagation.

  • Use mode: session only when the demo must show typed input, prompts, key presses, or terminal timing.

  • Keep ad hoc local recordings in the XDG cache via --cast; do not commit cache recordings.

Fixture Policy

  • Use deterministic Atmos demo fixtures under demo/casts.
  • Do not reuse product examples or test fixtures just to make a docs cast easier.
  • Keep demo output stable: no local absolute paths, hostnames, real account IDs, secrets, random IDs, or live timestamps.

Workflow Patterns

  • Put repeatable setup in atmos casts setup using type: workdir for fixture copies and a local GOBIN for the Atmos binary.
  • Keep pre-recording clean steps simple; they remove stale .cast files before recording and do not need failure cleanup semantics.
  • Put cleanup-after-recording steps after the type: cast step and use when: always when they restore secrets, stop services, or remove Terraform state.
  • Leave validation steps success-only so validation runs only after recording and required cleanup complete successfully.
  • Use output: none for noisy setup, reset, and cleanup commands that should not be part of the story.
  • Prefer type: cast mode: steps with nested type: shell steps for command demos; add type: simulate steps only when typed prompts make a longer story easier to follow.
  • Use type: toast for short recorded status narration instead of shell printf output.
  • Keep large shell scripts out of recorded casts. If unavoidable, hide them in setup/cleanup and explain the user-facing result with lightweight Atmos commands in the recording.
  • Use path-based custom command names for demo casts, for example casts generate demo fixtures native-terraform plan, and publish fixture casts under /casts/demo/fixtures/....
Show full SKILL.md (333 more words)Show less

Authoring Checklist

  1. Define the user-facing story before editing YAML: what feature is being proven, what command should the user remember, and what output proves it worked?

  2. Add or update the workflow/custom command that regenerates the cast.

  3. Regenerate the .cast into website/static/casts.

  4. Review the cast as plain text for secrets, local paths, unstable timestamps, noisy logs, and shell complexity that distracts from Atmos.

  5. Embed it with the website CastPlayer component when the corresponding docs page can show it usefully, and in the feature's changelog blog post (see the pull-request skill's Blog post section) — new commands and features should ship their blog post with a working demo, not just prose. Use CastEmbed (which wraps CastPlayer with Download/Share controls) directly in blog posts, followed by a [View the full example](/examples/<name>) link; don't reach for EmbedExample there.

    mdx
    <CastEmbed src="/casts/cli/describe-component.cast" title="describe component" chrome controls scrubber />
  6. Commit only .cast files: the website renders them client-side, so no display derivatives are needed. Commit GIF/MP4/PNG/JPEG derivatives only when a publishing target cannot consume the player.

Static Screengrabs

Docs screengrabs (CLI help output, command output snapshots) are plain .cast recordings committed under website/static/casts/screengrabs/ and rendered as a single static frame with the CastPlayer static prop:

mdx
<CastPlayer title="atmos about --help" src="/casts/screengrabs/atmos-about--help.cast" static chrome />

Static mode shows the final terminal content of the whole recording at natural height (no playback, no controls, no viewport clipping). The bulk help screengrabs are generated by atmos --chdir=demo/casts casts generate screengrabs cli, which records every command in demo/casts/screengrabs/demo-stacks.txt via the global --cast flag; story-style demo casts (e.g. learn/mindset) are custom commands under demo/casts/atmos.d/screengrabs/.

Static Render Formats (CLI)

atmos cast render supports native static outputs in addition to GIF/MP4: --html (inline-styled span fragment), --ascii (plain text, no ANSI), --png, and --jpg. These are rendered in-process from the recording's final terminal content — no aha, agg, or ffmpeg required. The global --cast flag accepts the same extensions (--cast=out.png), including on --help invocations. Use these for artifacts outside the website (GitHub embeds, image exports, machine-readable text); the website itself consumes raw casts.

© 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

Just SKILL.md in .claude/skills/atmos-asciicast of cloudposse/atmos.

Open the folder on GitHubat commit 110e139

Compare with similar skills

Atmos Asciicast 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 Asciicast compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Atmos Asciicast this skillcloudposse/atmos1.4k—~1.6kAutomated safety check: NotesApache-2.0
Monitor CInrwl/nx29k6 repos~4.7kAutomated safety check: PassMIT
Terraform and OpenTofu Guideagentscope-ai/QwenPaw36k6 repos~4.2kAutomated safety check: PassApache-2.0
Vercel Optimize Auditvercel-labs/agent-skills32k8 repos~4.3kAutomated safety check: PassNone
Analyze GitHub Action Logswithastro/astro63k1 repos~1.3kAutomated safety check: PassCustom licence
Openclaw Live Updateropenclaw/openclaw392k—~3.7kAutomated safety check: PassMIT

Similar skills

  • Monitor CI

    nrwl/nx

    Monitor Nx Cloud CI pipeline and handle self-healing fixes. An agent skill from nrwl/nx.

    29k GitHub starsUsed in 6 repos~4.7k tokens
    DevOps & CloudAuto-check passed
  • Terraform and OpenTofu Guide

    agentscope-ai/QwenPaw

    Guidance for writing and testing Terraform and OpenTofu code: module structure, naming, test approaches, CI/CD workflows, state handling and security scanning.

    36k GitHub starsUsed in 6 repos~4.2k tokens
    DevOps & CloudAuto-check passed
  • Vercel Optimize Audit

    vercel-labs/agent-skills

    Official

    Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations.

    32k GitHub starsUsed in 8 repos~4.3k tokens
    DevOps & CloudAuto-check passed
  • Official

    Analyze recent GitHub Actions workflow runs to identify patterns, mistakes, and improvements.

    63k GitHub starsUsed in 1 repo~1.3k tokens
    DevOps & CloudAuto-check passed
  • Openclaw Live Updater

    openclaw/openclaw

    Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation.

    392k GitHub stars~3.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Docs Learn PR Preview

    netdata/netdata

    Use only when the user explicitly asks to build, run, preview, inspect, or validate learn.netdata.cloud locally using the contents of a PR or documentation branch before merge.

    81k GitHub stars~2k tokensUpdated today
    DevOps & CloudAuto-check passed

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

Categories

Questions about Atmos Asciicast

What does Atmos Asciicast do?

Create and update Atmos repository asciicast demos for internal documentation, website publishing, and CastPlayer/CastEmbed embeds. Atmos Asciicast is an agent skill from cloudposse/atmos. Create and update Atmos repository asciicast demos for internal documentation, website publishing, and CastPlayer/CastEmbed embeds.

When should I use Atmos Asciicast?

Atmos Asciicast fits situations like: devOps & Cloud work in your project.

How do I install Atmos Asciicast in Claude Code?

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

How do I install Atmos Asciicast in Codex?

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

Can I use Atmos Asciicast 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-asciicast -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-asciicast, .gemini/skills/atmos-asciicast, .github/skills/atmos-asciicast and .opencode/skills/atmos-asciicast in your project.

What does Atmos Asciicast need to run?

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

Does Atmos Asciicast 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 Asciicast safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Atmos Asciicast use?

Atmos Asciicast 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 Asciicast use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Atmos Asciicast?

Skills that share tags, products or a category with Atmos Asciicast: Monitor CI (nrwl/nx, 29k stars), Terraform and OpenTofu Guide (agentscope-ai/QwenPaw, 36k stars), Vercel Optimize Audit (vercel-labs/agent-skills, 32k stars) and Analyze GitHub Action Logs (withastro/astro, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Atmos Asciicast?

cloudposse (a GitHub organization) maintains it in cloudposse/atmos, which has 1,398 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 10, 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.