Skip to content
Back to search

cloudishai

MarketplaceWorks with Claude CodeGitHub

Agent Skills for Cloudish, the cloud an AI agent deploys a container to.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/cloudishai--skills/badge.svg)](/listings/cloudishai--skills)

HTML

<a href="/listings/cloudishai--skills"><img src="/api/listings/cloudishai--skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**Claude Code**

/plugin marketplace add cloudishai/skills
/plugin install cloudish@cloudishai

**Any agent that reads `SKILL.md`** (Claude Code, Codex, Cursor, …) — copy [`skills/cloudish`](skills/cloudish) into your agent's skills directory, or install the full skill straight from Cloudish:

mkdir -p ~/.claude/skills/cloudish
curl -s https://cloudish.ai/skill.md -o ~/.claude/skills/cloudish/SKILL.md

Then ask your agent: *"Deploy this app to Cloudish."*

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 15 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "cloudishai",
  3. "description": "Agent Skills for Cloudish, the cloud an AI agent deploys a container to.",
  4. "owner": {
  5. "name": "Hal9 Inc",
  6. "url": "https://cloudish.ai"
  7. },
  8. "plugins": [
  9. {
  10. "name": "cloudish",
  11. "source": "./",
  12. "description": "Deploy apps to Cloudish at a live URL: server-side builds, persistent storage for databases and files, user sign-in via OIDC, and API keys agents mint themselves and humans claim later."
  13. }
  14. ]
  15. }
README.md · README · 92 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="center"><img src="assets/cloudish-160.png" alt="Cloudish"></p>
  2. <h1 align="center">Cloudish Skills</h1>
  3. <p align="center">
  4. Agent Skills for <a href="https://cloudish.ai">Cloudish</a>, the cloud an AI agent deploys a container to.
  5. </p>
  6. Cloudish lets an agent create its own API key with one unauthenticated call,
  7. build any Dockerfile or source folder server-side, and run it as a long-lived
  8. container with an optional persistent volume, paid from prepaid credits the key
  9. can never exceed. No browser, no card, no local Docker.
  10. ## Skills
  11. | Skill | What it does |
  12. |---|---|
  13. | [`cloudish`](skills/cloudish/SKILL.md) | Prepares a project, deploys it to Cloudish, and reports the live URL. |
  14. The skill is a copy of **https://cloudish.ai/skill.md** and the docs it links
  15. to (credits, instances, replicas, container isolation, changelog), bundled so
  16. the agent reads them locally. It never fetches instructions at runtime; new
  17. versions ship as new releases of this plugin.
  18. ## What it runs and sends
  19. The plugin contains instructions only: no MCP server, hooks, scripts, or
  20. binaries. When you ask it to deploy, the agent uses `curl` and `tar` to call
  21. the Cloudish API at `https://cloudish.ai`, and to check that your deployed app
  22. answers at its own URL (`https://<name>.cloudish.app/`, or your own domain):
  23. - **Sends** a `.tar.gz` of the project folder (excluding `.git` and `.env*`) to
  24. Cloudish to be built and hosted, plus the project name, port, how it should
  25. run (always on, or sleeping when idle), and any env vars or secrets you ask
  26. it to set.
  27. - **Creates** a Cloudish API key with an unauthenticated call when the
  28. project doesn't have one yet. The key is used only to authenticate API calls
  29. to `cloudish.ai`, and is never printed to chat.
  30. - **Reuses** that key on later runs instead of minting another, so the project
  31. keeps the same Cloudish balance. It's a key the skill created on Cloudish,
  32. not one of your other credentials. A sub-agent can get its own key, minted
  33. and funded by the parent agent's key.
  34. - **Reports** the agent product and model (for example `claude-code`,
  35. `claude-opus-5-5`) when it creates a key, if known, plus `skills-repo`
  36. as the source. All three are optional.
  37. Adding credits happens outside Claude: the agent gives you a one-time
  38. `www.cloudish.ai` link, and any payment is made on that page in your browser.
  39. If your app signs its users in with Cloudish, that sign-in runs between your
  40. deployed app and `www.cloudish.ai`, not through the agent.
  41. The bundled docs are generated from the ones served at cloudish.ai, with links
  42. between them pointing at the local files.
  43. Your deployed code and data are handled under Cloudish's
  44. [privacy policy](https://www.cloudish.ai/privacy) and
  45. [terms](https://www.cloudish.ai/terms).
  46. ## Install
  47. **Claude Code**
  48. ```
  49. /plugin marketplace add cloudishai/skills
  50. /plugin install cloudish@cloudishai
  51. ```
  52. **Any agent that reads `SKILL.md`** (Claude Code, Codex, Cursor, …) — copy
  53. the [`skills/cloudish`](skills/cloudish) folder into your agent's skills
  54. directory.
  55. Then ask your agent: *"Deploy this app to Cloudish."*
  56. **In the Claude apps and Cowork**, the agent runs in a sandbox: when asked,
  57. allow outbound network access to `cloudish.ai` (the API) and `cloudish.app`
  58. (where your deployed apps are served). Keys don't carry over between chats
  59. there, so claim yours (the agent can give you a link) to keep your projects
  60. and credits with your account.
  61. ## Layout
  62. ```
  63. skills/cloudish/SKILL.md the skill (copy of cloudish.ai/skill.md)
  64. skills/cloudish/*.md the docs it links to, bundled
  65. .claude-plugin/ Claude Code plugin + marketplace manifests
  66. plugin.json OpenAI / Agent Plugins manifest
  67. assets/ icon
  68. ```
  69. ## License
  70. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.