Index of every page on this site: llms.txt
All skills
erkamyaman avatar

/cli-for-your-app

@7fcc555
Run it yourself

Use when making an app or library usable by a person's own AI agent. Designs a command-line interface so agents can drive the app without a built-in chatbot.

  • 2 files
  • 2.2 KB
  • Updated 2 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills/cli-for-your-app

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈44 tokens for metadata: the name and description. ≈350 when used: this file. ≈150 more on demand in 1 file.

Description uses 2.2% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈176 characters, or 2.2%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

CLI for your app

Inspired by DHH's Rails World 2026 keynote: https://www.youtube.com/watch?v=vDjW_dRyKXY

From the talk

DHH says he doesn't want in-app chatbots. He wants to bring his own agent and let it use apps through a CLI, and he jokingly demands one from every app "by next Friday". He cites the Hey CLI as an example. The CLI design details below are our additions, not from the talk.

The talk's view: instead of adding a chatbot to every app, let users bring their own agent and give it a command line to your app. A good CLI is also easy for humans and scripts to use.

When to use

  • Your app has actions users repeat or want to automate.
  • You're tempted to add an in-app assistant.

Steps

  1. List the app's main read and write actions (list, show, create, update, search).
  2. Map each to a command with predictable names: app <noun> <verb>.
  3. Make output easy to parse: a --json flag, stable field names, and clear exit codes.
  4. Handle auth without prompts that block an agent (token via environment variable or config file).
  5. Add --help text with an example for every command.
  6. Make destructive commands explicit (--confirm or a dry-run flag).

Verification

Give an agent only the CLI's --help output and a task. If it completes the task without extra hints, the CLI is clear enough. Fix whatever it got stuck on.

See references/cli-checklist.md.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 7fcc555. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Activeupdated 2 months ago

README badge

README badge for erkamyaman/dhh-p-bloom-agent-skills/cli-for-your-app