CLI Skills

What it does

Example prompts

• “/cli-skills”

Requirements

• Pre-approved tools (allowed-tools): Read, Grep, Glob

Workflow steps

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

1. 1User Experience First: CLI should feel responsive and provide clear feedback
2. 2Graceful Degradation: Handle missing services, network errors, and timeouts gracefully
3. 3Consistent Output: Use the output API for all user-facing messages
4. 4Cross-Platform: Test on macOS, Linux, and Windows
5. 5Terminal Compatibility: Test with different terminal emulators and sizes

What it can do on your machine

Read from SKILL.md and the folder at commit 6244d46. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Grep
  • Glob

  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 go).

  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

CLI Skills loads about 1.2k tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 239 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~28

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

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

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 llama-farm/llamafarm at commit 6244d46, republished under its Apache-2.0 licence (© llama-farm). 239 words, ~1,217 tokens.

name

cli-skills

description

CLI best practices for LlamaFarm. Covers Cobra, Bubbletea, Lipgloss patterns for Go CLI development.

allowed-tools

Read, Grep, Glob

user-invocable

false

cli/
  cmd/             # Cobra command implementations
    config/        # Configuration types and loading
    orchestrator/  # Service management and process control
    utils/         # Shared utilities (HTTP, output, logging)
    version/       # Version and upgrade handling
  internal/        # Internal packages (not exported)
    tui/           # Reusable TUI components
    buildinfo/     # Build-time information

var myCmd = &cobra.Command{
    Use:   "mycommand [args]",
    Short: "Brief description",
    Long:  `Extended description with examples.`,
    Args:  cobra.MaximumNArgs(1),
    RunE: func(cmd *cobra.Command, args []string) error {
        // Implementation with error returns
        return nil
    },
}

func init() {
    rootCmd.AddCommand(myCmd)
    myCmd.Flags().StringVar(&flagVar, "flag", "default", "Flag description")
}

type myModel struct {
    viewport viewport.Model
    textarea textarea.Model
    width    int
    height   int
    err      error
}

func (m myModel) Init() tea.Cmd {
    return tea.Batch(m.textarea.Focus(), doAsyncWork())
}

func (m myModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
    var cmds []tea.Cmd
    switch msg := msg.(type) {
    case tea.WindowSizeMsg:
        m.width = msg.Width
        m.height = msg.Height
    case tea.KeyMsg:
        switch msg.String() {
        case "ctrl+c":
            return m, tea.Quit
        }
    }
    return m, tea.Batch(cmds...)
}

func (m myModel) View() string {
    return lipgloss.JoinVertical(lipgloss.Left,
        m.viewport.View(),
        m.textarea.View(),
    )
}

// Use the output API for consistent messaging
utils.OutputInfo("Starting service %s...", serviceName)
utils.OutputSuccess("Service started successfully")
utils.OutputError("Failed to start service: %v", err)
utils.OutputProgress("Downloading model...")
utils.OutputWarning("Service already running")

// Ensure services are running before operations
factory := GetServiceConfigFactory()
config := factory.ServerOnly(serverURL)
orchestrator.EnsureServicesOrExitWithConfig(config, "server")

// Or with multiple services
config := factory.RAGCommand(serverURL)
orchestrator.EnsureServicesOrExitWithConfig(config, "server", "rag", "universal-runtime")

© llama-farm, 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 3 other files in .claude/skills/cli-skills of llama-farm/llamafarm.

• SKILL.md
• bubbletea.md
• cobra.md
• performance.md

Open the folder on GitHubat commit 6244d46