agentleFS
javimoschjavimosch/supercli/skills/supercli/SKILL.md

supercli.quickstart

Skill53 starsChanged 5 months agoMITView on GitHub

SuperCLI capability router — discover and execute CLI commands through namespace.resource.action interface

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Instead of running raw commands, use:

    line 13
  2. Very specific:

    Never search the filesystem (plugins/, grep, glob) to find plugins or commands.

    line 20
  3. Distinctive:

    learn: Read usage documentation

    line 43
  4. Distinctive:

    execute: Run the command

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

SuperCLI Quickstart

SuperCLI is a deterministic capability router that wraps external CLIs behind a unified namespace.resource.action interface.

Key Concept

Instead of running raw commands, use:

supercli <namespace> <resource> <action> [--flags]

Agent Rules (CLI-first discovery)

Never search the filesystem (plugins/, grep, glob) to find plugins or commands. Use the CLI itself — it has built-in filters:

# Start here
supercli --json

# Find plugins by name (instead of grepping plugin.json files)
supercli plugins explore --name <query>

# Learn about a plugin
supercli plugins learn <plugin-name>

# Find plugins for a task
supercli discover --intent "<task>"

# List all commands matching a keyword
supercli commands --query <keyword> --limit 50 --json

Workflow

  1. discover: Find plugins/commands for an intent
  2. learn: Read usage documentation
  3. inspect: View command schema and flags
  4. plan: Preview execution steps
  5. execute: Run the command

supercli skills

Skill documents provide agent-facing guidance in SKILL.md format. Use supercli skills to discover and fetch skill documentation.

# List all available skills (command-level + catalog)
supercli skills list

# Get skill documentation for a specific capability
supercli skills get <namespace.resource.action>

# Get the skills usage guide (teaches how to use the skills system)
supercli skills teach

# Search skills catalog for matching skills
supercli skills search --query <text>

# Sync skills catalog from providers
supercli skills sync

# Manage skill providers
supercli skills providers list
supercli skills providers add --name <provider> --roots <path>
supercli skills providers remove --name <provider>

supercli plugins

Plugins extend supercli with additional command capabilities.

# Explore available plugins in the registry
supercli plugins explore

# Learn about a specific plugin
supercli plugins learn <plugin-name>

# Install a plugin from registry
supercli plugins install <plugin-name>

# Install a plugin from git repository
supercli plugins install --git <repo-url> --manifest-path <path>

# List installed plugins
supercli plugins list

# Show plugin details
supercli plugins show <plugin-name>

# Check plugin health
supercli plugins doctor <plugin-name>

Important Flags

FlagPurpose
--jsonMachine-readable output
--humanFormatted output for humans
--non-interactiveFail fast (for agents)

Exit Codes

CodeMeaning
0Success
82Validation error (missing args)
85Invalid argument
92Resource not found
105Integration error
110Internal error

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.