agentleFS
williamcorrea23williamcorrea23/sap-router-skill/.agents/skills/automation-pilot-catalog-explorer/SKILL.md

automation-pilot-catalog-explorer

Skill1 starsChanged 4 months agoMITView on GitHub

Discover available commands and catalogs in SAP Automation Pilot via API. Use when you need to find what executors/commands exist, get command definitions, or explore a catalog before generating new commands. Essential for complex command generation involving multiple services.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When generating a command that involves multiple services:

    line 75

≈ “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

Catalog Explorer

Discover available commands in SAP Automation Pilot dynamically via API.

Prerequisites

Environment variables must be set:

export AUTOPI_HOSTNAME="emea.autopilot.cloud.sap"
export AUTOPI_USERNAME="your-username"
export AUTOPI_PASSWORD="your-password"

API Operations

List All Catalogs

Discover what catalogs are available in the tenant.

# List all catalogs (SAP-provided + custom)
curl -s -u "$AUTOPI_USERNAME:$AUTOPI_PASSWORD" \
  "https://$AUTOPI_HOSTNAME/api/v1/catalogs"

# List only SAP-provided catalogs (built-in)
curl -s -u "$AUTOPI_USERNAME:$AUTOPI_PASSWORD" \
  "https://$AUTOPI_HOSTNAME/api/v1/catalogs?provided=true"

# List only custom/tenant catalogs
curl -s -u "$AUTOPI_USERNAME:$AUTOPI_PASSWORD" \
  "https://$AUTOPI_HOSTNAME/api/v1/catalogs?own=true"

List Commands in a Catalog

CATALOG="applm-sapcp"
curl -s -u "$AUTOPI_USERNAME:$AUTOPI_PASSWORD" \
  "https://$AUTOPI_HOSTNAME/api/v1/commands?catalog=$CATALOG"

Get Command Definition

COMMAND_ID="applm-sapcp:RestartCfApp:1"
curl -s -u "$AUTOPI_USERNAME:$AUTOPI_PASSWORD" \
  "https://$AUTOPI_HOSTNAME/api/v1/commands/$COMMAND_ID"

Search Across Catalogs

Find commands matching a pattern.

# List all SAP-provided catalog IDs
curl -s -u "$AUTOPI_USERNAME:$AUTOPI_PASSWORD" \
  "https://$AUTOPI_HOSTNAME/api/v1/catalogs?own=false"

# Search specific catalogs for commands matching a keyword
for catalog in applm-sapcp sm-sapcp cf-sapcp; do
  echo "=== $catalog ==="
  curl -s -u "$AUTOPI_USERNAME:$AUTOPI_PASSWORD" \
    "https://$AUTOPI_HOSTNAME/api/v1/commands?catalog=$catalog"
done

Workflow: Complex Command Generation

When generating a command that involves multiple services:

1. User: "Create a command that restarts CF apps and checks SM bindings"

2. Discover relevant catalogs:
   - Query: GET /commands?catalog=applm-sapcp
   - Query: GET /commands?catalog=sm-sapcp

3. Find specific commands:
   - Found: applm-sapcp:RestartCfApp:1
   - Found: sm-sapcp:GetServiceBinding:1

4. Fetch definitions to understand parameters:
   - GET /commands/applm-sapcp:RestartCfApp:1
   - GET /commands/sm-sapcp:GetServiceBinding:1

5. Generate composite command using discovered executors

Error Handling

ErrorMeaningAction
401 UnauthorizedInvalid credentialsCheck AUTOPI_USERNAME/PASSWORD in .env
404 Not FoundCatalog/command doesn't existUse discovery to find correct ID
Empty responseNo commands in catalogCatalog may be empty or restricted

Related Skills

  • automation-pilot-command-generation — Uses this skill for executor discovery
  • automation-pilot-content-management-via-api — Deploy generated commands
  • automation-pilot-executions-api — Run and monitor commands

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.