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

/pulumi-create-agent

@cd1011f official
by pulumipulumi/agent-skills80 stars
8
Run it yourself

Create a reusable Pulumi Agent with saved instructions, a role, and selected integrations. Use when the user asks to create, define, or set up a new Pulumi Agent.

Use this Skill: https://skilld.dev/gh/pulumi/agent-skills/pulumi-create-agent

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

referencesautomation-recovery.md

≈346 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Automation recovery

Keep the agent and known automation IDs. Fix only the unfinished step; do not recreate the agent or delete it as a rollback.

Saved settings differ

Report the automation ID, requested versus saved values, and active or paused state. An active automation may run with the saved settings. Ask whether to pause that ID unless the pause is already authorized.

For an authorized pause, use skill pulumi-setup-agent-automation. If it is not installed, retain the ID and pending pause request and explain that the recovery procedure is unavailable.

Create response was lost

Use ListAgentAutomationsV2 and GetAgentAutomationV2 to check whether creation succeeded. Follow all relevant pages. Use returned request or resource identifiers where available; a matching name or configuration alone does not establish which request created it.

If the outcome remains uncertain, report candidate IDs and states without retrying, adopting, or automatically pausing them. Explain that active candidates may run and ask whether the user wants a specific ID paused. A failed or incomplete read is not proof that nothing was created.

Resume later

Retain the draft, confirmed IDs, and unresolved choices. Resume the incomplete step after the required decision or access is available. Distinguish saved configuration from sender setup and actual task execution.

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 alerts3d3 checks · Risk SAFE
  • Gen Agent Trust Hub3d

    This skill is a configuration assistant for creating Pulumi Agents and automation tasks via the Pulumi CLI. It uses standard CLI commands and JSON request files to manage agent definitions and schedules. No security risks were detected.

  • Socket3d

    No alerts

  • Snyk3d

    Risk: LOW · No issues

Signed by skilld at cd1011f. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 4 days ago

README badge

README badge for pulumi/agent-skills/pulumi-create-agent