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.

referencesadditional-outcomes.md

≈420 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Start a first task

Use this procedure only when the user asks for an immediate task in addition to creating the agent.

Discover and describe CreateTasks, GetTask, ListTasks, and GetTaskEvents on the target backend. Use the verified organization and saved agent ID. Keep the task within the agent's responsibility.

Choose which CLI connections the task may use, separately from the agent's role and MCP integrations. Set cliIntegrations explicitly: omitting it enables all configured CLI connections; [] enables none. Use the requested connections and explain this default before submission. If the API cannot apply the selection, keep the task as a draft.

Write the task message, agent ID, and CLI selection to a JSON request file using the described schema. Submit with --input and retain the returned taskId.

Read the task back to verify its agent binding and status. Use task events to check the initial message if GetTask does not expose it. Report any field, such as CLI selection, that the API does not return rather than claiming it was verified. Check execution within a bounded wait and distinguish task creation from successful completion.

If creation times out, use task list and get operations to reconcile the outcome before retrying. Follow all pages and use returned identifiers where available; matching text alone does not establish which request created a task. If the result remains uncertain, report the candidate IDs and states without retrying or cancelling them.

Keep the created agent if task setup fails. Resume only the unfinished step. A first task does not replace the creation skill's question about recurring automation.

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