---
name: Observal Agents
slug: observal-agents
category: AI Engineering
description: Observal Agents creates, validates, publishes, versions, and manages Observal Agents from the command line, including pulling, archiving, restoring, and transferring ownership. Use it when building, installing, or changing an Agent definition or managing its lifecycle.
github: "https://github.com/Observal/Observal/tree/main/observal_cli/skills/observal-agents"
language: Python
stars: 2364
forks: 472
install: "npx degit https://github.com/Observal/Observal/tree/main/observal_cli/skills/observal-agents ~/.claude/skills/observal-agents"
installs_to: ~/.claude/skills/observal-agents
source_path: observal_cli/skills/observal-agents/SKILL.md
collection_size: 10
category_size: 2451
collection_url: "https://dirskills.com/collections/Observal/Observal"
added: 2026-08-18T06:58:07.092Z
last_synced: 2026-08-18T06:58:07.092Z
canonical_url: "https://dirskills.com/skills/observal-agents"
---

# Observal Agents

Observal Agents creates, validates, publishes, versions, and manages Observal Agents from the command line, including pulling, archiving, restoring, and transferring ownership. Use it when building, installing, or changing an Agent definition or managing its lifecycle.

**Install:**

```bash
npx degit https://github.com/Observal/Observal/tree/main/observal_cli/skills/observal-agents ~/.claude/skills/observal-agents
```

## README

# Managing Observal Agents

## Execution contract

1. Execute commands with a 60 second timeout.
2. **Use machine output by default:** add `--output json` whenever supported. Parse list results from `items` and pagination fields.
3. Use `--help` before acting when a path or flag is uncertain.
4. Keep workflows noninteractive. Supply required fields, `--no-prompt`, and confirmation flags.
5. Use UUIDs or `qualified_name` values returned by JSON. Never automate with row numbers.
6. Prefer native `agent init`, `agent add`, and `agent build` over hand-written scaffolding or custom validation.
7. Verify every publish, release, pull, ownership, and lifecycle mutation.
8. Never print MCP environment values, headers, tokens, or other secrets.
9. Mutations are sent once. After an uncertain transport failure, read Agent state before retrying.

## Choose the workflow

| User intent | Workflow |
| --- | --- |
| Find or inspect an Agent | Discover and inspect |
| Install an existing Agent into a harness | Pull and verify |
| Create a simple Agent in one call | Direct create |
| Author an Agent with components or files | Init, add, build, publish |
| Change the current listing without a new reviewed version | Update in place |
| Publish a reviewed patch, minor, or major version | Release |
| Create many Agents from a prepared file | Bulk create |
| Archive, restore, transfer, or manage co-authors | Lifecycle and collaboration |

Read [Agent workflows](references/agent-workflows.md) completely before executing the selected workflow.

## State rules

- `create` without complete flags starts a wizard. Agents must provide all required inputs or use a file.
- `publish --update` changes the current Agent in place.
- `release --bump` creates a reviewed version. Do not use update when the user asked for a release.
- Public teamspace publication may remain private with a pending visibility or listing review. Report the actual returned status.
- Pull success requires checking `files`, `warnings`, and `setup_commands`. Partial setup is not success.
- A 409 is a decision point, not a generic retry signal. Read current state before choosing update or release.

## Completion

Report the canonical Agent identity, resulting status and version, files changed for local operations, warnings, and the smallest next action. Verify with `agent show`, `agent versions`, or `scan` when the mutation response is not sufficient.