agentleFS
Sign inStart free
MongoDBKnown publishermongodb/agents/.agents/skills/atlas-agent-engine-docs/SKILL.md

atlas-agent-engine-docs

Skill8 starsChanged 26 days agoApache-2.0View on GitHub

Answer Atlas Agent Engine platform questions from current documentation. Use for questions about the agentengine CLI, project creation, local development, deployment, Atlas setup, memory, remote MCP, agent-to-agent communication, governance, monitoring, or network egress. Consult the documentation source before answering rather than relying on prior knowledge.

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Use this skill to answer platform questions from the current documentation on demand.

    line 8
  2. Distinctive:

    Do not construct page URLs by guessing path segments.

    line 22
  3. Distinctive:

    If it is unavailable, respond only that the Atlas Agent Engine documentation couldn't be reached right now, and suggest trying again later.

    line 28
  4. Distinctive:

    If it is available, navigate from the base URL to the pages relevant to the topic and read only those.

    line 29
  5. Distinctive:

    If the documentation does not cover the question, say so.

    line 31
  6. Distinctive:

    Use this list to decide whether a question belongs to this skill and what to look for.

    line 35
  7. Distinctive:

    Call out preview-only behavior, prerequisites, or access requirements when the source documents them.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Atlas Agent Engine Documentation

Use this skill to answer platform questions from the current documentation on demand. Do not preload the documentation set or answer platform-specific questions from memory when a documentation source is available.

Documentation Source

The only documentation source is the public site:

https://www.mongodb.com/docs/agentengine

Available means a request to that site returns HTTP 200 with a documentation page body.

Treat it as unavailable on any of: HTTP 404, any other 4xx or 5xx, a network error or timeout, or a 200 whose body is not documentation (for example a redirect to a generic landing or sign-in page). The site is published, so unavailable means a temporary problem or a changed URL.

Do not construct page URLs by guessing path segments. Start at the base URL and follow the site's own navigation, search, or links to reach a page.

Retrieval Workflow

  1. Identify the platform topic in the request.
  2. Request the documentation site and apply the availability check above.
  3. If it is unavailable, respond only that the Atlas Agent Engine documentation couldn't be reached right now, and suggest trying again later. Do not answer the platform question from memory, and do not mention private sources, credentials, or alternative documentation.
  4. If it is available, navigate from the base URL to the pages relevant to the topic and read only those.
  5. Answer from the retrieved page content and cite the exact page URL you read.
  6. If the documentation does not cover the question, say so. Do not invent platform behavior or fill gaps with stale knowledge.

Topics In Scope

Use this list to decide whether a question belongs to this skill and what to look for. These are topic names, not URLs or file paths; resolve the actual page through the site itself.

  • Getting started
  • CLI installation and authentication
  • Project creation
  • Local development
  • Deep agents
  • Build and deployment
  • Memory
  • Remote MCP
  • Agent-to-agent communication
  • Atlas organizations, projects, and workspaces
  • Guardrails and policy engine
  • Monitoring
  • Monorepos
  • Network egress
  • Agent manifest reference

Answer Format

  • State the answer first.
  • Cite the retrieved documentation page at the end.
  • Call out preview-only behavior, prerequisites, or access requirements when the source documents them.

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.

Check your setup, free