agentleFS
itentialitential/infra-agent-skills/skills/sdwan-site-onboarding/SKILL.md

sdwan-site-onboarding

Skill1 starsChanged 32 days agoApache-2.0View on GitHub

Bring a new branch site onto an SD-WAN fabric from a reusable site blueprint, attach its edge devices, confirm it is operating, and back it out if needed — currently Prisma SD-WAN (site template creation and deployment, device-shell assignment, deployment status, removal) and Versa Director (device creation from a post-staging template, device activation, confirmation). Use when onboarding one or more branch sites. Not for authoring routing or security policy (see sdwan-policy-management). Assumes an authenticated client for the target SD-WAN controller is already available; this skill does not provision or authenticate it. Check references/INDEX.md for which platforms and operations are covered.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Not for building the routing, security, or path policy a site uses — see sdwan-policy-management.

    line 19
  2. Very specific:

    Not for wireless SSID/WLAN setup, even where one vendor sells both — see wireless-network-management.

    line 20
  3. Very specific:

    Not for point-to-point VPN tunnels — see vpn-tunnel-management.

    line 22
  4. Very specific:

    Not for device software upgrades on an already-onboarded site — see software-upgrade-lifecycle.

    line 23
  5. Very specific:

    Only two platforms are documented today, so these are claims expected to hold for any SD-WAN platform and do not extend automatically to a …

    line 27
  6. Distinctive:

    A site name may already be in use: Check for an existing site of the same name first.

    line 37
  7. Distinctive:

    Does not cover authoring routing, security, or path policy, wireless networks, or software upgrades.

    line 55
  8. Distinctive:

    Does not cover data-center sites, firewall-hosted SD-WAN, or virtual edge instance provisioning unless the platform procedure says so.

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

SD-WAN Site Onboarding

Takes a branch site from nothing to an operating member of the SD-WAN fabric — site and device configuration created from a blueprint, edge hardware attached, health confirmed — and, where the platform allows, reverses it, following the target platform's own documented procedure.

When to use this skill

  • Creating a site blueprint from a proven reference site, then deploying one or more new sites from it, with or without the edge device already in hand.
  • Attaching or releasing an edge device for a site that is being onboarded.
  • Checking whether a deployed site finished onboarding, or removing a site that should not exist.
  • Not for building the routing, security, or path policy a site uses — see sdwan-policy-management.
  • Not for wireless SSID/WLAN setup, even where one vendor sells both — see wireless-network-management.
  • Not for point-to-point VPN tunnels — see vpn-tunnel-management.
  • Not for device software upgrades on an already-onboarded site — see software-upgrade-lifecycle.

Universal concepts (shared SD-WAN vocabulary, not a wire standard)

Only two platforms are documented today, so these are claims expected to hold for any SD-WAN platform and do not extend automatically to a platform not listed in references/INDEX.md. Where a platform differs, its own procedure wins.

  • A site and its edge device are separate objects. Where the platform allows it, site configuration can be created before the physical device is available and bound to the device later.
  • A device must be known to the controller before it can carry a site. How and when it is attached (during deployment or in a later step) varies by platform; follow the platform procedure.
  • Deployment is asynchronous where documented. An accepted request is not a finished site; confirm the final state of each site separately.
  • A site name may already be in use. Check for an existing site of the same name first; the platform may update it or reject the request.
  • Removal usually has ordering constraints (device detached before the site can go); where the platform documents them, follow that order.

Procedure

  1. Identify the target platform — from the request or the platform argument. Check references/INDEX.md; if no matching row exists, stop: this skill doesn't cover it yet.
  2. Open references/<platform>/procedure.md and follow it exactly — it holds that platform's sequences, confirmation gates, error handling, patterns, limitations, tools, and verification checklist.
  3. Report the outcome using that procedure's own status vocabulary — don't normalize it away.

Known limitations

  • Platform coverage is in references/INDEX.md; a platform not listed there needs a new reference file first.
  • Does not cover authoring routing, security, or path policy, wireless networks, or software upgrades.
  • Does not cover data-center sites, firewall-hosted SD-WAN, or virtual edge instance provisioning unless the platform procedure says so.

Contributing to this skill

SKILL.md only changes for two reasons: a bug in the universal concepts/router logic above, or adding a pointer to a newly-supported platform. Platform-specific changes — a new error code, a corrected field, a changed API route — belong in that platform's own references/<platform>/ files, never here.

Tools

Each platform assumes its own authenticated client — see references/INDEX.md for which, and that platform's procedure.md for the operations.

Verification checklist

  • Target platform confirmed against references/INDEX.md before proceeding
  • That platform's own procedure.md was followed, including its confirmation gates on deploying, assigning or releasing devices, and removing deployments, shells, or sites
  • Outcome reported using the platform procedure's own status vocabulary

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.