agentleFS
itentialitential/infra-agent-skills/skills/sdwan-policy-management/SKILL.md

sdwan-policy-management

Skill1 starsChanged 32 days agoApache-2.0View on GitHub

Look up, create, edit, put into effect (activate, or bind to sites), take out of effect, and delete a centralized SD-WAN policy on a supported SD-WAN orchestrator — currently Cisco Catalyst SD-WAN Manager (original template-policy model, centralized policy only) and Palo Alto Networks Prisma SD-WAN (stacked path and QoS policy). A policy is assembled from reusable pieces and applied to sites; which pieces this skill authors and which must already exist depends on the platform (see references/INDEX.md). Orchestrator-level policy, distinct from firewall-management's security rules and vpn-tunnel-management's point-to-point tunnels. Assumes an authenticated client for the target orchestrator's API 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

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Not for building the reusable inputs a platform's policy refers to (lists, prefixes, applications, and similar) where that platform's …

    line 18
  2. Very specific:

    Not for security rules on a firewall — see firewall-management.

    line 21
  3. Very specific:

    Not for building a point-to-point VPN tunnel on a gateway — see vpn-tunnel-management.

    line 22
  4. Very specific:

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

    line 23
  5. Distinctive:

    Does not cover firewall rules, point-to-point VPN tunnels, or wireless SSID/WLAN management, even where the same vendor offers them in one …

    line 54
  6. Very specific:

    Does not cover localized (device-level) policy, or authoring the reusable inputs a platform's policy refers to where that platform's …

    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 Policy Management

Manages the lifecycle of a centralized SD-WAN policy — create, edit, put into or out of effect, delete — on whichever orchestrator the caller is targeting, following that platform's own documented procedure exactly.

When to use this skill

  • Looking up, creating, editing, putting into effect (activating, or binding to sites), taking out of effect, or deleting a centralized policy on a supported SD-WAN orchestrator. Which of those actions a platform supports is platform-dependent; see references/INDEX.md.
  • Not for building the reusable inputs a platform's policy refers to (lists, prefixes, applications, and similar) where that platform's procedure does not cover them, or for device-level (localized) policy; see references/INDEX.md for what each platform's procedure covers.
  • Not for security rules on a firewall — see firewall-management.
  • Not for building a point-to-point VPN tunnel on a gateway — see vpn-tunnel-management.
  • Not for wireless SSID/WLAN management, even where one vendor offers both — see wireless-network-management.

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

These claims were checked against both documented platforms and do not extend automatically to a platform not listed in references/INDEX.md. Where a platform differs, its own procedure wins.

  • Saving a policy and putting it into effect may be separate states. Where a platform separates them, saving or editing does not change network behavior; activation does. Where it does not (a policy takes effect once attached to a site), treat an edit to anything already attached as a live change. Report which state the policy is in.
  • A policy is assembled from reusable pieces and applied to a scope. Where a platform lets pieces be shared, changing one can change every policy that uses it; check where it is used first.
  • Overlapping scopes can make behavior ambiguous. Where the same policy type can reach one site by more than one route, behavior may be unpredictable and the platform may not warn about it.
  • Putting a policy into or out of effect may complete asynchronously. An accepted request is not a confirmed outcome; confirm the final state before reporting success.

Procedure

  1. Identify the target platform — from the caller's 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 contains that platform's full operational procedure, error handling, patterns, known limitations, tools, and verification checklist.
  3. Report the outcome using that platform 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 before this skill can be used for it.
  • Does not cover firewall rules, point-to-point VPN tunnels, or wireless SSID/WLAN management, even where the same vendor offers them in one product.
  • Does not cover localized (device-level) policy, or authoring the reusable inputs a platform's policy refers to where that platform's procedure does not (see references/INDEX.md).

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 procedure changes — a new error code, a corrected field, a changed API path — belong in that platform's own references/<platform>/procedure.md, never here.

Tools

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

Verification checklist

  • Target platform confirmed against references/INDEX.md before proceeding
  • That platform's own procedure.md was followed, including its own confirmation gates on putting a policy into or out of effect, deleting one, and editing one that is in effect
  • 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.