AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Unifi Yourskill

skill-t3chnaztea-unifi-skills-template · by t3chnaztea

>-

— No reviews yet
0 installs
27 views
0.0% view→install

Install

$ agentstack add skill-t3chnaztea-unifi-skills-template

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-t3chnaztea-unifi-skills-template)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Unifi Yourskill? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

UniFi Yourskill

One or two sentences: what this covers, and that it assumes the auth lanes and endpoint map from unifi-connect. Cross-reference siblings by name (unifi-firewall, unifi-wifi, unifi-clients, unifi-context-map) instead of repeating their content.

Guidelines for a good UniFi skill

Delete this section in your real skill; it is authoring guidance.

  • Name: unifi-, lowercase and hyphens. The directory name MUST equal

the frontmatter name.

  • Description: starts with "Use when", lists concrete triggers and symptom

phrasings, ends with a "not for X, use Y" pointer. No workflow summary: an agent will follow the description instead of reading the body.

  • Parameterize everything site-specific. `` never a real address,

$UNIFI_API_KEY from env never a literal, ` / / placeholders. Where an example address is unavoidable use the documentation ranges: 192.0.2.x (RFC 5737) and aa:bb:cc:dd:ee:ff`.

  • Never include a real inventory. No MAC lists, no camera names or

placements, no WAN address, no SSID names, no household or company names. See unifi-context-map for why this matters more here than in most repos.

  • Original prose only. Do not paste from Ubiquiti docs or help-centre

articles. Write the lesson the docs do not teach, and link the docs as the canonical manual.

  • Say which version you verified against, in compatibility and in the body

for any version-sensitive claim. UniFi moves endpoints between releases with no deprecation notice. A claim stated as universal that was observed once on one controller is the most likely thing in a skill to be wrong.

  • Distinguish config from operational state. This API will echo back

settings it has not applied. If a claim rests on a read-back, say which field and which endpoint proves it.

  • Verify against ground truth. Every write ends with a fresh read and a

before/after. Show the reader how to confirm, not just how to change.

  • Keep SKILL.md under ~500 lines; push heavy detail into references/*.md.
  • Scripts are allowed here (this repo ships one) but keep them standard-library

only, dependency-free, and readable in one sitting. An agent operating someone's gateway should be running code they can audit in five minutes.

Overview

What this is and the core principle, in one or two sentences.

When to use

Symptoms and situations. When NOT to use.

[Your sections]

Quick-reference recipes, one worked example, the specific traps you learned. One excellent example beats five generic ones. If you have a postmortem, tell it: the numbers and the wrong turns are what make it stick.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.