New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Zabbix Metrics History

by automateyournetwork in automateyournetwork/netclaw

Retrieve polled metric history from Zabbix — interface utilization, counters and any collected item — over any time window, correctly routed between raw history and hourly trends.

Apache-2.0Auto-check passed

Install Zabbix Metrics History

skills CLI
$ npx skills add automateyournetwork/netclaw --skill zabbix-metrics-history -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install automateyournetwork/netclaw zabbix-metrics-history --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/automateyournetwork/netclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/workspace/skills/zabbix-metrics-history .claude/skills/zabbix-metrics-history && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
zabbix-metrics-history
GitHub stars
676
Token cost
~1.8k tokens
SKILL.md length
867 words
Files
1
Skills in repo
120
Repo updated
First seen
Licence
Apache-2.0

At a glance

Retrieve polled metric history from Zabbix — interface utilization, counters and any collected item — over any time window, correctly routed between raw history and hourly trends.

  • Works in 4 steps: item.get FIRST. Never call history.get… → pass the item's real value_type. Do not… → never mix value types in one call. → …
  • Someone asks what something WAS doing over time
  • SKILL.md covers Server, ⚠ Read this before you report…, The procedure — always, in… and The five reasons you get…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Zabbix Metrics History is an agent skill from automateyournetwork/netclaw. Retrieve polled metric history from Zabbix — interface utilization, counters and any collected item — over any time window, correctly routed between raw history and hourly trends. Use when someone asks what something WAS doing over time, from Zabbix specifically: is this normal, what did this interface do overnight, was it like this last Tuesday. For the same kind of question against Auvik-collected telemetry instead, use auvik-performance.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: An AI agent that claws through your network. The licence is Apache-2.0.

When your agent uses it

  • Someone asks what something WAS doing over time
  • From Zabbix specifically: is this normal
  • What did this interface do overnight
  • Was it like this last Tuesday

Example prompts

  • “/zabbix-metrics-history”

Requirements

  • A credential in ZABBIX_TOKEN

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. item.get FIRST. Never call history.get without it.
  2. pass the item's real value_type. Do not accept the default.
  3. never mix value types in one call.
  4. route between history and trends by the window.

What it can do on your machine

Read from SKILL.md and the folder at commit aa90e7d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are jsonc).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Zabbix Metrics History loads about 1.8k tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 867 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~117
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from automateyournetwork/netclaw at commit aa90e7d, republished under its Apache-2.0 licence (© automateyournetwork). 867 words, ~1,821 tokens.

Download SKILL.mdSave it as .claude/skills/zabbix-metrics-history/SKILL.md (or your agent's skills folder).
name
zabbix-metrics-history
description
Retrieve polled metric history from Zabbix — interface utilization, counters and any collected item — over any time window, correctly routed between raw history and hourly trends. Use when someone asks what something WAS doing over time, from Zabbix specifically: is this normal, what did this interface do overnight, was it like this last Tuesday. For the same kind of question against Auvik-collected telemetry instead, use `auvik-performance`.
version
1.0.0
license
Apache-2.0
tags
zabbix, nms, snmp, monitoring, history, trends, utilization, baseline, observability
user-invocable
true

Zabbix Metrics History

Server

zabbix-mcp — vendored third-party (mpeirone/zabbix-mcp-server, GPL-3.0, pinned 0722f48), running from its own virtualenv. Three tools: zabbix_api(method, params), zabbix_api_docs(method), zabbix_api_list(object). Read-only, enforced two ways (forced flag + destructive-method deny-list).

⚠ Read this before you report "no data"

This server is a generic passthrough. It will not stop you getting a wrong answer.

Unlike most NetClaw integrations, there is no code between you and the API enforcing correctness. Zabbix has two traps that return an empty array and a success status — no error, no warning. If you skip the procedure below you will confidently tell an engineer an interface was idle when it was carrying traffic.

Follow the procedure. It is the only safeguard that exists.

The procedure — always, in this order

Step 1 — item.get FIRST. Never call history.get without it.
jsonc
zabbix_api("item.get", {
  "hostids": ["<hostid>"],
  "search": {"key_": "net.if.in"},          // or whatever you're after
  "output": ["itemid","name","key_","value_type","units","history","trends"]
})

You need four fields off every item:

FieldWhy
value_typeStep 2 depends on it. Getting it wrong returns empty, silently
historyhow far back raw values exist — or 0, meaning never stored
trendshow far back hourly aggregates exist — or 0, meaning none
unitsso your answer has units
Step 2 — pass the item's real value_type. Do not accept the default.

history.get defaults history to 3 (numeric unsigned). Measured on a stock Zabbix 7.0: 84 of 121 items are 0 (float). So the default is wrong for most items, and wrong silently.

value_typeMeaning
0float ← most interface counters and rates
1character
2log
3unsigned ← the API default
4text
5binary
jsonc
zabbix_api("history.get", {
  "itemids": ["<itemid>"],
  "history": 0,                    // ← the item's OWN value_type, not the default
  "time_from": <epoch>, "time_till": <epoch>,
  "output": "extend", "sortfield": "clock", "sortorder": "DESC", "limit": 500
})
Step 3 — never mix value types in one call.

A single history.get serves one value type. Query four items of mixed types and you get back only the matching ones — the rest vanish with no error. Measured: 2 of 4 returned each way, zero overlap.

Group your items by value_type, make one call per group, merge the results.

Raw history is short-lived; hourly aggregates last far longer. item.get told you both in Step 1.

Requested windowUseSay in your answer
entirely within historyhistory.getraw polled values
entirely beyond history, trends > 0trend.gethourly min/avg/max, not instantaneous
spans the boundaryboth, mergedwhich part came from which
beyond bothneither existsnot retained — see below

trend.get returns value_min / value_avg / value_max / num per hour, and is numeric only.

Say when you used trends. "The peak was 400 Mbps" from raw values and from an hourly average are different claims, and an engineer sizing a link needs to know which they have.

The five reasons you get nothing back

They are indistinguishable over the wire — all five are an empty array. Tell them apart, and word them differently.

CauseHow to tellHow to say it
Wrong value typeyou didn't do Step 1/2Never report this. Re-query correctly
Aged outwindow predates history, trends > 0"beyond raw retention — here is the hourly data"
Retention disabledhistory=0 and/or trends=0 on the item"this item does not retain that" — a configuration fact, not an absence
Never collecteditem exists, no values ever, empty lastclock"monitored but has never returned a value" — a real finding, usually a broken poll
Genuinely idledata exists and the values are zero"zero throughput" — the only one that means nothing happened

Retention can be switched off per item. Measured on a stock install: 10 items had trends=0, and 5 had both history=0 and trends=0 — collected purely to fire triggers, never stored. Read the item; do not guess.

Show full SKILL.md (292 more words)Show less

Every answer must carry

  • The source — Zabbix, and which host/item.
  • The window actually served, which may differ from the one requested (say so if it does).
  • Whether the values are raw or hourly aggregates.
  • The item's units.
  • Zabbix's own clock where relevant — if a "last 5 minutes" query looks empty, clock skew between you and the NMS is a likely cause, and surfacing the NMS time makes that diagnosable instead of baffling.
  • Unambiguous timezones.
  • The bound, if you limited the result, plus how to narrow the query.

Refuse a future window or a reversed start/end with the reason — do not return empty.

If the same item key exists on multiple hosts, never merge them into one series without saying so.

Boundaries — which skill owns what

Want to…Use
Receive unsolicited trapssnmptrap-mcp — that is push; this polls on an interval and keeps history
Flow recordsipfix-mcp — flows, not counters
Metrics from infrastructure you instrumentedprometheus, grafana — pull-based stores; this is the NMS for gear you did not instrument
SaaS monitoring with its own agentsauvik, thousandeyes, datadog — this is the self-hosted NMS an enterprise already runs
Current device statepyats, multivendor-cli, fortinet — they read the device now; this answers what it was over time, and can answer for a device that is unreachable right now
Problems and alertszabbix-problem-review
Availability and inventoryzabbix-availability

Rules

  1. item.get before history.get. Always. There is no shortcut and nothing will catch you.
  2. Never report "no data" without identifying which of the five causes it is.
  3. Say when an answer came from hourly aggregates.
  4. This integration is read-only. There is no write path; do not attempt one.
  5. No per-call audit trail exists for this integration. Say so if someone needs an auditable record.

© automateyournetwork, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in workspace/skills/zabbix-metrics-history of automateyournetwork/netclaw.

Open the folder on GitHubat commit aa90e7d

Compare with similar skills

Zabbix Metrics History next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Zabbix Metrics History compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Zabbix Metrics History this skillautomateyournetwork/netclaw676—~1.8kAutomated safety check: PassApache-2.0
North Star Metricphuryn/pm-skills27k—~1kAutomated safety check: PassMIT
Investigate MetricPostHog/posthog40k—~1.9kAutomated safety check: PassCustom licence
Iterative Retrievalaffaan-m/ECC277k7 repos~1.6kAutomated safety check: PassMIT
Product Metrics Dashboard Designphuryn/pm-skills27k—~1.3kAutomated safety check: PassMIT
CI Metricspytorch/pytorch104k—~1.1kAutomated safety check: PassCustom licence

Similar skills

  • North Star Metric

    phuryn/pm-skills

    Define a North Star Metric and 3-5 supporting input metrics that form a metrics constellation.

    27k GitHub stars~1k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

  • Investigate Metric

    PostHog/posthog

    Official

    Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations queries.

    40k GitHub stars~1.9k tokensUpdated today
    Product & Project ManagementAuto-check passed

  • Iterative Retrieval

    affaan-m/ECC

    Pattern for progressively refining context retrieval to solve the subagent context problem.

    277k GitHub starsUsed in 7 repos~1.6k tokens
    Agent WorkflowsAuto-check passed

  • Product Metrics Dashboard Design

    phuryn/pm-skills

    Designs a product metrics dashboard: a North Star and input metrics, a definition table with data sources, chart types and alert thresholds, and a screen layout.

    27k GitHub stars~1.3k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

  • CI Metrics

    pytorch/pytorch

    Query PyTorch CI, GitHub Actions, HUD, Grafana, and infrastructure metrics.

    104k GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Startup Metrics Framework

    wshobson/agents

    Track, calculate, and optimize key performance metrics for SaaS, marketplace, consumer, and B2B startups from seed through Series A, including unit economics, growth efficiency, and cash management.

    40k GitHub stars~2.5k tokensUpdated 6 days ago
    Business, Finance & HRAuto-check passed

More from automateyournetwork/netclaw

All 120 skills in this repo

  • EVE-NG Lab Topology Design

    automateyournetwork/netclaw

    Entry point for designing EVE-NG network labs: classifies the request, gathers missing requirements, proposes options and validates the resulting topology.

    677 GitHub stars~612 tokensUpdated today
    Auto-check passed

  • ACI Policy Change Deployment

    automateyournetwork/netclaw

    Deploys Cisco ACI policy changes only behind an approved ServiceNow Change Request, capturing pre and post-change fault baselines and rolling back automatically on a fault delta.

    677 GitHub stars~4.2k tokensUpdated today
    Auto-check passed

  • Cisco ACI Fabric Health Audit

    automateyournetwork/netclaw

    Runs a phased health audit of a Cisco ACI fabric through MCP tools: node status, links, tenant and policy review, faults and endpoint learning.

    677 GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • Anta Validation

    automateyournetwork/netclaw

    Validate Arista EOS network state against ANTA's pre-built 208-test catalogue, with structured pass/fail verdicts.

    677 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Arista Cvp

    automateyournetwork/netclaw

    Arista CloudVision Portal (CVP) automation via REST API — device inventory, events, connectivity monitoring, tag management (4 tools).

    677 GitHub stars~2.2k tokensUpdated today
    Auto-check: notes

  • AWS Cloud Monitoring

    automateyournetwork/netclaw

    AWS CloudWatch monitoring — metrics, alarms, log queries, VPC flow log analysis, network performance.

    677 GitHub stars~1k tokensUpdated today
    Auto-check passed

Questions about Zabbix Metrics History

What does Zabbix Metrics History do?

Retrieve polled metric history from Zabbix — interface utilization, counters and any collected item — over any time window, correctly routed between raw history and hourly trends. Zabbix Metrics History is an agent skill from automateyournetwork/netclaw. Retrieve polled metric history from Zabbix — interface utilization, counters and any collected item — over any time window, correctly routed between raw history and hourly trends.

When should I use Zabbix Metrics History?

Zabbix Metrics History fits situations like: someone asks what something WAS doing over time; from Zabbix specifically: is this normal; what did this interface do overnight; was it like this last Tuesday.

How do I install Zabbix Metrics History in Claude Code?

Run `npx skills add automateyournetwork/netclaw --skill zabbix-metrics-history -a claude-code`. Or copy the skill folder (workspace/skills/zabbix-metrics-history in automateyournetwork/netclaw) into .claude/skills/zabbix-metrics-history in your project. Claude Code loads it when a task matches its description.

How do I install Zabbix Metrics History in Codex?

Run `npx skills add automateyournetwork/netclaw --skill zabbix-metrics-history -a codex`. Or copy the skill folder (workspace/skills/zabbix-metrics-history in automateyournetwork/netclaw) into .agents/skills/zabbix-metrics-history in your project. Codex loads it when a task matches its description.

Can I use Zabbix Metrics History in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add automateyournetwork/netclaw --skill zabbix-metrics-history -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/zabbix-metrics-history, .gemini/skills/zabbix-metrics-history, .github/skills/zabbix-metrics-history and .opencode/skills/zabbix-metrics-history in your project.

What does Zabbix Metrics History need to run?

SKILL.md names no scripts, command-line tools or credentials: Zabbix Metrics History is instructions for the agent only. Our summary lists: A credential in ZABBIX_TOKEN.

Does Zabbix Metrics History access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Zabbix Metrics History safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Zabbix Metrics History use?

Zabbix Metrics History is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Zabbix Metrics History use?

About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Zabbix Metrics History?

Skills that share tags, products or a category with Zabbix Metrics History: North Star Metric (phuryn/pm-skills, 27k stars), Investigate Metric (PostHog/posthog, 40k stars), Iterative Retrieval (affaan-m/ECC, 277k stars) and Product Metrics Dashboard Design (phuryn/pm-skills, 27k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Zabbix Metrics History?

automateyournetwork (a GitHub user) maintains it in automateyournetwork/netclaw, which has 676 GitHub stars. The repository holds 120 skills in this directory. The repository was last updated on October 9, 2026.

Source: automateyournetwork/netclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.