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

by HybridAIOne in HybridAIOne/hybridclaw

Read Zabbix monitoring state, inspect monitored hosts, summarize current or recent problems, and prepare guarded incident-response context without exposing Zabbix credentials.

MITAuto-check passedDevOps & Cloud

Install Zabbix

skills CLI
$ npx skills add HybridAIOne/hybridclaw --skill zabbix -a claude-code

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

GitHub CLI
$ gh skill install HybridAIOne/hybridclaw zabbix --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/HybridAIOne/hybridclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/zabbix .claude/skills/zabbix && 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
GitHub stars
159
Token cost
~2k tokens
SKILL.md length
690 words
Files
2
Skills in repo
72
Repo updated
First seen
Licence
MIT

At a glance

Read Zabbix monitoring state, inspect monitored hosts, summarize current or recent problems, and prepare guarded incident-response context without exposing Zabbix credentials.

  • Works in 3 steps: Browser admin: open the active… → Browser /chat or TUI fallback → Local console fallback
  • Tasks that involve Incident response
  • SKILL.md covers Credential Rules, Command Contract, Filters and Error Interpretation, plus 1 more section
  • Runs JavaScript scripts from its folder; calls node; needs ZABBIX_API_TOKEN and HYBRIDCLAW_GATEWAY_TOKEN

What it does

Zabbix is an agent skill from HybridAIOne/hybridclaw. Read Zabbix monitoring state, inspect monitored hosts, summarize current or recent problems, and prepare guarded incident-response context without exposing Zabbix credentials.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It sits in DevOps & Cloud, covering Incident response. The repository describes itself as: Enterprise-ready self-hosted AI assistant runtime with sandboxed execution, secure credentials, approvals, and memory. The licence is MIT.

When your agent uses it

  • Tasks that involve Incident response

Example prompts

  • “/zabbix”

Requirements

  • A credential in ZABBIX_API_TOKEN
  • A credential in HYBRIDCLAW_GATEWAY_TOKEN

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Browser admin: open the active HybridClaw admin URL ending in /admin/secrets and set
  2. Browser /chat or TUI fallback
  3. Local console fallback

What it can do on your machine

Read from SKILL.md and the folder at commit 8162701. 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

    Ships script files (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

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

  • Network

    Links to these hosts (documentation or services it may open):

    • zabbix.com

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ZABBIX_API_TOKEN
    • HYBRIDCLAW_GATEWAY_TOKEN

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

Context cost

Zabbix loads about 2k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 690 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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 HybridAIOne/hybridclaw at commit 8162701, republished under its MIT licence (© HybridAIOne). 690 words, ~2,009 tokens.

Download SKILL.mdSave it as .claude/skills/zabbix/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
zabbix
description
Read Zabbix monitoring state, inspect monitored hosts, summarize current or recent problems, and prepare guarded incident-response context without exposing Zabbix credentials.
user-invocable
true
requires.bins
node

Zabbix

Use this skill for Zabbix production monitoring reads: API health checks, monitored host inventory, current or recent problems, problem-state triggers by severity, and concise incident summaries that can feed R29 cards. Zabbix tells us what is broken; local or SSH maintenance skills investigate and remediate on the affected host.

This v1 skill is read-only. Do not acknowledge, suppress, close, update, or delete Zabbix objects through this skill. If a later task adds write operations, each write must be amber/red, require an exact operator grant through F8/F14, and include the Zabbix event id and action in the approval text.

Credential Rules

Set or update the API token in this order:

  1. Browser admin: open the active HybridClaw admin URL ending in /admin/secrets and set ZABBIX_API_TOKEN.
  2. Browser /chat or TUI fallback: /secret set ZABBIX_API_TOKEN "<zabbix-api-token>".
  3. Local console fallback:
bash
hybridclaw secret set ZABBIX_API_TOKEN "<zabbix-api-token>"

For live calls, run the helper to build a gateway http_request payload and pass only the emitted httpRequest object to the built-in http_request tool. The helper sets bearerSecretName: "ZABBIX_API_TOKEN" for authenticated Zabbix methods so the gateway injects the bearer token server-side. It never prints Authorization headers, token values, usernames, passwords, or Zabbix session tokens.

When a terminal-side live smoke test is needed, pass --live to the same http-request command. It posts the same httpRequest object to the HybridClaw gateway /api/http/request route and stops after the first Zabbix 401/403 response. Set HYBRIDCLAW_GATEWAY_URL and HYBRIDCLAW_GATEWAY_TOKEN only for gateway access; do not store those as Zabbix credentials.

Do not call Zabbix with curl when the gateway http_request tool is available. Do not ask the user to paste a Zabbix API token, username/password, or session token into chat.

If the operator has a tenant-specific frontend path, pass it with --base-url or set ZABBIX_BASE_URL in the runtime environment. The helper accepts both https://zabbix.example.com/zabbix and https://zabbix.example.com/zabbix/api_jsonrpc.php and normalizes both to the JSON-RPC endpoint. HTTPS is required by default. Use --allow-http only for a trusted local or private Zabbix frontend where plaintext HTTP is an intentional operator choice.

Command Contract

Show helper usage:

bash
node skills/zabbix/zabbix.cjs --help

Build an unauthenticated API smoke-test request:

bash
node skills/zabbix/zabbix.cjs --format json http-request api-version \
  --base-url https://zabbix.example.com/zabbix

List monitored hosts and interfaces:

bash
node skills/zabbix/zabbix.cjs --format json http-request hosts \
  --base-url https://zabbix.example.com/zabbix \
  --monitored-only

Read current or recent problems:

bash
node skills/zabbix/zabbix.cjs --format json http-request problems \
  --base-url https://zabbix.example.com/zabbix \
  --recent \
  --limit 50

Read triggers in problem state:

bash
node skills/zabbix/zabbix.cjs --format json http-request triggers-problem \
  --base-url https://zabbix.example.com/zabbix \
  --limit 50

Run one live gateway-proxied request, with no retry loop:

bash
node skills/zabbix/zabbix.cjs --live --format json http-request problems \
  --base-url https://zabbix.example.com/zabbix \
  --recent \
  --limit 50

The helper prints a wrapper such as { "command": "http-request", "httpRequest": { ... } }. Pass only the httpRequest value to the built-in http_request tool.

Official API references: Zabbix API overview, host.get, problem.get, and trigger.get.

Show full SKILL.md (295 more words)Show less

Filters

Use IDs when filtering by host or host group because Zabbix JSON-RPC read methods filter most reliably on hostids and groupids:

bash
node skills/zabbix/zabbix.cjs --format json http-request problems \
  --base-url https://zabbix.example.com/zabbix \
  --host-id 10084 \
  --group-id 2 \
  --severity high \
  --unacknowledged \
  --unsuppressed \
  --tag service=postgres \
  --time-from 1767225600 \
  --limit 25

Supported read filters:

  • --host-id <id> / --host <id> and --group-id <id> / --host-group <id> can be repeated.
  • --tag <name> or --tag <name=value> can be repeated.
  • --severity <0-5|name> can be repeated or comma-separated.
  • --acknowledged or --unacknowledged for problem reads.
  • --suppressed or --unsuppressed for problem reads.
  • --time-from <unix-seconds> and --time-till <unix-seconds> for problem reads.
  • --recent includes recently resolved problems; omit it for unresolved current problems.

Severity names are not-classified, information, warning, average, high, and disaster.

Error Interpretation

  • Gateway errors saying ZABBIX_API_TOKEN is not set, unavailable, missing, or unresolved mean the active HybridClaw runtime cannot resolve the stored secret. Ask the operator to set it in the same runtime/session and retry once after the runtime can see the secret.
  • Gateway errors saying ZABBIX_API_TOKEN is blocked by secret resolution policy mean the stored secret exists but policy/runtime access blocked the injection path. Report the policy problem instead of asking for the same secret again.
  • Zabbix 401 or 403 responses mean the gateway injected a token but Zabbix rejected it or the token lacks permission. Stop after that first failed live call and report a credential/setup problem; do not retry in a loop.
  • Zabbix JSON-RPC error responses should be reported with the method, code, message, and data. Do not transform them into local remediation steps unless the user asks.
  • Network, timeout, 429, or 5xx responses are upstream or connectivity failures. Report the response and retry only when the user asks.

Incident Summary Guidance

When summarizing Zabbix state, preserve the event id, host, trigger/problem name, severity, acknowledged/suppressed state, age, tags, and any maintenance or acknowledgement context. Keep remediation separate from observation unless another approved maintenance skill has verified the host state.

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

Files

SKILL.md and 1 other file in skills/zabbix of HybridAIOne/hybridclaw.

  • SKILL.md
  • zabbix.cjs

Open the folder on GitHubat commit 8162701

Compare with similar skills

Zabbix 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Zabbix this skillHybridAIOne/hybridclaw159—~2kAutomated safety check: PassMIT
Kubernetes Network Root Cause Analysiskubeshark/kubeshark12k—~5.3kAutomated safety check: PassApache-2.0
UModel Root Cause Analysisalibaba/UnifiedModel415—~1.9kAutomated safety check: PassCustom licence
Learningskortix-ai/suna20k—~1.1kAutomated safety check: PassCustom licence
Nix Config Debugryan4yin/nix-config2.1k—~1.2kAutomated safety check: PassMIT
Oncallpigweed-project/pigweed548—~963Automated safety check: PassApache-2.0

Similar skills

  • Kubernetes Network Root Cause Analysis

    kubeshark/kubeshark

    Investigates past Kubernetes incidents from Kubeshark traffic snapshots: takes captures, dissects API calls, extracts PCAPs and compares traffic over time.

    12k GitHub stars~5.3k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

  • UModel Root Cause Analysis

    alibaba/UnifiedModel

    Investigates a service incident to its root cause by querying a UModel object graph alongside metrics, logs, topology and recent deployments.

    415 GitHub stars~1.9k tokensUpdated 17 days ago
    DevOps & CloudAuto-check passed

  • Learnings

    kortix-ai/suna

    The project's episodic memory: a timestamped ledger of rules paid for with real outages and near-misses, one entry per incident.

    20k GitHub stars~1.1k tokensUpdated today
    DevOps & CloudAuto-check passed

  • Nix Config Debug

    ryan4yin/nix-config

    A skill your agent uses when something here is broken or stops working: an eval or build error, a failed activation, a dead or restarting unit, a mihomo or DNS outage, an unreachable host or MicroVM…

    2.1k GitHub stars~1.2k tokensUpdated today
    DevOps & CloudAuto-check passed

  • Oncall

    pigweed-project/pigweed

    Pigweed oncall rotation runbooks and maintenance workflows (such as rolling CIPD client tools for b/315378787).

    548 GitHub stars~963 tokensUpdated today
    DevOps & CloudAuto-check passed

  • Axiom SRE Investigator

    openclaw/clawhub

    Investigates incidents and production problems with hypothesis-driven debugging, queries Axiom observability data when available, and keeps secrets out of commands and output.

    9.5k GitHub stars~7.1k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

More from HybridAIOne/hybridclaw

All 72 skills in this repo

  • Hermes3000 Writing

    HybridAIOne/hybridclaw

    Use Hermes3000 to plan, draft, revise, save, check consistency, and export long-form manuscripts through the Hermes3000 AI writing portal API.

    159 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Manim Video

    HybridAIOne/hybridclaw

    Plan, script, render, and stitch Manim Community Edition videos in Python.

    159 GitHub stars~4.7k tokensUpdated today
    Auto-check: notes

  • Skill Creator

    HybridAIOne/hybridclaw

    Create and update SKILL.md-based skills with strong trigger metadata, lean docs, and reliable init, validate, package, and publish workflows.

    159 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • XLSX

    HybridAIOne/hybridclaw

    Create, edit, inspect, and analyze .xlsx spreadsheets and Excel workbooks.

    159 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Excalidraw

    HybridAIOne/hybridclaw

    Create and revise editable .excalidraw diagrams as Excalidraw JSON for architecture diagrams, flowcharts, sequence diagrams, concept maps, and other hand-drawn explainers.

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

  • Google Ads

    HybridAIOne/hybridclaw

    Manage Google Ads accounts with safe GAQL reporting, campaign planning, guarded mutations, and gateway-proxied REST API calls.

    159 GitHub stars~4k tokensUpdated today
    Auto-check passed

Categories

Questions about Zabbix

What does Zabbix do?

Read Zabbix monitoring state, inspect monitored hosts, summarize current or recent problems, and prepare guarded incident-response context without exposing Zabbix credentials. Zabbix is an agent skill from HybridAIOne/hybridclaw. Read Zabbix monitoring state, inspect monitored hosts, summarize current or recent problems, and prepare guarded incident-response context without exposing Zabbix credentials.

When should I use Zabbix?

Zabbix fits situations like: tasks that involve Incident response.

How do I install Zabbix in Claude Code?

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

How do I install Zabbix in Codex?

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

Can I use Zabbix 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 HybridAIOne/hybridclaw --skill zabbix -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, .gemini/skills/zabbix, .github/skills/zabbix and .opencode/skills/zabbix in your project.

What does Zabbix need to run?

Going by SKILL.md and its folder, Zabbix needs JavaScript for the scripts in its folder, the command-line tools its instructions call (node) and credentials named ZABBIX_API_TOKEN and HYBRIDCLAW_GATEWAY_TOKEN. Our summary lists: A credential in ZABBIX_API_TOKEN; A credential in HYBRIDCLAW_GATEWAY_TOKEN.

Does Zabbix access the network?

SKILL.md names 1 domain. As links in the text: zabbix.com. This is read from the text; nothing was executed.

Is Zabbix 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 use?

Zabbix is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Zabbix use?

About 2k tokens (SKILL.md is roughly 8k 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?

Skills that share tags, products or a category with Zabbix: Kubernetes Network Root Cause Analysis (kubeshark/kubeshark, 12k stars), UModel Root Cause Analysis (alibaba/UnifiedModel, 415 stars), Learnings (kortix-ai/suna, 20k stars) and Nix Config Debug (ryan4yin/nix-config, 2.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Zabbix?

HybridAIOne (a GitHub organization) maintains it in HybridAIOne/hybridclaw, which has 159 GitHub stars. The repository holds 72 skills in this directory. The repository was last updated on October 9, 2026.

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