SKILLEMALL.ai
GitHub ↗ RU Sign in

AC mikrotik-routeros-isp-br

Expert-level management of MikroTik RouterOS devices and VSOL GPON OLTs via SSH or RouterOS API (port 8728/8729) and REST API (port 80/443). Use this skill whenever the user mentions MikroTik, RouterOS, RB, CCR, CRS, hAP, Winbox CLI, /ip route, /interface, /ppp, /queue, firewall rules, OSPF, BGP, VRRP, PPPoE, CGNAT, RADIUS, VLAN, OLT, GPON, ONT, PON port, or any ISP infrastructure task. Also triggers for: "show MikroTik routes", "configure PPPoE on RB4011", "check OLT uptime", "add firewall rule", "backup RouterOS config", "failover script", "notificação de link caído", "alerta Telegram MikroTik", "WhatsApp failover", "Evolution API RouterOS", "netwatch script", "script de failover com WhatsApp", "load balance actions", "conectar na API do MikroTik", "listar interfaces via API", "multi-device mikrotik", "TOOLS.md mikrotik", "netwatch-notify eworm", "backup upload mikrotik", "check-health routeros", "telegram-chat routeros", "dhcp-to-dns mikrotik", "eworm scripts routeros".

ClawHub Agent Skills author: charllesvale v2.0.5 MIT-0 10 files · 1 script body ≈ 2 133 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

IntegrationTelegramWhatsAppInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
94/100
safety, quality, tests
Safety 60%
96
Quality 40%
91
Run on models
none yet
Process rating
C
50/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 4

    ✓ No critical or high findings

    Medium and low: 4
    • low Exfiltration net-credential-use SKILL.md:141
      Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
      curl -u "$MIKROTIK_USER:$MIKROTIK_PASS" \
      security skill
    • low Exfiltration net-credential-use SKILL.md:146
      Credential used in a network call (verify the destination is the intended service) (destination host is a configured variable; documentation of a security skill)
      curl -k -u "$MIKROTIK_USER:$MIKROTIK_PASS" https://$MIKROTIK_HOST/rest/ip/address
      variable hostsecurity skill

    A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "requirements"
    • note frontmatter-key unknown frontmatter key "security"

    Process rating: all ten parameters 50/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 4 mutating operations with no state check
    • 40Consistency. Frontmatter name (mikrotik-routeros-isp-br) differs from the folder (mikrotik-routeros-isp)
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 16 steps
    • 100Execution cost. Instruction body is 2133 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Description length 987: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 23 example trigger phrases
    • +4Structure: 22 headings
    • +3Step-by-step instructions: 16 items
    • +4Has examples (15 code blocks)
    • +4Reference files are cited in the instructions (6 of 6)
    • +3All 2 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: suspicious
    This appears to be a legitimate router-management skill, but it includes risky production-network examples that need manual review before use.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026