SKILLEMALL.ai
GitHub ↗ RU Sign in

AB hearth

A fast, read-only health-check sweep across every device in a homelab — ping, uptime/load, memory/disk, services, and app health, in 14 seconds with output you can scan in 30. Configuration-driven (~/.hearth/devices.yaml describes the lab; the skill is generic). Use when the user asks "how is the lab?", "server status", "check all servers", "is X up?", "health check", "what's down?", "anything broken?". Supports Linux, macOS, Raspberry Pi, Android (Termux/chroot), and Windows hosts (HTTP-only probe). Honest reporting — devices that can't be probed at L4 (Windows, chroots) are reported as such, never faked green. Read-only — never restarts services, never writes to remote hosts.

ClawHub Agent Skills author: Only 1 Naren v0.1.5 MIT-0 22 files · 5 scripts body ≈ 2 083 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process B 73/100 · Nearly there — weak spots: inputs and preconditions, running it twice

GeneratorData and analyticsInfrastructuretype 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
92/100
safety, quality, tests
Safety 60%
87
Quality 40%
99
Run on models
none yet
Process rating
B
73/100
Nearly there
Inputs and preconditions w 11
0
Running it twice w 4
30
Tools and files w 18
60
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Dangerous commands cmd-shell-rc docs/INSTALL.md:55
      Writes to a shell startup file
      echo 'export PATH="/opt/homebrew/bin:$PATH"' >> ~/.zshrc
    • medium Dangerous commands cmd-autorun-instruction SKILL.md:102
      Instructs the agent to auto-run a script on every session
      - **"why is X down?"** — first run `./scripts/sweep.sh --device <X>` to confirm the failure mode, then suggest investigation paths based on which layer failed (L1 = network, L4 = services, L5 = app).
    • low Risky intent intent-offensive-security docs/TROUBLESHOOTING.md:44
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - name: phone-pentest
    • low Risky intent intent-offensive-security examples/archetypes/linux-nosystemd-chroot.md:19
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)
      - name: phone-pentest
      fixture
    • low Risky intent intent-offensive-security examples/archetypes/linux-nosystemd-chroot.md:41
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)
      === 192.0.2.50 phone-pentest ===
      fixture

    Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 73/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 3 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 100Steps. 35 steps
    • 100When it triggers. States when to use and when not to
    • 100Failures and branches. 8 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2083 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 13 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (9 tags): a typed call is more reliable

    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)
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 7 example trigger phrases
    • +3Description length 686: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 35 items
    • +3Output format is stated explicitly
    • +4Has examples (3 code blocks)
    • +4Reference files are cited in the instructions (2 of 5)
    • +3All 2 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 99.

    External checks

    ClawHub: suspicious
    This homelab health-check skill is mostly coherent, but it deserves Review because it can run configured shell commands on devices and weakens SSH/credential safety while presenting itself as guaranteed read-only.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026