SKILLEMALL.ai
GitHub ↗ RU Sign in

BD home-assistant-hub

Real-time Home Assistant monitoring, alert rules, TTS voice notifications on Echo devices, Telegram delivery, entity inspection. Service calls are HARD-DENIED by default — require explicit safe-domains opt-in.

ClawHub Agent Skills author: vincsta v1.5.1 MIT-0 12 files · 2 scripts body ≈ 3 702 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Real-time Home Assistant monitoring, alert rules, TTS voice notifications on Echo devices, Telegram delivery, entity inspection.

As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureTelegramInfrastructuretype 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
B
88/100
safety, quality, tests
Safety 60%
95
Quality 40%
78
Run on models
none yet
Process rating
D
45/100
Unfinished process
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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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
  • low Dangerous commands cmd-background-process daemon.sh:15
    Starts a background / autostarted process
    disown $NODEPID
  • low Exfiltration exfil-webhook-url scripts/telegram-deliver.js:61
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    const url = `https://api.telegram.org/bot${botToken}/sendMessage`;
    placeholder
  • low Dangerous commands cmd-background-process SKILL.md:66
    Starts a background / autostarted process (quoted — discussed, not commanded)
    The hub runs as background processes (`nohup`, `disown`) that persist beyond your session. `pkill -f "ha-hub.js start"` can match multiple processes. Always verify process state before killing.
    quoted
  • low Dangerous commands cmd-background-process start.sh:8
    Starts a background / autostarted process
    nohup node "$SCRIPT_DIR/scripts/ha-hub.js" start > "$SCRIPT_DIR/logs/hub.log" 2>&1 &
  • low Dangerous commands cmd-background-process start.sh:11
    Starts a background / autostarted process
    disown $HUB_PID

Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 45/100

  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
  • 75Steps. 3 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3702 tokens

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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 209: enough signal without eating the budget
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 3 items
  • +4Has examples (15 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 3 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: suspicious
Review before installing: this is a disclosed Home Assistant integration, but it handles broad home-control credentials and defaults to unencrypted Home Assistant traffic.
LLM: suspicious (high) · 11 Jul 2026