SKILLEMALL.ai
GitHub ↗ RU Sign in

AC Agent Notify

Cross-platform notification sound and taskbar flash for AI coding agents (Claude Code, OpenClaw, Codex, Kiro, Cursor, etc.). Plays alert sounds and visual notifications when the agent needs confirmation or completes tasks. Auto-detects the agent environment and configures hooks accordingly. Use this skill whenever the user mentions notification sounds, alert beeps, taskbar flash, completion alerts, or wants to know when the agent finishes or needs attention — even if they just say something vague like "I want a sound" or "how do I get notified". Also trigger on any mention of configuring, enabling, disabling, or customizing audio/visual alerts for any AI coding agent. Works on Windows, macOS, and Linux.

ClawHub Agent Skills author: Miluer v0.1.0 MIT-0 6 files · 2 scripts body ≈ 2 762 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

AnalyzerAI and agentsSoftware developmenttype 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
91/100
safety, quality, tests
Safety 60%
93
Quality 40%
87
Run on models
none yet
Process rating
C
55/100
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

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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Dangerous commands cmd-execpolicy-bypass skill.md:327
      Runs PowerShell with execution policy bypassed
      powershell.exe -ExecutionPolicy Bypass -File "$AGENT_HOME/notify.ps1" -Type confirm -ConfigPath "$AGENT_HOME/notify-config.json"
    • low Dangerous commands cmd-execpolicy-bypass skill.md:267
      Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)
      "command": "powershell.exe -ExecutionPolicy Bypass -File \"$AGENT_HOME/notify.ps1\" -Type confirm -ConfigPath \"$AGENT_HOME/notify-config.json\""
      quoted
    • low Dangerous commands cmd-execpolicy-bypass skill.md:278
      Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)
      "command": "powershell.exe -ExecutionPolicy Bypass -File \"$AGENT_HOME/notify.ps1\" -Type done -ConfigPath \"$AGENT_HOME/notify-config.json\""
      quoted

    Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
    • note frontmatter-key unknown frontmatter key "triggers"

    Process rating: all ten parameters 55/100

    • 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. 6 mutating operations with no state check
    • 40Consistency. Frontmatter name (Agent Notify) differs from the folder (agent-notify)
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 18 steps
    • 100Failures and branches. 13 branches, has a failure section
    • 100Execution cost. Instruction body is 2762 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

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +5Description quotes 2 example trigger phrases
    • +3Description length 712: enough signal without eating the budget
    • +4Structure: 17 headings
    • +3Step-by-step instructions: 18 items
    • +4Has examples (22 code blocks)
    • +3All 2 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: clean
    This skill is a local notification setup helper whose file changes and hooks are disclosed and aligned with its purpose, though users should review its broad trigger words and incomplete Windows artifact before installing.
    LLM: benign (high) · VirusTotal: · 29 May 2026