本文へ移動
cccskills
無料GitHub で公開

whendone-plus

Automatically notify the user when long-running terminal commands finish (npm test, docker build, git push, etc.). The agent monitors command execution and sends a desktop notification on completion if the command ran longer than threshold (default 10s). Use when user asks to "notify me when done", "desktop notification when command finishes", "alert when done", or "tell me when this completes". Do NOT use for interactive commands (vim, nano, less, htop), commands that always complete in <5s, or streaming commands (tail -f).

インストール方法を見る

含まれるファイル(2)

  • SKILL.md6.6 KB
  • scripts/notify.js973 B

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

WhenDone Plus

Automatically notify when long-running commands complete.

How It Works

  1. User runs a long command (e.g. npm test, docker build, git push)
  2. The agent monitors the command execution time
  3. If the command runs longer than the threshold (default 10s), the agent notifies the user on completion
  4. Exit code is passed through

Workflow

Step 1: Detect long-running command

Identify commands likely to exceed threshold:

  • npm test, npm run test, npx playwright test
  • docker build, docker compose up, docker compose down
  • git push, git pull, git clone
  • pip install, npm install, pnpm install, yarn install
  • cargo build, cargo test, go build, dotnet build
  • Custom scripts, database migrations, data processing pipelines
  • ffmpeg, rsync, scp, large file transfers

Step 2: Monitor execution

Start a background timer when the command begins. Track:

  • Elapsed wall-clock time
  • Peak memory usage (if available)
  • Child process tree (for pipeline awareness)

Step 3: Notify on completion

Basic notification format:

✅ "Command finished: npm test completed in 142s (exit 0)"
❌ "Command finished: docker build failed in 89s (exit 1)"

Include:

  • Command name (first word + key args)
  • Execution time (rounded to seconds)
  • Exit code (success/failure)
  • Optional: memory peak, output file path if redirected

Step 4: Handle edge cases

  • Commands completing under 10s: no notification (too fast to matter)
  • Interactive/TUI commands (vim, nano, htop): skip (user is watching)
  • Piped commands (e.g. npm test | grep error): monitor the pipeline, not the first process
  • Backgrounded commands (&): notify on background process completion
  • Chained commands (;): notify per-segment or in aggregate
  • Commands killed by signal: notify with signal name (e.g. "killed by SIGTERM")

Notification Mechanisms

Windows Toast Notification (PowerShell)

Add-Type -AssemblyName System.Windows.Forms
$balloon = New-Object System.Windows.Forms.NotifyIcon
$balloon.Icon = [System.Drawing.SystemIcons]::Information
$balloon.BalloonTipTitle = "Command Complete"
$balloon.BalloonTipText = "npm test finished in 142s (exit 0)"
$balloon.Visible = $true
$balloon.ShowBalloonTip(5000)
Start-Sleep -Seconds 5
$balloon.Dispose()

Terminal Bell (cross-platform)

echo -e "\a"                         # ASCII bell character
printf '\a'                          # POSIX

BurntToast Module (Windows 10/11)

Import-Module BurntToast
New-BurntToastNotification -Text "Command Complete", "npm test finished in 142s (exit 0)"

macOS Notification

osascript -e 'display notification "npm test finished in 142s" with title "Command Complete"'
terminal-notifier -title "Command Complete" -message "npm test finished in 142s"

Linux Notification (notify-send)

notify-send "Command Complete" "npm test finished in 142s"

Error Handling

ErrorCauseFix
Notification never firesCommand completed under thresholdExpected. Threshold is 10s by default.
Wrong exit code reportedShell pipeline masking failuresUse $PIPESTATUS in bash, $LASTEXITCODE in PowerShell
Notification module missingBurntToast/notify-send not installedFallback to terminal bell or Write-Host
Silent failure on background jobJob detached from monitor processUse Wait-Job in PowerShell, wait in bash
Double notificationParent and child process both fireTrack PID tree, notify only on root process
Desktop notification blockedSystem focus assist or DnD modeFallback to terminal output with colored exit code
Command output lostNotification intercepts stdout/stderrAlways tee or capture output before monitoring

Anti-Patterns

MistakeFix
Notify for every commandOnly if >10s threshold
Breaking pipesEnsure stdout/stderr passthrough
Breaking exit codesPass through original exit code
Notifications for interactive commandsSkip if TUI detected
Notify and then continue workingWait for notification confirmation or user acknowledgment
Assuming notification system is availableAlways have a text-only fallback (Write-Host)
Monitoring subprocess instead of pipelineTrack the entire pipeline PID group

Customization

SettingDefaultDescription
Threshold10sMinimum command duration to trigger notification
Notification styleToasttoast, bell, or both
Include exit codeYesShow pass/fail in notification
Show elapsed timeYesInclude duration in notification text
Fallback on failureBellWhat to do if toast notification fails

Checklist

  • Notification method matches platform (BurntToast on Windows, terminal-notifier on macOS, notify-send on Linux)
  • Threshold duration set appropriately (default 10s — not too short, not too long)
  • Not used for interactive commands (vim, nano, htop, less)
  • Custom message includes the command name and result (success/fail)
  • Fallback: terminal bell or Write-Host if notification fails

Sources

  • Windows Toast API (docs.microsoft.com/en-us/windows/apps/design/shell/tiles-and-notifications)
  • BurntToast PowerShell module (github.com/Windos/BurntToast)
  • notify-send (Linux Desktop Notifications Specification)
  • terminal-notifier (github.com/julienXX/terminal-notifier)
  • macOS osascript display notification (developer.apple.com)
  • POSIX terminal bell (ASCII 0x07)
  • Shell job control (bash manual, PowerShell about_Jobs)

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Apply professional, premium UI/UX design standards when building or styling web interfaces. Use this skill when the user asks to create a website, landing page, web app, dashboard, UI component, or any visual interface — or when they ask to make something look better, more professional, or more beautiful. Covers visual hierarchy, typography, color systems, layout, spacing, motion, dark mode, responsive design, and conversion patterns. Activate even when the user doesn't say "design" — if they're building a web frontend, these standards apply.

日本語の概要は準備中です。原文の説明を表示しています。

EliasOulkadi/shokunin1142026年10月5日 更新

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

日本語の概要は準備中です。原文の説明を表示しています。

EliasOulkadi/shokunin1142026年10月5日 更新

Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

日本語の概要は準備中です。原文の説明を表示しています。

EliasOulkadi/shokunin1142026年10月5日 更新

api-forge

無料

Design REST/GraphQL APIs with OpenAPI 3.1, error handling, pagination, rate limiting, webhooks, and idempotency. Use when user asks to design an API, create endpoints, define REST/GraphQL schema, or generate OpenAPI spec. Do NOT use for database schema design, frontend API integration, or non-HTTP protocols (gRPC, WebSocket, MQTT).

日本語の概要は準備中です。原文の説明を表示しています。

EliasOulkadi/shokunin1142026年10月5日 更新

Implement authentication and authorization with OWASP Top 10 standards, OAuth 2.0 + OIDC, WebAuthn/Passkeys, session management, and RBAC/ABAC. Use when user asks to implement login, signup, authentication, authorization, JWT, OAuth, SSO, passkeys, MFA, or role-based access. Do NOT use for API key management (use api-forge), encryption at rest, or network-level security (firewalls, WAF).

日本語の概要は準備中です。原文の説明を表示しています。

EliasOulkadi/shokunin1142026年10月5日 更新

Generate brand guidelines, design systems with design tokens (W3C format), creative direction (SCAMPER, Design Thinking, TRIZ), and design briefs with scope and success criteria.

日本語の概要は準備中です。原文の説明を表示しています。

EliasOulkadi/shokunin1142026年10月5日 更新

EliasOulkadi のスキルをすべて見る

このスキルの問題を報告する