Skip to content
cccskills
FreePublished on GitHub

task-banner

Set up (or toggle) a macOS desktop banner that appears whenever Claude Code finishes a task, showing a one-line summary of what was done. Use when the user says "notify me when Claude is done", "desktop notification on completion", "set up the task banner", "mute the banner", or "unmute the banner".

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md3.1 KB
  • mac-overlay.js16.0 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

task-banner

Show a large, always-on-top desktop banner when Claude Code finishes a turn — with a one-line summary of what was actually completed. Works even when macOS Notification Center silently drops osascript display notification calls (a common problem: the CLI has no Notification Center registration, so the command exits 0 but nothing shows).

The banner is a borderless Cocoa overlay window drawn by mac-overlay.js (a JXA script adapted from peon-ping), so no notification permissions are needed.

Requirements

  • macOS (the overlay uses Cocoa via JXA / osascript -l JavaScript)
  • Claude Code with hooks support

Setup

  1. Copy mac-overlay.js from this skill directory to ~/.claude/scripts/mac-overlay.js.

  2. Merge a Stop hook into ~/.claude/settings.json (read the file first and preserve existing hooks):

{
  "hooks": {
    "Stop": [
      {
        "matcher": "",
        "hooks": [
          {
            "type": "command",
            "command": "m=$(cat /tmp/claude-banner-msg 2>/dev/null); rm -f /tmp/claude-banner-msg; [ -f ~/.claude/banner.off ] || osascript -l JavaScript ~/.claude/scripts/mac-overlay.js \"${m:-Task done}\" blue \"\" 0 4 2>/dev/null || true",
            "async": true
          }
        ]
      }
    ]
  }
}
  1. To make the banner show what was finished (instead of the generic "Task done"), add this to your global agent instructions file (~/.claude/CLAUDE.md or AGENTS.md):

After finishing each task, write a short summary of what was completed to /tmp/claude-banner-msg (e.g. printf 'Typecheck fixed and committed' > /tmp/claude-banner-msg). Identify the actual task; never use a generic "task done".

The Stop hook displays the message and deletes the file. If the file is absent, it falls back to "Task done".

Toggle (mute / unmute)

The hook checks a sentinel file — no config editing needed:

touch ~/.claude/banner.off   # mute the banner
rm -f ~/.claude/banner.off   # unmute

When the user asks to mute/unmute the banner, run the matching command and report the resulting state.

How it works / notes

  • mac-overlay.js <message> <color> <icon> <slot> <dismiss_seconds> — color is blue/yellow/red, dismiss 0 means persistent-until-click.
  • The hook consumes /tmp/claude-banner-msg even while muted, so no stale summary pops up later when unmuted.
  • On recent macOS the JXA bridge constant NSTextAlignmentCenter evaluates to the legacy AppKit value (2), which the unified runtime treats as right-aligned — the bundled script hardcodes alignment 1 (center) to compensate.
  • /tmp/claude-banner-msg is shared across parallel Claude sessions; if two finish in the same instant one banner may show the other's summary. Use a per-session file path if that ever matters.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Design, plan, and analyze A/B tests with statistical rigor. Use when the user asks about A/B testing, split testing, experiment design, statistical significance, sample size calculation, test duration, multivariate testing, or conversion experiments. Trigger phrases include "A/B test", "split test", "experiment", "statistical significance", "sample size", "test duration", "which version wins", "conversion experiment", "hypothesis test", "variant testing".

The English summary is being prepared. Showing the original description.

OpenClaudia/openclaudia-skills721Updated Oct 21, 2026

Build and manage an affiliate marketing program. Use when the user says "affiliate program", "affiliate marketing", "affiliate partners", "referral commissions", "affiliate network", "partner program", "affiliate tracking", or asks about creating, managing, or growing an affiliate or partner program.

The English summary is being prepared. Showing the original description.

OpenClaudia/openclaudia-skills721Updated Oct 21, 2026

Manages Ahrefs API usage in Python using `ahrefs-python` library. Use when working with SEO / marketing related tasks or with data including backlinks, keywords, domain ratings, organic traffic, site audits, rank tracking, and brand monitoring. Covers `ahrefs-python` usage including AhrefsClient / AsyncAhrefsClient, typed request/response models, error handling, and all API sections.

The English summary is being prepared. Showing the original description.

OpenClaudia/openclaudia-skills721Updated Oct 21, 2026

Generate an AI Citations Report (GEO) for a domain — which AI-search prompts cite the site across Google AI Overview and ChatGPT, plus organic-traffic context and per-article citation coverage. Use when the user asks for an 'AI citations report', 'GEO citations report', or 'which AI prompts cite <domain>'.

The English summary is being prepared. Showing the original description.

OpenClaudia/openclaudia-skills721Updated Oct 21, 2026

Research and enrich B2B leads using the Apollo.io API. Use when the user says "find leads", "prospect research", "company enrichment", "find decision makers", "B2B leads", "lead research", "enrich contacts", "find VP of marketing at", or asks about finding people at specific companies or in specific roles.

The English summary is being prepared. Showing the original description.

OpenClaudia/openclaudia-skills721Updated Oct 21, 2026

Audit a domain's backlink profile using the SemRush API. Use when the user says "audit backlinks", "check my backlinks", "backlink analysis", "link profile", "toxic links", "disavow", "link building opportunities", "referring domains", "anchor text", or asks about a site's link authority.

The English summary is being prepared. Showing the original description.

OpenClaudia/openclaudia-skills721Updated Oct 21, 2026

See all skills by OpenClaudia

Report a problem with this skill