用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/jordangaston/claude-plugins --skill notify命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Use when the user needs multi-source research with citation tracking, evidence persistence, and structured report generation. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or questions answerable with 1-2 searches.
Run Charlie Munger's two-track analysis on a decision — first the rational forces that actually govern the outcome, then the psychological biases that may be distorting the judgment. Use this skill whenever the user is making or reviewing a significant decision, asks "am I fooling myself", wants a decision sanity-checked or de-biased, worries they're being manipulated or sold to, or mentions the Munger two-step, two-track analysis, or misjudgment. Especially useful before commitments that are hard to reverse: investments, hires, purchases, partnerships, strategy pivots.
Apply the full Farnam Street latticework of ~100 mental models to analyze a problem or decision. Use this skill whenever the user asks to think through a decision, analyze a problem from multiple angles, stress-test a plan, or explicitly mentions mental models, first principles, inversion, second-order effects, or "how should I think about this". Also trigger for open-ended strategic questions ("should we do X", "what am I missing", "help me reason about this") where structured multi-lens analysis beats a single-frame answer. The skill requires scanning ALL models against the problem, then applying the 3-5 best-fit models deeply.
基于 SOC 职业分类
正在显示 SKILL.md
| name | notify |
| description | Send macOS notifications to the user for Claude Code events |
| version | 1.0.0 |
| command | ${HOME}/.claude/skills/notify/run.sh |
Use this skill to send macOS notifications to the user through Notification Center when tasks complete, errors occur, or user input is needed.
Invoke this skill when:
You must invoke this script in order to send the notification
${HOME}/.claude/skills/notify/run.sh <event-type> [message]
Event types:
complete - Task completed successfullyerror - Task failed or encountered an errorquestion - You need user inputbackground - Background task completedUser says: "Run the test suite and notify me when it's done"
You should invoke when tests finish:
${HOME}/.claude/skills/notify/run.sh complete "Test suite completed: 157 tests passed"
User says: "Deploy to staging and let me know if it fails"
You should invoke if deployment fails:
${HOME}/.claude/skills/notify/run.sh error "Deployment failed: connection timeout"
User says: "Refactor the auth module and ping me if you need my input"
You should invoke when you need clarification:
${HOME}/.claude/skills/notify/run.sh question "Should I use JWT or session tokens for authentication?"
User says: "Start the build in the background and notify me when done"
You should invoke when background build completes:
${HOME}/.claude/skills/notify/run.sh background "Build completed successfully in 2m 34s"
terminal-notifier via Homebrew if not presentterminal-notifier (installed automatically if missing)Check that terminal-notifier is installed:
which terminal-notifier
Verify Notification Center permissions:
If automatic installation of terminal-notifier fails:
Ensure Homebrew is installed:
brew --version
Manually install terminal-notifier:
brew install terminal-notifier
Check for connectivity issues or Homebrew updates:
brew update
brew doctor
Check your macOS sound settings:
The skill executes claude-notifier.sh located in the same directory, which handles: