majiayu000
majiayu000/claude-skill-registry
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/majiayu000/claude-skill-registry --skill perplexity-deep-search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。
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
Analyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.
回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据，按主题分组汇总"我都做了什么"，并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。
基于 SOC 职业分类
正在显示 SKILL.md
| name | perplexity-deep-search |
| version | 1.0.0 |
| description | Deep research using Perplexity AI. Comprehensive reports with citations and analysis. |
| metadata | {"openclaw":{"emoji":"🔍","category":"research"}} |
Deep research using Perplexity AI. Comprehensive reports with citations and analysis.
| Use Case | Example |
|---|---|
| Market research | "Competitive analysis of AI coding assistants" |
| Technology evaluation | "Compare vector databases for production use" |
| Trend analysis | "State of MCP ecosystem 2025" |
| Due diligence | "Company X funding, team, product overview" |
| Learning | "Explain quantum computing to a programmer" |
| Tool | Best For | Depth |
|---|---|---|
| Perplexity | Quick, cited answers | Medium |
| Pokee Deep Research | Comprehensive reports | Deep (25+ min) |
| Web Search | Specific facts | Shallow |
| arXiv Watcher | Academic papers | Deep |
Be specific:
"Compare Supabase vs Firebase for real-time apps in 2025.
Focus on: scalability, pricing, self-hosting options."
Drill deeper:
"What are the specific limitations of Firebase's real-time
sync at 10k+ concurrent users?"
Combine multiple sources:
"Based on the above, which is better for a startup with
< 1000 users planning to scale to 100k?"
Request structured output:
## Summary
2-3 sentence overview
## Key Findings
- Point 1 (with citation)
- Point 2 (with citation)
## Comparison Table
| Criteria | Option A | Option B |
|----------|----------|----------|
## Recommendations
1. Best for X
2. Best for Y
## Sources
- [Title](URL)
{
"name": "weekly-tech-digest",
"schedule": {"kind": "cron", "expr": "0 9 * * 1"},
"payload": {
"kind": "agentTurn",
"message": "Use perplexity to research: 'AI agent frameworks 2025'. Focus on new releases, emerging standards, key players."
},
"sessionTarget": "isolated",
"notify": true
}