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 ai-status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 | ai-status |
| description | Check your AI model configuration - see what's set up, current model, credits remaining |
Quick status check for AI model configuration. Shows:
/ai-statusRun the test script silently:
bash ~/Claudesidian/System/scripts/test-ai-connections.sh 2>/dev/null
Also check:
System/user-profile.yaml for AI settings**Your AI Configuration**
| Mode | Status | Model |
|------|--------|-------|
| Premium | ✅ Ready | Claude Sonnet |
| Budget Cloud | {{✅ Ready / ❌ Not set up}} | {{Kimi K2.5 / —}} |
| Offline | {{✅ Ready / ❌ Not set up}} | {{Qwen 2.5 14B / —}} |
| Smart Routing | {{✅ Enabled / ❌ Disabled}} | |
**Currently using:** {{current_model}}
{{If OpenRouter configured:}}
**OpenRouter credits:** ${{balance}} remaining
{{If Ollama configured:}}
**Ollama:** {{Running ✅ / Not running ⚠️}}
---
**Quick actions:**
- `/model` — Switch models
- `/ai-setup` — Configure more options
- "Use budget model" — Quick switch for this task
If something isn't working:
**⚠️ Issues detected:**
{{If OpenRouter not working:}}
- Budget cloud: API key may be invalid or no credits
Fix: Check openrouter.ai/credits
{{If Ollama not running:}}
- Offline mode: Ollama isn't running
Fix: Open Ollama app, or run `ollama serve` in Terminal
Need help? Run `/ai-setup` to reconfigure.
**Your AI Configuration**
Currently using **Claude** (premium) only.
Want to save money or work offline? Run `/ai-setup` to configure:
- 💰 Budget cloud (80% cheaper for routine tasks)
- ✈️ Offline mode (works without internet)
**Your AI Configuration**
⚠️ **Currently offline** — Using local model
| Mode | Status |
|------|--------|
| Premium (Claude) | ❌ No internet |
| Budget Cloud | ❌ No internet |
| **Offline** | ✅ Active |
**Using:** Qwen 2.5 14B (local)
When you're back online, I'll automatically have access to Claude again.
Update System/usage_log.md to mark AI status check as used.
Analytics (Silent):
Call track_event with event_name ai_status_checked (no properties).
This only fires if the user has opted into analytics. No action needed if it returns "analytics_disabled".