Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/majiayu000/claude-skill-registry --skill chatgpt명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
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。
SKILL.md 표시 중
SOC 직업 분류 기준
| name | chatgpt |
| description | OpenAI's conversational AI assistant. |
| category | ai |
OpenAI's conversational AI assistant.
curl -sSL https://canifi.com/skills/chatgpt/install.sh | bash
Or manually:
cp -r skills/chatgpt ~/.canifi/skills/
Configure via canifi-env:
# First, ensure canifi-env is installed:
# curl -sSL https://canifi.com/install.sh | bash
canifi-env set OPENAI_API_KEY "your_api_key"
Your credentials, your choice. Canifi LifeOS respects your privacy.
If you prefer not to share credentials with Claude Code:
If you're comfortable sharing credentials, you can store them locally:
canifi-env set SERVICE_EMAIL "your-email"
canifi-env set SERVICE_PASSWORD "your-password"
Note: Credentials stored in canifi-env are only accessible locally on your machine and are never transmitted.
User: "Ask ChatGPT to explain quantum computing"
Assistant: Sends query and returns response
User: "Use the Data Analyst GPT"
Assistant: Engages specialized GPT
User: "Create an image of a sunset"
Assistant: Generates with DALL-E
User: "Have ChatGPT review this code"
Assistant: Runs code analysis
| Error | Cause | Solution |
|---|---|---|
| Auth Failed | Invalid key | Check API key |
| Rate Limited | Too many requests | Wait or upgrade |
| Context Length | Message too long | Reduce input |
| Model Error | Capacity issue | Retry |