发现优质的 AI Agent 技能
聚合 Claude Skills、LangChain、AutoGPT 等优质资源,助力开发者快速构建智能应用
IB Command Terms for English B
- **Analyze**: Break down to bring out essential elements - **Comment**: Give judgment based on reasoning - **Examine**: Consider in detail - **Interpret**: Use knowledge to explain meaning
Language Standards
- L.K-12.1: Demonstrate command of grammar and usage - L.K-12.2: Demonstrate command of capitalization, punctuation, spelling
CLI Contract: Image Generation Skill
This document defines the Command Line Interface (CLI) contract and exit-code policy for the image generation skill.
Dashlane CLI
Access your Dashlane vault from the command line. Read-only access to passwords, secure notes, secrets and OTP codes.
Exploration Playbook
> Dynamic investigation procedures for PR review. These commands discover the current state > of the codebase rather than relying on hardcoded file paths or static references. > All discovery uses `grep`, `find`, `ls`, `wc`, and `git` -- never hardcoded file paths.
Tinker Command Center
> **Your $200 Opus session didn't have to happen.** Tinker shows you exactly where every token goes — before the bill arrives.
Shell Security Ultimate
Your agent has root access. Every command it runs is one bad inference away from `rm -rf /` or `curl | bash` from a stranger's repo.
SSH Tunnel
SSH tunneling, port forwarding, and secure remote access. Covers local/remote/dynamic forwards, jump hosts, ProxyCommand, multiplexing, key management, and connection debugging.
SQL Toolkit
Work with relational databases directly from the command line. Covers SQLite, PostgreSQL, and MySQL with patterns for schema design, querying, migrations, indexing, and operations.
Regex Patterns
Practical regular expression cookbook. Patterns for validation, parsing, extraction, and refactoring across JavaScript, Python, Go, and command-line tools.
Emergency Rescue Kit
Step-by-step recovery procedures for the worst moments in a developer's day. Every section follows the same pattern: **diagnose → fix → verify**. Commands are non-destructive by default. Destructive steps are flagged.