一键导入
contributing
Use when contributing new skills to the skill-lib repository, installing skills locally, or verifying skill compliance with repository standards
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。
菜单
Use when contributing new skills to the skill-lib repository, installing skills locally, or verifying skill compliance with repository standards
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。
基于 SOC 职业分类
| name | contributing |
| description | Use when contributing new skills to the skill-lib repository, installing skills locally, or verifying skill compliance with repository standards |
Guidelines for installing skills and contributing new ones to this repository.
Skill-Lib is a curated collection of reusable AI Agent Skills. Each skill follows the writing-skills standard with standardized frontmatter, structure, and content guidelines.
| Action | Command / Step |
|---|---|
| Install all skills | git clone https://github.com/Dqz00116/skill-lib.git then copy directories |
| Install single skill | Download skill-name/SKILL.md to ~/workspace/skills/skill-name/ |
| Add new skill | Create skill-name/SKILL.md following standards below |
| Update index | python scripts/generate-summary.py --write |
git clone https://github.com/Dqz00116/skill-lib.git /tmp/skill-lib
mkdir -p ~/workspace/skills
cp -r /tmp/skill-lib/*/ ~/workspace/skills/
rm -rf /tmp/skill-lib
mkdir -p ~/workspace/skills/code-analysis
curl -o ~/workspace/skills/code-analysis/SKILL.md \
https://raw.githubusercontent.com/Dqz00116/skill-lib/main/code-analysis/SKILL.md
Each skill must contain:
skill-name/
└── SKILL.md # Required
Optional: README.md, templates/, examples/, scripts/.
| Item | Format | Example |
|---|---|---|
| Directory name | lowercase + hyphens | code-analysis |
SKILL.md filename | uppercase | SKILL.md |
name field | matches directory | code-analysis |
description | starts with Use when... | Use when analyzing unfamiliar code |
Required frontmatter:
---
name: skill-name
description: Use when [triggering conditions]
---
Required sections:
## Overview — 1-2 sentence summary## When to Use — triggering conditions and anti-casesRecommended sections:
## Quick Reference — tables for scanning## Common Mistakes — what goes wrong and fixesMust sanitize:
skill-name/SKILL.md following standardspython scripts/generate-summary.py --write to update index| Mistake | Fix |
|---|---|
Missing ## Overview | Add 1-2 sentence summary after title |
description describes workflow | Rewrite to start with Use when... |
| Directory name uses camelCase | Use lowercase + hyphens |
| Specific paths in examples | Replace with generic placeholders |
| Forgetting to update index | Run generate-summary.py --write |
Use when the current Agent LLM cannot process images directly and visual analysis is needed — bridges images through KimiCode CLI print mode to a multimodal Kimi model for text description
Use when building HUDs, menus, inventory screens, settings panels, or any widget-based interface in Unreal Engine 5. Also use when connecting C++ logic to UMG Blueprint visuals, handling gamepad or keyboard focus navigation, managing UI state, creating widget animations, or troubleshooting UMG performance issues like frame drops, hitches, or widget memory leaks.
Use when working in a DevFlow project with .devflow/ directory and gate-based step-by-step workflows
Use when analyzing unfamiliar code modules, understanding system architecture, or preparing for refactoring
Use when implementing new modules from design documents, adding features to existing code, or generating structured implementations
Use when recording work sessions, tracking decisions and outcomes, or documenting lessons learned