Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add liyecom/liye-ai --skill skill-creatorgit clone --depth 1 https://github.com/liyecom/liye-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/liyecom/liye-ai/skill-creator)<a href="https://agentmods.dev/skills/liyecom/liye-ai/skill-creator"><img src="https://agentmods.dev/badge/skills/liyecom/liye-ai/skill-creator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/liyecom/liye-ai/skill-creator"><img src="https://agentmods.dev/badge/skills/liyecom/liye-ai/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00011 | $0.01266 |
| Opus 5 | $0.00005 | $0.00633 |
| Sonnet 5 | $0.00002 | $0.00253 |
| Haiku 4.5 | $0.00001 | $0.00127 |
Grade A, and why
skill-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
来源: ComposioHQ/awesome-claude-skills 适配: LiYe OS 三层架构
提供创建 Claude Skills 的完整指导，包括专业知识封装、工作流设计、工具集成等。
When to Use This Skill
当需要创建新的 Claude 技能时：
- 设计技能结构和范围
- 编写 SKILL.md 规范文件
- 组织脚本和模板
- 遵循最佳实践
- 发布和维护技能
Core Capabilities
1. 技能结构设计
标准目录结构：
skill-name/
├── SKILL.md # 必须：技能定义文件
├── scripts/ # 可选：辅助脚本
├── templates/ # 可选：文档模板
└── references/ # 可选：参考资料
2. SKILL.md 编写规范
必须包含的 Frontmatter：
---
name: skill-name
description: 清晰描述技能功能
domain: 所属域
version: 1.0.0
status: active | draft | deprecated
---
必须包含的章节：
- When to Use This Skill: 明确使用场景
- Core Capabilities: 核心能力列表
- Usage Examples: 真实使用示例
- Dependencies: 依赖项说明
3. LiYe OS 三层适配
在 LiYe OS 中创建技能需要考虑三层架构：
L1 方法论层 (docs/methodology/):
# skill_definition.md - 10 模块结构
1. Skill Identity
2. Capability Model
3. Mental Models
4. Methods & SOPs
5. Execution Protocols
6. Output Structure
7. Templates
8. Tools Access
9. Evaluation
10. Evolution
L2 可执行层 (src/skill/atomic/):
// index.ts
export const skill: Skill = {
id: 'skill-name',
name: 'Skill Name',
execute: async (input) => { ... }
};
// spec.yaml
id: skill-name
type: atomic
input: { ... }
output: { ... }
L3 指令层 (.claude/skills/):
# SKILL.md - 简洁的使用指导
针对 Claude 的操作指令
4. 最佳实践
- 单一职责: 每个技能专注一个明确目标
- 清晰边界: 明确说明何时使用/不使用
- 丰富示例: 提供真实场景的使用案例
- 版本管理: 使用 SemVer 版本号
- 持续演进: 维护 evolution_log.md
5. 发布流程
- 在 99_Incubator 开发和测试
- 完成所有必需文件
- 通过验证清单
- 迁移到正式域
- 更新索引文件
Usage Examples
示例 1: 创建数据分析技能
用户: 帮我创建一个 Amazon 广告分析技能
Claude: [使用 skill-creator 技能设计结构、生成模板文件]
示例 2: 从文档生成技能
用户: 把这个 API 文档转换成 Claude 技能
Claude: [使用 skill-creator 技能提取关键信息、生成 SKILL.md]
示例 3: 评审现有技能
用户: 检查这个技能是否符合规范
Claude: [使用 skill-creator 技能对照最佳实践进行评审]
Dependencies
无外部依赖，纯知识型技能。
LiYe OS Integration
业务域引用
此技能被以下业务域引用：
- 99_Incubator: 技能孵化（主域）
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 180 lines · 11 tokens per session scan A 784a6987f3c2
skill-creator is a skill published in the GitHub repository liyecom/liye-ai (33 stars, last pushed 3d ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,266 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
antigravity-skill-orchestrator
A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.
torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
pentest-playbook
7-phase pentest pipeline from passive recon to exploitation.
recon-playbook
Use when starting or restructuring an authorized external web and API assessment.