skills-managing — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited skills-managing (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Comprehensive guide for creating and managing skills in the Antigravity Skill Engine (ASE), following the Registry V3.1 architecture with domain-based organization and semantic matching.
Skills are organized by domain categories:
.agent/skills/
├── registry.json # V3.1 索引 (唯一真理来源)
│
├── 1-dev/ # 开发域
│ └── {skill-name}/SKILL.md
├── 2-audit/ # 审计域
│ └── {skill-name}/SKILL.md
├── 3-sys/ # 系统域
│ └── {skill-name}/SKILL.md
├── 4-tools/ # 工具域
│ └── {skill-name}/SKILL.md
└── external/ # 外部依赖
└── {skill-name}/SKILL.md{skill-name}/
├── SKILL.md (required) # Main skill content
├── resources/ # Templates, guides, assets
└── scripts/ # Optional executable tooling{
"version": "3.1.0",
"categories": {
"1-dev": "DEV (开发域)",
"2-audit": "AUDIT (审计域)",
"3-sys": "SYS (系统域)",
"4-tools": "TOOLS (工具域)",
"external": "EXTERNAL (外部依赖)"
},
"skills": {
"X.Y": {
"id": "skill-name",
"name": "X.Y Display Name",
"category": "category-id",
"description": "Copied from SKILL.md frontmatter",
"skill_path": ".agent/skills/{category}/{skill-name}/SKILL.md"
}
}
}关键变更 (V3.1): 移除了intent_keywords,仅使用description进行语义匹配。
| Mode | Trigger | Description |
|---|---|---|
| CREATE | create, new, add | Create a new skill from scratch |
| INGEST | import, clone, ingest | Import an existing skill from git |
| HARVEST | harvest, archive, save resource | Archive a reusable resource to a skill |
| Category | Use When |
|---|---|
1-dev | 功能架构、开发规范、会话管理 |
2-audit | 代码审计、调试、测试 |
3-sys | 生态维护、技能管理、文档初始化 |
4-tools | 文档处理、视觉设计 |
external | 公司专属、外部依赖 |
mkdir -p .agent/skills/{category}/{skill-name}/resourcesRequired Frontmatter:
---
name: skill-name
description: Clear description including trigger scenarios. This is used for semantic matching - be descriptive!
---Body Structure:
"X.Y": {
"id": "skill-name",
"name": "X.Y Display Name",
"category": "{category}",
"description": "Copy from SKILL.md frontmatter",
"skill_path": ".agent/skills/{category}/{skill-name}/SKILL.md"
}git clone {repo} .agent/skills/_import.agent/skills/{category}/{skill-name}/registry.json_import directoryWhen reusable resources are identified during task execution (or manually triggered):
{{PLACEHOLDER}} syntaxwrite_to_file .agent/skills/{category}/{skill}/resources/{resource-name}.mdUpdate the skill's SKILL.md Resource Files section with a link to the new resource.
| Principle | Rule |
|---|---|
| 500-Line Rule | SKILL.md 不超过 500 行 |
| Progressive Disclosure | 详细文档放 resources/ |
| Gerund Naming | 使用动名词后缀 (*-ing) |
| Single Source | description 从 SKILL.md 复制到 registry |
description for semantic matchingarchitecting, debugging)Quick Debug:
registry.json?skill_path pointing to correct location?description rich enough for semantic matching?| Topic | File |
|---|---|
| Ingestion Protocol | ingestion-protocol.md |
| Skill Review Checklist | skill-review.md |
| MCP Integration | mcp-integration-guide.md |
Skill Status: COMPLETE ✅ Line Count: < 200 ✅ Registry Version: V3.1 ✅
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.