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 agentmods add agents/xerrors/yuxi/skills-managementgit clone --depth 1 https://github.com/xerrors/YuxiWhat 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 | $0.00000 | $0.02308 |
| Opus 5 | $0.00000 | $0.01154 |
| Sonnet 5 | $0.00000 | $0.00462 |
| Haiku 4.5 | $0.00000 | $0.00231 |
Grade A, and why
skills-management 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 yesterday.
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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
管理 Skills
Skill 是一个可复用的能力包,通常包含一个 SKILL.md、提示词、参考资料和可选脚本。智能体先看到 Skill 的描述,再按需要读取 SKILL.md;Skill 声明的工具和 MCP 依赖会随激活状态加入模型请求。
什么时候用 Skill
把一类稳定、可复用的工作方式放进 Skill,例如文档处理、研究流程、报表生成或某个外部服务的操作规范。单次任务要求写在对话中;需要跨对话复用的规则和资料再考虑 Skill 或用户工作区文件。
Skill 保存在哪里
| 来源 | 位置和事实 | 谁可以安装/管理 |
|---|---|---|
| 内置 | 随代码发布,启动时同步索引 | 管理员可以启用/停用,不能删除或直接编辑 |
| 共享上传/远程 | Skill 持久目录 + PostgreSQL 索引 | 管理员按共享范围管理 |
| 个人 | 当前用户 UserWorkspace 的 agents/skills/<slug> |
当前用户;不创建共享 Skill 数据库记录 |
运行时路径是:
- 共享和内置 Skill:
/home/gem/skills/<slug>/,对 Agent 只读; - 个人 Skill:
/home/gem/user-data/agents/skills/<slug>/,位于当前用户的 UserWorkspace。
同一用户有个人 Skill 和共享 Skill 使用同一个 slug 时,个人版本覆盖该用户看到的共享版本。删除个人版本后,如果共享版本仍可访问,会恢复共享版本。
创建 Skill
标准目录至少包含根级 SKILL.md:
my-skill/
├── SKILL.md
├── tools/ # 可选脚本
└── prompts/ # 可选提示词或参考资料
SKILL.md 使用 YAML frontmatter:
---
name: 文档整理
slug: document-cleanup
description: 按指定结构整理文档,并保留可核对的来源。
tool_dependencies: []
mcp_dependencies: []
skill_dependencies: []
---
# 文档整理
## 何时使用
说明这个 Skill 解决什么问题,以及什么时候不该使用。
## 操作步骤
写出 Agent 应遵循的步骤、限制和验收方式。
必填字段是 name 和 description。slug 可省略,省略时直接使用 name,因此省略 slug 时 name 本身也必须是小写字母、数字和单个短横线组成的值;中文或带空格的展示名称会校验失败。建议显式填写 slug,把自然语言名称和稳定标识分开。名称和 slug 最多 128 个字符。
依赖字段含义:
| 字段 | 作用 |
|---|---|
tool_dependencies |
需要的内置工具 |
mcp_dependencies |
需要的 MCP 服务器 |
skill_dependencies |
需要先提供说明的其他 Skill |
个人 Skill 只作为用户文件读取,不解析这些平台依赖;需要依赖工具、MCP 或其他 Skill 时,安装为共享 Skill。
安装方式
进入“扩展 → Skills”,可以选择:
- 推荐 Skill:从推荐列表生成安装草稿。
- 上传:上传 ZIP 或单个
SKILL.md,解析后生成草稿。 - 远程安装:从 GitHub 仓库、ModelScope Skill 或合集拉取一个或多个 Skill。
- 在线编辑:编辑已有且有管理权限的共享 Skill 文件和依赖。
- Agent 内安装:主智能体使用
install_skill把 Skill 安装到当前用户的个人来源;子智能体不能使用该工具。
上传和远程安装都先解析为草稿,再选择个人或共享位置并确认。确认前可以检查名称、说明、文件和依赖;取消草稿不会写入正式 Skill。
远程来源限制
管理员在“设置 → 基本设置 → Skill 配置 → 远程来源白名单”中维护 remote_skill_source_policy.allowed_hosts。默认允许 github.com 和 modelscope.cn;主机名必须精确匹配,保存空列表会关闭远程安装。
示例来源:
anthropics/skills
https://github.com/anthropics/skills
https://modelscope.cn/skills/@anthropics/pdf
https://modelscope.cn/collections/MiniMax/MiniMax-Office-skills
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.
- yesterday First seen · 155 lines · 0 tokens per session scan A 5cb0dd437dd8
skills-management is an agent published in the GitHub repository xerrors/Yuxi (6,591 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,308 tokens. 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 agents, from other repositories
txtify-qa
QA gatekeeper for Txtify. Use to run the full verification ladder on the current tree and report evidence — before merging, releasing, or when asked "does everything still work?".
agents
Agent 模块是系统的执行引擎,基于 LangGraph StateGraph 实现单个 Agent 的完整执行生命周期管理。.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
2026-04-20-relay-handoff
Demo Agent Ada found that Relay parser failures were caused by missing fenced-code terminators in synthetic notes.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.