C
ClineSec/cline-skills
Open-source Agent Skills for Claude Code, Codex, and Cursor
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
- ★ 数取值
- 1 ★ · ClineSec/cline-skills · 取自 GitHub 搜索 API · (2026-11-13 20:00:50 核对)
- 来源明细
- 从该仓库的 GitHub 页面直接读取 · 条目类型:开源项目
- 收录与活跃
- 收录于 2026-11-05 · 最近见到 2026-11-14 · 共见到 10 次 · 被 1 个来源列出
- 评分构成
- 综合分 103 · 1 ★ · 1 个来源 · repo
常见问题(答案都来自我们的记录)
它适合谁 / 用来做什么?
我们把它归在这些标签下: 开源项目。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
仓库
ClineSec/cline-skills;我们收录于 2026-11-05;最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。# Cline Skills
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
Open-source Agent Skills for Claude Code, Codex, and Cursor,
from Cline Technologies. A skill is a packaged set of instructions and helper scripts that an agent
loads when a task calls for it. Install this catalog once, and its skills are available in every
project on your machine.
## Skills
| Skill | What it does |
| agent-config-integrity | Assesses the agent, MCP, hook, and permission config in a repository without executing any of it, and ends in a report a person signs |
| ai-inventory | Finds the AI in a repository and writes it down as a CycloneDX AI-BOM, with a report a person signs |
| init-policy-relay | Connects a repository to a policy repository, so agents sync security guidance at session start and load only what each task needs |
| mcp-preflight | Answers whether it's safe for a team to use an MCP server before it connects, from whatever evidence exists, and ends in a verdict with conditions that a person signs |
| policy-relay-distill | Distills policy documents into that guidance and commits it to a policy repository |
| security-review | Reviews a repository or release for what someone could do to it, from outside the repository and without running it, and ends in a report a person signs |
| skill-creator | Creates or revises portable skills in a catalog |
| threat-model | Builds a threat model by discovery instead of an interview, read-only, with a color-coded architecture diagram and a report a person signs |
| tprm-review | Researches a vendor from the documents you downloaded and the public record, reports where its account doesn't hold together, and ends in a report a person signs |
Each skill has its own usage guide. The two PolicyRelay skills work together, so start with the
PolicyRelay overview.
## Install
You need Git. On macOS, Linux, or WSL:
sh
curl -fsSL https://raw.githubusercontent.com/ClineSec/cline-skills/main/scripts/team-skills.sh \
| sh -s -- install https://github.com/ClineSec/cline-skills.git
On Windows, in PowerShell:
powershell
$installer = Invoke-RestMethod https://raw.githubusercontent.com/ClineSec/cline-skills/main/scripts/team-skills.ps1
& ([scriptblock]::Create($installer)) install https://github.com/ClineSec/cline-skills.git
Review downloaded scripts before running them if your security policy requires it. Then start a new
agent session and ask for what you need, such as "init policy relay". Some skills have their own
requirements, listed in their guides.
from Cline Technologies. A skill is a packaged set of instructions and helper scripts that an agent
loads when a task calls for it. Install this catalog once, and its skills are available in every
project on your machine.
## Skills
| Skill | What it does |
| agent-config-integrity | Assesses the agent, MCP, hook, and permission config in a repository without executing any of it, and ends in a report a person signs |
| ai-inventory | Finds the AI in a repository and writes it down as a CycloneDX AI-BOM, with a report a person signs |
| init-policy-relay | Connects a repository to a policy repository, so agents sync security guidance at session start and load only what each task needs |
| mcp-preflight | Answers whether it's safe for a team to use an MCP server before it connects, from whatever evidence exists, and ends in a verdict with conditions that a person signs |
| policy-relay-distill | Distills policy documents into that guidance and commits it to a policy repository |
| security-review | Reviews a repository or release for what someone could do to it, from outside the repository and without running it, and ends in a report a person signs |
| skill-creator | Creates or revises portable skills in a catalog |
| threat-model | Builds a threat model by discovery instead of an interview, read-only, with a color-coded architecture diagram and a report a person signs |
| tprm-review | Researches a vendor from the documents you downloaded and the public record, reports where its account doesn't hold together, and ends in a report a person signs |
Each skill has its own usage guide. The two PolicyRelay skills work together, so start with the
PolicyRelay overview.
## Install
You need Git. On macOS, Linux, or WSL:
sh
curl -fsSL https://raw.githubusercontent.com/ClineSec/cline-skills/main/scripts/team-skills.sh \
| sh -s -- install https://github.com/ClineSec/cline-skills.git
On Windows, in PowerShell:
powershell
$installer = Invoke-RestMethod https://raw.githubusercontent.com/ClineSec/cline-skills/main/scripts/team-skills.ps1
& ([scriptblock]::Create($installer)) install https://github.com/ClineSec/cline-skills.git
Review downloaded scripts before running them if your security policy requires it. Then start a new
agent session and ask for what you need, such as "init policy relay". Some skills have their own
requirements, listed in their guides.
收录徽章(可选)
想把收录标记放进 README 就复制这行,可选,不影响收录。
[](https://anclum.com/zh/s/clinesec-cline-skills/)
- 来源
- github · https://github.com/ClineSec/cline-skills
- 按领域浏览
- 开源项目
- Traction
- 1 ★
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。