C
ClineSec/cline-skills
Open-source Agent Skills for Claude Code, Codex, and Cursor
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
- Star count
- 1 ★ · ClineSec/cline-skills · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-11-05 · last seen 2026-11-14 · seen 10× · listed by 1 sources
- Score
- score 103 · 1 ★ · 1 sources · repo
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: 开源项目. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
ClineSec/cline-skills;first catalogued 2026-11-05;last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.# 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.
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/clinesec-cline-skills/)
- Source
- github · https://github.com/ClineSec/cline-skills
- Browse by field
- Open source
- Traction
- 1 ★
- added
- today
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.