src-link
Skill1 starsChanged 8 months agoMITView on GitHub
类型: 通用工具 描述: 统一管理 src/projects 下各项目到 ~/.claude/skills 的软链接 版本: v1.0.0 位置: ~/src/projects/tools/user-scripts/skills/src-link/
In this repository40 other files it gives its agents.
- ralphSkill
- prdSkill
- th-prd-driven-dev-workflowSkill
- th-ralph-evoSkill
- th-ralphSkill
- th-workflow-decision-engineSkill
- agent-factorySkill
- arch-linuxSkill
- article-writingSkill
- browser-useSkill
- code-reviewSkill
- decision-recordSkill
- githubSkill
- knowledge-hubSkill
- long-doc-generatorSkill
- long-running-agentSkill
- th-model-compare-searchSkill
- newapi-cliSkill
- orchestratorSkill
- playwright-cliSkill
- prd-evolutionSkill
- prd-to-codeSkill
- prompt-expertSkill
- prompt-optimizerSkill
- puppeteer-cliSkill
- ralphSkill
- prdSkill
- requirement-to-prdSkill
- site-analyzerSkill
- skill-creatorSkill
- skill-stocktakeSkill
- th-bug-analyzerSkill
- th-deep-coder2Skill
- th-deep-coderSkill
- th-enterprise-test-agentSkill
- gitnexus-assistantSkill
- th-ralph-evoSkill
- th-ralphSkill
- unified-searchSkill
- web-fetchSkill
The file
Files
Src-Link Skill 管理
类型: 通用工具 描述: 统一管理 src/projects 下各项目到 ~/.claude/skills 的软链接 版本: v1.0.0 位置:
~/src/projects/tools/user-scripts/skills/src-link/
快速开始
# 查看所有链接
src-link list
# 查看源目录中的 skill
src-link sources
# 检查指定 skill 状态
src-link check <skill-name>
# 创建单个链接
src-link create <skill-name>
# 批量创建所有未链接的 skill
src-link create-all命令参考
| 命令 | 说明 |
list | 列出 ~/.claude/skills 下所有软链接 |
sources | 扫描并列出所有源目录中的 skill |
check <name> | 检查指定 skill 的链接状态 |
create <name> | 为指定 skill 创建软链接 |
create-all | 为所有未链接的 skill 创建软链接 |
remove <name> | 移除指定 skill 的软链接 |
fix | 自动修复断裂的链接 |
search <keyword> | 搜索 skill |
工作原理
- 自动扫描源目录:
~/src/projects/tools/user-scripts/skills~/src/projects/ai/skills/skills~/src/projects/*/skills
- 识别有效 skill: 必须包含
SKILL.md文件 - 创建软链接: 从源目录链接到
~/.claude/skills/
规则
- 必须使用
src-link工具创建软链接 - 修改源目录文件后，软链接自动同步
- 禁止在
~/.claude/skills/下直接创建普通目录 - 禁止修改
~/.claude/skills/下的文件
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.