SumSec-Skills / plugin-dev
CLAUDE.md8 starsChanged 18 days agoApache-2.0View on GitHub
Claude Code 插件开发工具箱，覆盖从设计到验证的完整链路。 组件通过 sync-skills 从 claude-plugins-official/plugins/plugin-dev submodule 同步，映射表见 .claude/skills/sync-skills/scripts/skill-map.json。
In this repository8 other files it gives its agents.
- agents-dev/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- dev-tools/CLAUDE.mdCLAUDE.md
- semantic-linter/CLAUDE.mdCLAUDE.md
- taste-skill/CLAUDE.mdCLAUDE.md
- writing-zh/CLAUDE.mdCLAUDE.md
- .cursor/rules/sumsec-skills-repo.mdcCursor rule
- sync-skillsSkill
The file
Files
Plugin Dev
Claude Code 插件开发工具箱，覆盖从设计到验证的完整链路。
技能 / Agent / 命令清单
| 类型 | 名称 | 文件 | 说明 |
| Command | /plugin-dev:create-plugin | commands/create-plugin.md | 引导式 8 阶段插件创建工作流 |
| Skill | agent-development | skills/agent-development/SKILL.md | 创建自治 Agent，含 AI 辅助生成 |
| Skill | command-development | skills/command-development/SKILL.md | 编写带 frontmatter / 参数的 Slash 命令 |
| Skill | hook-development | skills/hook-development/SKILL.md | 事件驱动自动化与 Hook API |
| Skill | mcp-integration | skills/mcp-integration/SKILL.md | Model Context Protocol 服务器集成 |
| Skill | plugin-structure | skills/plugin-structure/SKILL.md | 插件目录与 manifest 组织 |
| Skill | plugin-settings | skills/plugin-settings/SKILL.md | 使用 .claude/plugin-name.local.md 配置模式 |
| Skill | skill-development | skills/skill-development/SKILL.md | 渐进式披露与强触发的 Skill 编写指南 |
| Agent | agent-creator | agents/agent-creator.md | AI 辅助生成 Agent 配置 |
| Agent | plugin-validator | agents/plugin-validator.md | 校验插件结构与 manifest |
| Agent | skill-reviewer | agents/skill-reviewer.md | 审查 Skill 描述、触发词与渐进披露 |
安装
cc --plugin-dir plugin-dev验证
- 修改插件结构或组件清单后，检查
plugin-dev/.claude-plugin/plugin.json与实际commands/、skills/、agents/路径一致。 - 同步组件时同时检查
.claude/skills/sync-skills/scripts/skill-map.json，不要只改复制后的目标目录。 - 提交前用
git diff --stat plugin-dev .claude/skills/sync-skills/scripts/skill-map.json确认同步范围。
来源
组件通过 sync-skills 从 claude-plugins-official/plugins/plugin-dev submodule 同步，映射表见 .claude/skills/sync-skills/scripts/skill-map.json。
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.