Formats plugin folders and files according to Claude Code plugin marketplace guidelines
Automatically formats plugin folders to meet Claude Code marketplace standards. Triggers on commands like "format this plugin" to fix directory structures, validate JSON schemas, enforce lowercase-with-hyphens naming, and update documentation files.
/plugin marketplace add ZenterFlow/claude-priority/plugin install plugin-formatter@claude-priorityThis skill inherits all available tools. When active, it can use any tool Claude has access to.
rules.mdschemas/marketplace-schema.jsonschemas/plugin-schema.jsonscripts/README.mdscripts/validate-frontmatter.shscripts/validate-json.shscripts/validate-naming.shtemplates/README.md.templatetemplates/agent.md.templatetemplates/manifest.json.templatetemplates/marketplace.json.templatetemplates/plugin.json.templatetemplates/plugin.md.templatetemplates/skill.md.templateAutomatically format plugin structures, skills, and marketplace files according to Claude Code specifications.
Take a plugin directory and ensure all files, metadata, and documentation conform to Claude Code plugin marketplace standards, including:
When given a plugin folder path:
.claude-plugin/plugin.json (required)agents/ directoryskills/ directoryREADME.md and plugin.md.claude-plugin/plugin.json:
name, version, description, author, keywords, licenseagents and skills pathsplugin.md:
README.md:
skills/ directoryFor each skill in skills/:
Directory name: Convert to lowercase-with-hyphens
skill.md:
name, description, licensemanifest.json (optional):
name, description, version, triggers.claude-plugin/marketplace.json (repository root):
name, owner, description, version, plugins[]name, source, description, version, author, keywords, categoryChart-Correction.md → chart-correction.md)Required Plugin Structure:
plugin-name/
├── .claude-plugin/
│ └── plugin.json
├── agents/
│ └── plugin-name-tutor.md
├── skills/
│ ├── skill-one/
│ │ ├── skill.md (required)
│ │ └── manifest.json (optional)
│ └── skill-two/
│ └── skill.md
├── plugin.md
└── README.md
Required Marketplace Structure:
repository-root/
└── .claude-plugin/
└── marketplace.json
After formatting, provide:
User: "format this plugin"
Skill:
Analyzing plugin at: ./01-chart-basics
Found:
- Plugin: chart-basics v0.1.0
- Agent: chart-basics-tutor.md
- Skills: 8 found
Actions taken:
✅ Renamed Chart-Correction-Decoder/ → chart-correction-decoder/
✅ Updated skill.md frontmatter: name "Chart-Correction-Decoder" → "chart-correction-decoder"
✅ Created missing manifest.json for chart-correction-decoder
✅ Updated README.md skills list (added 5 new skills)
✅ Updated plugin.md version history
✅ Validated plugin.json schema
Summary:
✅ 8 skills formatted
✅ 5 files renamed
✅ 2 documentation files updated
⚠️ 1 optional manifest.json created
Plugin is now compliant with Claude Code marketplace v0.1.1
.claude/skills/plugin-formatter/templates/.claude/skills/plugin-formatter/schemas/.claude/skills/plugin-formatter/rules.mdv1.0.0 - Initial formatter for Claude Code Plugin Marketplace v0.1.1
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.