plugin-structure

This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.

1.96x

Quality

—

Does it follow best practices?

Impact

100%

1.96x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete templates and directory layouts, but it is verbose and largely monolithic, underusing its own reference files. Progressive disclosure and workflow clarity are the main weak spots.

Suggestions

Tighten or relocate the Best Practices, Common Patterns, and Troubleshooting sections into the existing reference files, keeping SKILL.md as a lean overview that points to them.

Link to the specific reference files inline at the relevant sections (e.g. manifest-reference.md in the Plugin Manifest section, component-patterns.md in the Component Organization section) instead of a single generic pointer at the end, and remove the reference to the non-existent `examples/` directory.

Add an explicit step-by-step plugin scaffolding workflow with validation checkpoints (e.g. verify plugin.json location in .claude-plugin/, confirm component directories are at plugin root, validate auto-discovery) so the creation process is sequenced rather than implied.

Dimension	Reasoning	Score
Conciseness	The body is well-structured and substantive, but lengthy Best Practices, Common Patterns, and Troubleshooting sections add generic guidance (e.g. "Use descriptive names that indicate purpose", "Avoid: utils/, misc.md") that could be tightened or moved to reference files, fitting the mostly-efficient-but-could-be-tightened anchor.	2 / 3
Actionability	Provides concrete directory trees, copy-paste-ready JSON manifest blocks, and specific file-format examples (commands/agents markdown, hooks.json, .mcp.json), giving fully executable, specific guidance.	3 / 3
Workflow Clarity	The content is logically organized (structure, manifest, components, naming, discovery) but is a reference document rather than a sequenced creation workflow; there are no explicit validation checkpoints or fix-retry feedback loops for building a plugin, matching the steps-present-but-checkpoints-missing anchor.	2 / 3
Progressive Disclosure	Two reference files exist (component-patterns.md, manifest-reference.md) but are only generically signaled at the very end ("see files in `references/` and `examples/` directories") rather than linked inline at the relevant sections, the detailed manifest/component content that should be split is inline, and the cited `examples/` directory does not exist.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and complete, clearly answering both what the skill does and when to use it in third-person voice. It is somewhat verbose but every quoted trigger earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as "create a plugin", "scaffold a plugin", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", and "configure auto-discovery", matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	The explicit "This skill should be used when the user asks to..." clause states both what the skill does and when to use it, satisfying the anchor requiring clear what-and-when with explicit triggers.	3 / 3
Trigger Term Quality	Provides good coverage of natural phrases a user would actually say, including quoted terms like "create a plugin", "scaffold a plugin", "understand plugin structure", and "add commands/agents/skills/hooks".	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Claude Code plugin structure and manifest configuration) with distinct, specific triggers unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anthropics/claude-plugins-official
Commit: 30a213f

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.