CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

63

1.96x
Quality

43%

Does it follow best practices?

Impact

100%

1.96x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/plugin-dev/skills/plugin-structure/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

72%

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 excels at trigger term coverage and distinctiveness, providing extensive natural language phrases that would help Claude match this skill accurately. However, it is structurally imbalanced — it reads entirely as a 'Use when...' clause without a preceding 'what this does' statement describing the skill's concrete capabilities and outputs. Adding a clear capability summary would significantly improve it.

Suggestions

Add a leading capability statement before the trigger clause, e.g., 'Scaffolds Claude Code plugins, generates plugin.json manifests, organizes components (commands, agents, skills, hooks), and sets up directory structures following best practices.'

Restructure to separate 'what' from 'when': start with concrete actions the skill performs, then follow with the existing 'Use when...' trigger list.

DimensionReasoningScore

Specificity

The description names the domain (Claude Code plugins) and references several actions like 'create a plugin', 'scaffold a plugin', 'set up plugin.json', 'add commands/agents/skills/hooks', but these are embedded in trigger phrases rather than stated as concrete capabilities the skill performs. It lacks a clear 'what this does' statement listing specific actions.

2 / 3

Completeness

The description is essentially all 'when' (trigger conditions) but lacks a clear 'what does this do' statement. There is no explicit description of the skill's capabilities or outputs — it only lists when it should be triggered. The 'what' is only implied through the trigger phrases.

2 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would say: 'create a plugin', 'scaffold a plugin', 'plugin structure', 'plugin.json', 'auto-discovery', 'commands/agents/skills/hooks', 'plugin directory layout', 'manifest configuration'. These are highly natural phrases a user would use.

3 / 3

Distinctiveness Conflict Risk

The description is highly specific to Claude Code plugin architecture, with distinct terms like 'plugin.json', '${CLAUDE_PLUGIN_ROOT}', 'auto-discovery', and 'Claude Code plugin architecture'. This creates a very clear niche unlikely to conflict with other skills.

3 / 3

Total

10

/

12

Passed

Implementation

14%

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

This skill reads as an exhaustive reference document rather than an actionable skill for Claude. It is extremely verbose, explaining many concepts Claude already knows, while lacking a clear step-by-step workflow for the primary use case of scaffolding a plugin. The content would benefit enormously from being split into a concise overview SKILL.md with references to detailed component guides, and from adding an executable scaffolding workflow with validation steps.

Suggestions

Add a concrete, sequential 'Scaffold a new plugin' workflow at the top with executable mkdir/file-creation commands and a validation step (e.g., 'verify plugin loads by checking Claude Code settings').

Split detailed component documentation (commands, agents, skills, hooks, MCP servers) into separate reference files and link to them from a concise overview section.

Remove explanations of concepts Claude already knows: what kebab-case is, what semantic versioning means, what markdown frontmatter is, why hardcoded paths are bad, etc.

Create the referenced 'references/' and 'examples/' directories mentioned at the end, or remove the dangling reference.

DimensionReasoningScore

Conciseness

Extremely verbose at ~350+ lines. Explains many concepts Claude already knows (what kebab-case is, what semantic versioning is, what markdown frontmatter is, basic directory structures). Sections like 'Best Practices' and 'File Naming Conventions' are largely redundant with information Claude inherently understands. The 'Why it matters' explanation for CLAUDE_PLUGIN_ROOT is unnecessary padding.

1 / 3

Actionability

Provides concrete directory structures, JSON examples, and file format templates that are useful references. However, there's no step-by-step 'scaffold a plugin' workflow with executable commands (e.g., mkdir commands, file creation). The examples are illustrative rather than copy-paste executable — they show structure but don't provide a complete working plugin one could immediately create.

2 / 3

Workflow Clarity

Despite being a skill about creating/scaffolding plugins, there is no clear sequential workflow for actually creating a plugin. The content is organized as a reference document rather than a procedural guide. There are no validation checkpoints (e.g., 'verify plugin loads correctly by running X'). The troubleshooting section partially compensates but is reactive rather than proactive.

1 / 3

Progressive Disclosure

The content is a monolithic wall of text with no references to supporting files, despite ending with 'see files in references/ and examples/ directories' — which don't exist in the bundle. All content is inline when much of it (detailed component formats, naming conventions, best practices, troubleshooting) should be split into separate reference files. The skill tries to be both overview and comprehensive reference simultaneously.

1 / 3

Total

5

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
anthropics/claude-plugins-official
Reviewed

Table of Contents

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.