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.

83

1.96x
Quality

75%

Does it follow best practices?

Impact

100%

1.96x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/plugin-dev/skills/plugin-structure/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

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

The content is a thorough, mostly actionable reference with strong concrete JSON/directory examples and a clear auto-discovery sequence. Its weaknesses are verbosity in advisory sections, inlining of content that duplicate bundle files already hold, and an unreferenced/broken pointer to an examples/ directory.

Suggestions

Move the detailed manifest-field reference and component-pattern material into the existing references/component-patterns.md and references/manifest-reference.md files, then link them explicitly by name from the relevant sections instead of inlining them.

Trim the generic 'Best Practices' and 'File Naming Conventions' advice to the non-obvious rules only, removing guidance Claude already knows (e.g., 'use consistent naming', 'test on multiple systems').

Fix the closing pointer: remove or create the nonexistent examples/ directory, and replace the vague 'see files in references/ and examples/ directories' with explicit named links.

DimensionReasoningScore

Conciseness

The body is mostly efficient structured reference (concrete manifest/hook/MCP JSON shapes, an events list, directory trees), but generic advisory sections like 'Best Practices' ('Test on multiple systems', 'Document dependencies', 'Version consistently') and parts of 'File Naming Conventions' pad the document with guidance Claude largely already knows; it is not a 2 because the core reference content is genuinely specific and useful, and not a 4 because the padding is non-trivial across ~470 lines.

3 / 5

Actionability

Provides copy-paste-ready JSON examples for the manifest, hooks configuration, MCP servers, and concrete file-format templates for commands/agents/skills, covering the common cases; it is not a 5 because several sections (naming conventions, best practices, portability) are advisory prose without executable artifacts.

4 / 5

Workflow Clarity

The 'Auto-Discovery Mechanism' gives a clear numbered 6-step loading sequence with timing and override behavior, and 'Troubleshooting' supplies feedback for failure modes; it is not a 5 because there are no explicit validation checkpoints or validate-fix-retry loops, and not a 3 because the sequences that exist are clearly ordered and concrete.

4 / 5

Progressive Disclosure

The body has good section headers and a references/ bundle (component-patterns.md, manifest-reference.md) exists, but the references are never individually signaled or linked—only a vague closing 'see files in references/ and examples/ directories' (and examples/ does not exist, a broken reference), while manifest-reference and component-pattern content that belongs in those files is inlined; it is not a 2 because real section structure exists, and not a 4 because inlining and weak signaling are significant.

3 / 5

Total

14

/

20

Passed

Description

86%Weight 40%Scale 1-5

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 provides comprehensive, natural trigger phrases and a clear niche, with both 'what' and 'when' present. Its main weakness is leading with the 'when' and framing the 'what' as 'needs guidance on' topics rather than a direct statement of the skill's concrete actions.

Suggestions

Lead with a direct capability statement (e.g., 'Scaffolds and organizes Claude Code plugins: directory layout, plugin.json manifest, and component discovery') before the 'Use when...' clause to make the 'what' explicit.

Tighten the long quoted trigger list into a tighter set of the most natural user phrasings to reduce verbosity without losing coverage.

DimensionReasoningScore

Specificity

Lists several specific capability areas such as 'plugin directory layout, manifest configuration, component organization, file naming conventions', with minor gaps; it does not quite reach level 5 because the 'what' is framed as topics the user 'needs guidance on' rather than a comprehensive list of concrete actions the skill performs.

4 / 5

Completeness

The 'when' is explicit via 'should be used when the user asks to...' with concrete trigger phrases, and the 'what' is conveyed as 'guidance on plugin directory layout, manifest configuration, component organization...'; it falls short of 5 because the 'what' is stated indirectly as topics rather than a direct capability statement leading the description.

4 / 5

Trigger Term Quality

Comprehensive natural trigger phrases including synonyms ('create a plugin', 'scaffold a plugin', 'understand plugin structure', 'organize plugin components') plus concrete technical triggers like 'set up plugin.json' and 'use ${CLAUDE_PLUGIN_ROOT}'; it is not a 4 because coverage of natural phrasings is broad and varied.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Claude Code plugin architecture) with distinct, specific triggers unlikely to fire for unrelated skills; minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

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.