CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-code-plugin-development

This skill should be used when the user asks to "create a plugin", "build a plugin", "write a plugin", or wants to bundle agents, hooks, commands, skills, or MCP servers into a distributable Claude Code plugin.

97

1.93x
Quality

Does it follow best practices?

Impact

93%

1.93x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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 tight, actionable reference: real schemas, concrete CLI commands, an explicit verification checklist, and well-signaled one-level-deep references to actual bundle files. It respects Claude's competence while remaining copy-paste ready.

DimensionReasoningScore

Conciseness

The body is lean reference material — directory trees, real schemas, CLI commands, and troubleshooting fixes — with no padding explaining concepts Claude already knows. The component summary table overlaps slightly with the structure diagram but each token still earns its place.

3 / 3

Actionability

Provides copy-paste-ready artifacts: a minimal plugin.json and marketplace.json schema, concrete CLI commands ('claude plugin install <plugin>@<marketplace> --scope user'), ${CLAUDE_PLUGIN_ROOT} usage, and exact fix commands for the disabled-plugin case.

3 / 3

Workflow Clarity

A final checklist sequences finalization with an explicit verification step ('Test with claude --debug to verify loading'), and the troubleshooting section gives a clear diagnose→fix→restart loop, matching the anchor requiring explicit validation checkpoints.

3 / 3

Progressive Disclosure

The SKILL.md is an overview that signals one-level-deep references to real, verified files (plugin-manifest.md, plugin-components.md, cli-commands.md, debugging.md) under ./references/, with well-organized sections and easy navigation.

3 / 3

Total

12

/

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 precise, trigger-rich, and explicitly states both what the skill does and when to use it. It would reliably activate on natural plugin-creation requests without conflicting with other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'create a plugin', 'build a plugin', 'write a plugin', and 'bundle agents, hooks, commands, skills, or MCP servers into a distributable Claude Code plugin' — matching the top anchor of specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('bundle ... into a distributable Claude Code plugin') and when ('This skill should be used when the user asks to...'), matching the anchor that clearly answers both what AND when with explicit triggers.

3 / 3

Trigger Term Quality

Includes natural phrasings a user would actually say — 'create a plugin', 'build a plugin', 'write a plugin', 'bundle agents, hooks, commands, skills, or MCP servers' — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (Claude Code plugins) with distinct, plugin-specific triggers ('create/build/write a plugin', 'bundle ... MCP servers'), making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
dwmkerr/claude-toolkit
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.