plugin-creator
Create automatically creates new AI assistant code plugins with proper structure, validation, and marketplace integration when user mentions creating a plugin, new plugin, or plugin from template. specific to AI assistant-code-plugins repository workflow. Use when generating or creating new content. Trigger with phrases like 'generate', 'create', or 'scaffold'.
63
76%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/examples/jeremy-plugin-tool/skills/plugin-creator/SKILL.mdQuality
Discovery
82%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 has good trigger term coverage and completeness with explicit 'Use when' guidance. However, the overly broad trigger 'Use when generating or creating new content' undermines distinctiveness and could cause false matches with other creation-oriented skills. The specificity of capabilities could be improved by listing more concrete actions beyond 'proper structure, validation, and marketplace integration'.
Suggestions
Narrow the 'Use when' clause to remove the overly generic 'generating or creating new content' and instead scope it specifically to plugin creation contexts to reduce conflict risk.
List more concrete actions such as 'generates plugin manifest, creates directory structure, adds validation schemas, registers with marketplace' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (AI assistant code plugins) and mentions some actions like 'proper structure, validation, and marketplace integration', but these are somewhat vague—it doesn't list concrete steps like 'generate manifest files, create validation schemas, register with marketplace API'. | 2 / 3 |
Completeness | Clearly answers both 'what' (creates new AI assistant code plugins with proper structure, validation, and marketplace integration) and 'when' (explicit 'Use when' clause with trigger phrases like 'generate', 'create', 'scaffold', and mentions of creating/new plugins). | 3 / 3 |
Trigger Term Quality | Includes good natural trigger terms: 'creating a plugin', 'new plugin', 'plugin from template', 'generate', 'create', 'scaffold'. These are terms users would naturally use when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | The scope is narrowed to 'AI assistant-code-plugins repository workflow', which helps, but the generic triggers 'generate' and 'create' could easily conflict with many other skills. The phrase 'Use when generating or creating new content' is overly broad and could match unrelated creation tasks. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent workflow clarity and progressive disclosure. The main weakness is that actionability relies heavily on external reference files for concrete templates and code, meaning the SKILL.md itself doesn't contain copy-paste-ready content. Conciseness is reasonable but the output section is somewhat redundant with the instructions.
Suggestions
Include at least one inline example of a generated plugin.json template so the skill is actionable without requiring the external reference file
Remove or condense the Output section since it largely restates what steps 1-9 already describe, or merge it as a checklist into the final validation step
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary verbosity. The error handling table and examples section add useful context, but the output section largely restates what the instructions already cover. Some descriptions could be tightened. | 2 / 3 |
Actionability | The instructions provide a clear numbered sequence with specific directory structures, file names, and commands, but lack executable code examples. Template generation is delegated to external reference files rather than showing concrete snippets inline. Key details like the actual plugin.json structure or frontmatter format are not shown directly. | 2 / 3 |
Workflow Clarity | The 9-step workflow is clearly sequenced with explicit validation at step 9 (running validate-all-plugins.sh) and a clear instruction to fix issues before completion. The error handling table provides a feedback loop for common failure modes. The marketplace sync step (step 8) precedes validation, creating a logical progression. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled references to four separate resource files for detailed templates, creation workflows, examples, and error handling. References are one level deep and clearly labeled with descriptive annotations. The main SKILL.md stays at an appropriate summary level. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
69c73e9
- 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.