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'.
79
76%
Does it follow best practices?
Impact
Pending
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, but suffers from overly broad trigger phrases ('generate', 'create') that could cause false matches with many other skills. The specificity of actions is moderate—mentioning 'proper structure, validation, and marketplace integration' without detailing what those entail. The phrase 'Use when generating or creating new content' is dangerously broad and undermines the otherwise specific plugin-focused scope.
Suggestions
Narrow the 'Use when' clause to be plugin-specific only—remove the overly broad 'Use when generating or creating new content' and replace with 'Use when the user wants to create, scaffold, or generate a new AI assistant code plugin'.
Improve distinctiveness by removing generic triggers like 'generate' and 'create' as standalone triggers, and instead qualify them: 'create a plugin', 'generate a plugin', 'scaffold a plugin'.
| 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 and not fully concrete actions (e.g., what does 'proper structure' entail specifically?). | 2 / 3 |
Completeness | Clearly answers both 'what' (creates new AI assistant code plugins with proper structure, validation, and marketplace integration) and 'when' (explicit trigger phrases like 'generate', 'create', 'scaffold', and specific scenarios like 'creating a plugin, new plugin, or plugin from template'). | 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 domain is fairly specific (AI assistant-code-plugins repository), but trigger terms like 'generate', 'create', and 'scaffold' are extremely generic and could easily conflict with many other creation-oriented skills. The broad 'Use when generating or creating new content' clause significantly increases conflict risk. | 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 actionability: while the steps are clear and well-ordered, the actual content generation relies heavily on reference files (templates, examples) that aren't bundled, meaning the SKILL.md alone doesn't provide enough concrete detail to execute without those references. Conciseness could be improved by moving the error table and examples to reference files.
Suggestions
Include at least one inline, concrete plugin.json template snippet or YAML frontmatter example so the skill is partially executable without reference files
Move the error handling table to the referenced errors.md file and keep only a brief note about running validation and checking that file for troubleshooting
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary verbosity, such as the full directory tree that Claude could infer, the detailed error handling table that could be in a reference file, and the examples section which largely restates the workflow. Some tightening is possible. | 2 / 3 |
Actionability | The instructions provide a clear numbered sequence with specific commands (pnpm run sync-marketplace, validate-all-plugins.sh) and file paths, but lack executable code examples—no actual plugin.json template content, no concrete YAML frontmatter examples, and key details are deferred to reference files that aren't provided in the bundle. | 2 / 3 |
Workflow Clarity | The 9-step workflow is clearly sequenced with explicit validation at step 9 (run validation script, fix issues before completion), marketplace sync at step 8, and a clear error-recovery table. The instruction to 'fix any reported issues before completion' establishes a feedback loop for the destructive/generative operation. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to four specific resource files (plugin-creation-process.md, file-templates.md, examples.md, errors.md). The main SKILL.md stays at the right level of abstraction while pointing to detailed templates and walkthroughs. However, no bundle files were provided to verify these references exist. | 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
3a2d27d
- 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.