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 completeness with explicit 'Use when' triggers and reasonable specificity about the domain. However, the generic trigger terms ('generate', 'create') and the overly broad 'Use when generating or creating new content' clause create significant conflict risk with other skills. The specific actions could be more concrete (e.g., what 'proper structure' and 'marketplace integration' entail).
Suggestions
Narrow the 'Use when' clause to be plugin-specific rather than the overly broad 'generating or creating new content'—e.g., 'Use when the user wants to create, scaffold, or generate a new AI assistant code plugin.'
Add more concrete action details: specify what 'proper structure' means (e.g., 'generates manifest files, sets up directory layout, configures validation schemas') to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AI assistant code plugins) and some actions (create with proper structure, validation, marketplace integration), but the actions are somewhat vague—'proper structure' and 'marketplace integration' lack concrete detail about what specific operations are performed. | 2 / 3 |
Completeness | Clearly answers both 'what' (creates new AI assistant code plugins with structure, validation, marketplace integration) and 'when' (explicit 'Use when' clause with trigger phrases like 'generate', 'create', 'scaffold', plus contextual triggers like 'creating a plugin'). | 3 / 3 |
Trigger Term Quality | Includes good natural trigger terms: 'creating a plugin', 'new plugin', 'plugin from template', 'generate', 'create', 'scaffold'. These cover multiple natural phrasings a user might employ. | 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 'Use when generating or creating new content' is overly broad. | 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, properly delegating detailed templates and examples to reference files. Its main weakness is that actionability suffers from the lack of inline executable examples—the skill tells Claude what to generate but relies entirely on external files for the actual content templates. Conciseness could be improved by removing the redundant Output section and deduplicating the repeated validate/sync steps in examples.
Suggestions
Include at least one inline, concrete plugin.json template snippet so the skill is partially self-contained and actionable without requiring the reference file
Remove or condense the Output section, as it largely restates the Instructions steps 1-9
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy—the Output section largely restates what the Instructions already cover, and the Examples section repeats the sync/validate steps three times. The error handling table adds value but could be slightly tighter. | 2 / 3 |
Actionability | The instructions provide a clear numbered sequence with specific directory structures and file names, but lack executable code snippets for generating the actual file contents (e.g., no concrete plugin.json template inline, no actual command examples). It defers to external reference files for the actual templates, making it not copy-paste ready on its own. | 2 / 3 |
Workflow Clarity | The 9-step workflow is clearly sequenced with explicit validation at step 9 (run validate script, fix issues before completion), marketplace sync at step 8, and a clear error-recovery table. The feedback loop of 'fix any reported issues before completion' is present for this destructive/generative operation. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to detailed templates, examples, error patterns, and creation process docs. Content is appropriately split between the overview SKILL.md and the reference files. | 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
c8a915c
- 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.