Validation
75%| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 12 / 16 Passed | |
Implementation
77%This is a well-structured experimental skill with excellent workflow clarity and actionability. The dual-mode approach (Agent vs Inline) is clearly documented with explicit detection logic. Main weakness is length - the detailed output templates for each layer add significant tokens that could be externalized for better progressive disclosure.
Suggestions
Consider extracting the detailed layer analysis templates (Steps 2-4 in Inline Mode) to separate reference files like `layer-templates.md` to reduce main skill length
The three layer output templates share similar structure - consider a single parameterized template to reduce redundancy
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some redundancy - the inline mode templates repeat similar structures across all three layers, and the concept diagram, while helpful, adds tokens. The test scenarios and error handling sections are appropriately concise. | 2 / 3 |
Actionability | Provides fully concrete guidance with specific file paths to check, exact Task() syntax for agent launching, complete markdown templates for each layer's output, and executable code pattern examples in the final output template. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing for both Agent Mode (4 steps) and Inline Mode (5 steps). Includes explicit mode detection as first step, clear parallel vs sequential branching, and synthesis only after all layers complete. Error handling table provides recovery guidance. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections, but the skill is quite long (~300 lines) with detailed templates that could potentially be split into separate reference files. The inline mode layer templates are verbose and could be externalized while keeping the main skill as an overview. | 2 / 3 |
Total | 10 / 12 Passed |
Activation
22%This description fails to explain what the skill actually does beyond a vague label. While it includes explicit trigger commands, it lacks concrete actions, clear use cases, and any explanation of the 'three-layer' methodology. The 'EXPERIMENTAL' prefix and technical jargon make it difficult for Claude to know when this skill would be appropriate.
Suggestions
Add concrete actions explaining what 'three-layer parallel meta-cognition analysis' actually does (e.g., 'Analyzes problems from three perspectives simultaneously: logical, emotional, and strategic').
Add a 'Use when...' clause with natural language triggers describing scenarios where this analysis would be helpful (e.g., 'Use when the user needs multi-perspective analysis of complex decisions or wants to examine a problem from multiple angles').
Replace or supplement technical jargon with plain language that describes the benefit or outcome of using this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language ('meta-cognition analysis') without listing any concrete actions. It doesn't explain what the skill actually does - no verbs describing specific capabilities. | 1 / 3 |
Completeness | The 'what' is extremely weak (just 'meta-cognition analysis' with no explanation), and there's no 'when' clause explaining usage scenarios. The trigger terms are listed but don't constitute proper usage guidance. | 1 / 3 |
Trigger Term Quality | Includes explicit trigger terms ('/meta-parallel', '三层分析', 'parallel analysis', '并行元认知') but these are technical jargon rather than natural phrases users would say. The bilingual terms add some coverage but remain specialized. | 2 / 3 |
Distinctiveness Conflict Risk | The specific command triggers ('/meta-parallel') provide some distinctiveness, but 'parallel analysis' is generic enough to potentially conflict with other analytical skills. The niche is unclear without understanding what meta-cognition analysis means. | 2 / 3 |
Total | 6 / 12 Passed |
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.