meta-cognition-parallel

EXPERIMENTAL: Three-layer parallel meta-cognition analysis. Triggers on: /meta-parallel, 三层分析, parallel analysis, 并行元认知

Quality

24%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/meta-cognition-parallel/SKILL.md

Quality

Discovery

22%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is heavily jargon-laden and fails to explain what the skill concretely does or when it should be used beyond listing trigger commands. It lacks specificity about actions performed and provides no scenario-based guidance for skill selection. The bilingual trigger terms add some distinctiveness but don't compensate for the fundamental lack of clarity.

Suggestions

Add concrete actions describing what the skill produces — e.g., 'Analyzes a problem from three parallel cognitive layers: X, Y, Z, producing a structured comparison of perspectives.'

Add a 'Use when...' clause with natural scenario descriptions, e.g., 'Use when the user wants multi-perspective analysis of a complex problem or requests deep reasoning from multiple angles.'

Replace or supplement jargon like 'meta-cognition analysis' with plain-language equivalents so Claude can match this skill to natural user requests.

Dimension	Reasoning	Score
Specificity	The description says 'Three-layer parallel meta-cognition analysis' which is abstract and jargon-heavy. No concrete actions are listed — it doesn't explain what the skill actually does (e.g., what is analyzed, what output is produced).	1 / 3
Completeness	The 'what' is extremely vague ('meta-cognition analysis' with no elaboration on what it produces or how), and the 'when' is limited to listing slash commands and trigger phrases rather than describing scenarios. There is no 'Use when...' clause explaining the situations that warrant this skill.	1 / 3
Trigger Term Quality	It lists explicit trigger terms ('/meta-parallel', '三层分析', 'parallel analysis', '并行元认知') which are useful for command-based invocation, but these are not natural phrases a user would typically say when needing this capability. Terms like 'meta-cognition' and '并行元认知' are highly specialized jargon.	2 / 3
Distinctiveness Conflict Risk	The specific slash command '/meta-parallel' and bilingual trigger terms provide some distinctiveness, but the vague domain of 'meta-cognition analysis' could overlap with other analytical or reasoning skills. The niche is unclear enough that conflict risk remains moderate.	2 / 3
	Total	6 / 12 Passed

Implementation

27%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill suffers from significant verbosity, essentially duplicating the full analysis framework twice (agent mode and inline mode) within a single file. The templates are detailed but largely describe what Claude should think about rather than providing concrete executable steps. The lack of bundle files means all referenced agent files are missing, and the monolithic structure makes it hard to navigate.

Suggestions

Reduce content by at least 50%: merge the agent and inline mode sections by describing the difference in 2-3 lines and sharing the common template once, rather than repeating the full analysis structure for each mode.

Remove explanatory content Claude already knows (e.g., what ownership/borrowing is, what FinTech constraints are) and focus only on the specific analysis framework and output format.

Split layer analyzer templates into separate bundle files (layer1-analyzer.md, layer2-analyzer.md, layer3-analyzer.md) that are actually provided, and keep SKILL.md as a concise coordinator overview.

Add validation checkpoints: after collecting agent/layer results, verify each result contains the required fields (Error/Pattern, Confidence, etc.) before proceeding to synthesis.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~250+ lines. It explains concepts Claude already knows (what ownership/borrowing is, what PDF-like domain concepts are), repeats the same template structures for both agent and inline modes, includes extensive markdown templates that could be much more compact, and has unnecessary sections like 'Concept' diagrams and 'Feedback' requests.	1 / 3
Actionability	The skill provides structured templates and clear output formats, but the Task() launch syntax appears to be pseudocode rather than executable commands. The inline mode steps are essentially prompt templates telling Claude to 'analyze' things rather than providing concrete executable logic. The agent file references are speculative (no bundle files provided).	2 / 3
Workflow Clarity	The multi-step process is clearly sequenced for both agent and inline modes with numbered steps, and there's a mode detection step. However, there are no validation checkpoints — no verification that agent results are well-formed, no error recovery loops for malformed layer outputs, and the 'Collect Results' step (Step 3 in agent mode) lacks any validation before proceeding to synthesis.	2 / 3
Progressive Disclosure	The skill is a monolithic wall of text with no bundle files to support it. The referenced agent files (../../agents/layer1-analyzer.md etc.) don't exist in the bundle, and all content — including lengthy templates for both execution modes, test scenarios, and error handling — is crammed into a single file with no separation of concerns.	1 / 3
	Total	6 / 12 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: actionbook/rust-skills
Commit: fa60f79

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.