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

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/meta-cognition-parallel/SKILL.md

Quality

Content

38%Weight 40%Scale 1-5

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

The skill body lays out a clear two-mode workflow with structured templates, but is hampered by duplicated templated content, pseudocode rather than executable guidance, and a lack of any real bundle-based progressive disclosure. Validation of parallel agent results before synthesis is also missing.

Suggestions

De-duplicate the per-layer templates: keep one canonical set and have the Output Template reference it instead of repeating all three layers plus synthesis.

Add a validation checkpoint after Step 3 (Collect Results) that checks each layer result for required fields/confidence before synthesis, with a fix-and-retry loop for incomplete results.

Replace the pseudocode Task() blocks with concrete, copy-pasteable agent-launch instructions, or move the per-layer analyzer prompts into bundled reference files the skill actually ships with.

Dimension	Reasoning	Score
Conciseness	The ~300-line body duplicates the per-layer templates across Inline Mode and the Output Template, and relies heavily on fill-in placeholder scaffolding; while it avoids re-explaining known concepts, the volume of redundant templated content is noticeably verbose.	2 / 5
Actionability	Structured layer templates with concrete fields and focus areas give partial executable guidance, but the Agent Mode Task blocks are pseudocode with placeholder file contents and the layer templates are fill-in markdown rather than copy-paste runnable code.	3 / 5
Workflow Clarity	Steps are clearly sequenced per mode with explicit mode detection and a fallback table, but the parallel batch launch has no validation checkpoint confirming agent results before synthesis, so the batch-operation validation cap applies.	3 / 5
Progressive Disclosure	No bundle files exist and all content is inlined in a single long file; the only references point to external ../../agents/*.md files outside this bundle, and the per-layer templates are duplicated inline rather than split into navigable reference files.	2 / 5
	Total	10 / 20 Passed

Description

70%Weight 40%Scale 1-5

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 clearly communicates a distinct experimental capability with explicit bilingual trigger terms, covering both what and when. Its main weakness is abstract, jargon-heavy action language instead of concrete capability verbs.

Dimension	Reasoning	Score
Specificity	Names the domain ('Three-layer parallel meta-cognition analysis') and a couple of concrete actions (parallel launch, three-layer analysis, synthesis), but the verbs stay abstract ('analysis') rather than naming concrete operations.	3 / 5
Completeness	It states both what the skill does and when to use it via the explicit 'Triggers on:' clause, but the 'what' leans on jargon ('meta-cognition analysis') and the experimental qualifier rather than a fully concrete capability statement.	4 / 5
Trigger Term Quality	An explicit 'Triggers on:' list provides good keyword coverage across a slash command and bilingual synonyms (/meta-parallel, 三层分析, parallel analysis, 并行元认知), with only a few natural variations missing.	4 / 5
Distinctiveness Conflict Risk	The niche three-layer parallel analysis with a dedicated slash command and bilingual triggers is mostly distinct from other skills, with only minor overlap against generic analysis skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: actionbook/rust-skills
Path: skills/meta-cognition-parallel/SKILL.md
Commit: 5c40d3a

Reviewed: 14 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.