The body is highly actionable, well-sequenced with verification checkpoints, and uses clean one-level-deep progressive disclosure. It is slightly verbose in its meta-commentary about sibling skills and duplicated package-map prose.

Suggestions

Tighten or remove the 'Relationship to the mastra skill' section — the cross-skill disambiguation is meta-commentary that adds tokens without aiding task execution.

Deduplicate the package coverage: the 'Finding Documentation' table and the 'Mastra Package Map' table overlap; consolidate into the references/packages.md pointer and keep only one compact inline map.

Trim narrative restatements (e.g. repeating the dist/docs layout prose) in favor of the already-clear command examples to lift conciseness toward a 3.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and directive, but the 'Relationship to the mastra skill' meta-commentary and the partially restated package-map prose could be trimmed; a few tokens do not clearly earn their place.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: install commands, exact dist/docs lookup paths, grep/rg/jq commands, TypeScript targets, and typecheck commands rather than abstract direction.	3 / 3
Workflow Clarity	Multi-step process is clearly sequenced with validation checkpoints (resolve version → read shipped docs → verify symbols → typecheck) and explicit error-recovery feedback loops.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview with well-signaled, one-level-deep references (packages.md, agents-and-workflows.md, common-errors.md), all verified to exist and each annotated with what it covers.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 is specific, trigger-rich, and clearly distinguishes the skill via Mastra-scoped tokens. It fully answers both what it does and when to use it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (build agents/workflows/tools/memory/RAG, ask about named Mastra APIs, wire up orchestration, integrate scoped @mastra/* packages, debug TypeScript errors) rather than vague language.	3 / 3
Completeness	Explicitly answers 'what' (first sentence: answer questions and help build framework features) and 'when' (a four-clause 'Use when developers:' plus an explicit 'Triggers on:' list).	3 / 3
Trigger Term Quality	Includes a dedicated 'Triggers on:' list of natural terms a developer would actually say ('mastra agent', 'mastra memory', 'semantic recall', 'mastra rag', '@mastra/core', 'provider/model'), giving strong keyword coverage.	3 / 3
Distinctiveness Conflict Risk	The niche is narrowly scoped to the Mastra framework with trigger tokens tied to Mastra-named APIs and packages, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Reviewed

6 days ago

Table of Contents

Discovery Implementation Validation