pleaseai/mastra
Official agent skills for coding agents working with the Mastra AI framework
75
94%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that thoroughly covers what the skill does, when to use it, and provides extensive trigger terms. It uses proper third-person voice, lists concrete actions, enumerates specific packages and APIs, and includes an explicit triggers list. The numbered use-case scenarios and the 'Triggers on' clause make it highly actionable for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: answering questions about Mastra AI framework, building agents, workflows, tools, memory, and RAG features, wiring up agents and step-based orchestration, integrating specific packages, and debugging TypeScript errors from Mastra APIs. | 3 / 3 |
Completeness | Clearly answers both 'what' (answer questions about Mastra, help build agents/workflows/tools/memory/RAG) and 'when' (explicit 'Use when developers...' clause with four numbered scenarios plus a 'Triggers on' list with specific keywords). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms developers would use, including specific API names ('createWorkflow', 'createTool', 'createStep'), package names ('@mastra/core', '@mastra/memory', '@mastra/rag'), CLI references ('mastra CLI'), and common phrases like 'mastra agent', 'mastra workflow', 'semantic recall'. The explicit 'Triggers on' list is comprehensive. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific named framework (Mastra) with specific package names and API identifiers. Very unlikely to conflict with generic AI/TypeScript skills due to the precise naming throughout. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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 that excels at actionability and progressive disclosure, providing concrete commands and clear references to deeper documentation. The workflow for looking up docs and debugging errors is clearly sequenced. Minor conciseness issues exist with some redundancy between inline tables and referenced files, and the meta-section about the relationship to another skill adds cognitive overhead without strong payoff.
Suggestions
Trim or remove the 'Relationship to the mastra skill' section — it's meta-information about skill organization that doesn't help Claude execute tasks and consumes tokens.
Consider removing the inline package map table since it largely duplicates references/packages.md; a single line pointing to that reference would be more token-efficient.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts, but includes some redundancy — the 'Relationship to the mastra skill' section and repeated reminders to 'verify against dist/docs/' add tokens without proportional value. The package map table partially duplicates the references/packages.md it points to. | 2 / 3 |
Actionability | Provides concrete, executable bash commands for checking installations, looking up docs, grepping references, and resolving errors. The canonical lookup flow is copy-paste ready, and the rules of thumb give specific, actionable guidance (e.g., model string format, .commit() requirement, threadId/resourceId stability). | 3 / 3 |
Workflow Clarity | The canonical lookup flow is a clear 3-step sequence. The prerequisite section has a logical detect-then-install flow. The 'When Typecheck or Runtime Fails' section provides a clear escalation path: check common-errors.md first, then grep source. The 'Critical: Do Not Trust Internal Knowledge' section is a well-ordered 6-step verification workflow. | 3 / 3 |
Progressive Disclosure | Excellent structure with a clear overview in the main SKILL.md and well-signaled one-level-deep references to packages.md, agents-and-workflows.md, and common-errors.md. Content is appropriately split between the overview and reference files, with a clear navigation section at the bottom. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents