CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mastra

Comprehensive Mastra framework guide for building agents, workflows, tools, memory, workspaces, and storage with current APIs. Use for documentation lookup, API verification, TypeScript setup, common errors, migrations, and `mastra api` CLI tasks: inspect or call resources on local, Mastra platform, Trace Intelligence, or remote servers. For Mastra Factory operations, discover and activate the companion mastra-factory skill.

68

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

A well-structured instructional skill body with a strong reference-routing table, concrete commands, and clear decision sequences. The main cost is redundancy — the doc-lookup workflow is explained three times across sections and repeated links inflate token usage without adding guidance.

Suggestions

Merge 'Development workflow' into 'Priority order for writing code' — they cover the same lookup sequence; keep one canonical numbered workflow.

Consolidate the three 'don't trust your knowledge' sections (Critical, Priority order preamble, When you see errors) into one, and link embedded-docs.md once from the routing table plus one workflow step instead of five times.

Give the concrete invocation for `scripts/provider-registry.mjs` (e.g., `node scripts/provider-registry.mjs <args>`) instead of 'run this'.

DimensionReasoningScore

Conciseness

The body is mostly efficient and imperative, but there is real redundancy: the 'Development workflow' section restates the 'Prerequisites' and 'Priority order' sections (re-explaining the embedded-docs vs. remote-docs split), `references/embedded-docs.md` is linked five separate times, and 'don't trust internal knowledge' guidance appears in three sections ('Critical: Do not trust internal knowledge', 'Never write code without checking current docs first', 'When you see errors'). This is more than the 'minor instances' of a 4 but nowhere near the heavy padding of a 2.

3 / 5

Actionability

Concrete, mostly executable guidance throughout: `ls node_modules/@mastra/`, `npm run dev`, `npx skills add mastra-ai/skills --skill mastra-factory --agent <agent> -g`, specific error signatures ('Property X does not exist on type Y'), and a named script to run. Minor gap: 'run this' for `scripts/provider-registry.mjs` without the actual invocation command keeps it from a 5.

4 / 5

Workflow Clarity

Multi-step processes are clearly sequenced ('Priority order' 1→2→3, 'Development workflow' 4 steps) and the 'When you see errors' section provides a genuine feedback loop (check common-errors → verify current API → don't assume user mistake). Not a 5 because no explicit validation checkpoints exist — e.g., verifying the `mastra api trace query` command exists before use is stated but there is no verify-output step in the development workflow.

4 / 5

Progressive Disclosure

A routing table maps user questions to each of the 10 reference files (all verified present in the bundle) with a purpose summary per row, plus the script is listed with its role. All references are one level deep, clearly signaled, and the body stays a lean overview that delegates detail to those files.

5 / 5

Total

16

/

20

Passed

Description

92%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.

A strong description: it states concrete capabilities across the framework's full surface, includes an explicit 'Use for...' clause with concrete triggers, and cleanly separates the companion Factory skill's scope. The only weakness is that a few natural user phrasings (e.g., 'upgrade', 'debug') are missing from the trigger terms.

Suggestions

Add a few natural user phrasings to the trigger list, e.g. 'upgrading Mastra versions' or 'debugging Mastra errors', to broaden keyword coverage.

Trim the opener 'Comprehensive' — a mild buzzword that adds no trigger value.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'building agents, workflows, tools, memory, workspaces, and storage', 'documentation lookup, API verification, TypeScript setup, common errors, migrations', and 'inspect or call resources' via the `mastra api` CLI — covering all of the skill's major feature areas. This matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage'; a 4 would require minor coverage gaps, which are not present.

5 / 5

Completeness

It explicitly answers both questions: what ('Comprehensive Mastra framework guide for building agents, workflows, tools, memory, workspaces, and storage with current APIs') and when ('Use for documentation lookup, API verification, TypeScript setup, common errors, migrations, and `mastra api` CLI tasks'), matching the anchor 'Clearly and explicitly answers both what AND when with concrete trigger phrases'.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'Mastra', 'agents', 'workflows', 'common errors', 'migrations', 'TypeScript setup', 'documentation lookup', '`mastra api`'. It falls short of 5 because common user phrasings and synonyms ('upgrade', 'debug', 'setup a Mastra project') are not covered; it is clearly above 3's 'missing common variations'.

4 / 5

Distinctiveness Conflict Risk

The Mastra framework niche is clear and trigger terms are distinct, and the description actively reduces conflict risk by routing 'Mastra Factory operations' to the separate companion 'mastra-factory' skill. Minimal overlap with any generic skill; not a 4 since there is no meaningful overlap with closely related skills.

5 / 5

Total

19

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

stevenknowswhy/ProfessionalBuyer

Path

.claude/skills/mastra/SKILL.md

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.