CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mastra-docs

Documentation guidelines for Mastra. Use this skill when creating, editing, moving, deleting, or reviewing Mastra documentation, sidebars, redirects, or docs components.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

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.

The body is an exemplary lean, well-signaled overview for a reference-heavy guidelines skill, but its executable core is undermined by a missing `templates/` directory: every template path in the selection table and the mandatory checklist step point at files that are not in the bundle. Adding those files (or removing/inlining the template workflow) and an explicit verify-and-fix loop would lift the actionability and navigation substantially.

Suggestions

Add the `templates/` directory with the six template skeletons (overview.md, concept.md, how-to.md, quickstart.md, reference-api.md, integration.md) and CHECKLIST.md referenced in the table, or remove the template table and inline the essential skeleton shapes.

Add an explicit error-recovery loop to the authoring steps, e.g., run `pnpm check` (per references/CHECKS.md) before finishing and fix reported rule violations before proceeding.

State the concrete verification command in the body's step 4 rather than deferring it entirely to templates/CHECKLIST.md and the per-template checklists, so validation survives even if a template file is missing.

DimensionReasoningScore

Conciseness

The ~37-line body is lean and navigational: every line maps a file to its scope ("references/STYLEGUIDE.md: ISO 24495-1 plain-language principles..."), a dense template-selection table, four terse authoring steps, and a one-line closing principle. It assumes Claude's competence with no padded explanation of concepts Claude already knows, matching the 'every token earns its place' anchor.

5 / 5

Actionability

The steps are concrete ("Copy the template's skeleton into the new .mdx file and replace every $PLACEHOLDER", "run templates/CHECKLIST.md"), but the workflow's key dependencies — all seven `templates/*.md` files referenced in the table — are absent from the bundle, so the central copy-the-template action cannot be executed as written. This fits 'some concrete guidance but incomplete; missing key details' rather than the minor-gaps level of 4.

3 / 5

Workflow Clarity

The page-creation sequence is clear (pick template → copy skeleton → compare with conventions → prune optional sections) and ends with an explicit validation checkpoint ("Before finishing, run templates/CHECKLIST.md and the template's own self-review checklist"), matching 'clear sequence with most checkpoints present'. It stops short of 5 because no error-recovery feedback loop (e.g., fix and re-run when a check fails) is described in the body itself.

4 / 5

Progressive Disclosure

The overview-plus-references structure is well signaled — all nine `references/*.md` files exist and each gets a one-line scope description, one level deep. However, scored against the actual bundle, seven of the sixteen referenced paths (the entire `templates/` directory: overview.md, concept.md, how-to.md, quickstart.md, reference-api.md, integration.md, CHECKLIST.md) do not exist, so a substantial portion of the navigation is broken despite the good signaling.

3 / 5

Total

15

/

20

Passed

Description

87%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 well-formed description that clearly states both capability and explicit, task-specific triggers anchored to a distinct product domain. Minor room to broaden natural trigger synonyms (e.g., .mdx, docs pages).

DimensionReasoningScore

Specificity

The description lists several concrete actions ("creating, editing, moving, deleting, or reviewing") applied to specific artifacts ("Mastra documentation, sidebars, redirects, or docs components"), matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because 'Documentation guidelines for Mastra' summarizes the capability without enumerating what the guidelines cover (style, architecture, diagrams, templates, checks).

4 / 5

Completeness

Both parts are explicit: the what ("Documentation guidelines for Mastra") and a concrete when clause ("Use this skill when creating, editing, moving, deleting, or reviewing Mastra documentation, sidebars, redirects, or docs components") with specific trigger tasks. The when clause is more explicit than the anchor-4 example, matching the 'clearly and explicitly answers both what AND when with concrete trigger phrases' anchor.

5 / 5

Trigger Term Quality

Good natural keyword coverage — "Mastra documentation", "sidebars", "redirects", "docs components", plus the maintenance verbs users would naturally use. A few natural terms are missing (e.g., ".mdx", "docs pages", "docs site"), so it does not reach the comprehensive synonym/extension coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

"Mastra" names a distinct product and the trigger objects (sidebars, redirects, docs components) are specific to docs maintenance for that product, giving it a clear niche with minimal conflict risk beyond appropriately overlapping sibling Mastra skills.

5 / 5

Total

18

/

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

mastra-ai/mastra

Path

.claude/skills/mastra-docs/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.