CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nuxt-content

Nuxt Content v3 Git-based CMS for Markdown/MDC content sites. Use for blogs, docs, content-driven apps with type-safe queries, schema validation (Zod/Valibot), full-text search, navigation utilities. Supports Nuxt Studio production editing, Cloudflare D1/Pages deployment, Vercel deployment, SQL storage, MDC components, content collections.

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

75%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 highly actionable, code-first reference whose copy-paste examples span setup through deployment and troubleshooting. Its weaknesses are systematic duplication of the rule lists and marketing padding that hurt token efficiency, missing inline validation checkpoints, and a bundle-navigation gap: a phantom templates/ reference plus eight unmentioned scripts/ and assets/ files.

Suggestions

Consolidate 'Critical Rules', 'Best Practices', and 'Performance Tips' into a single rule list — the same 10 rules (ISO dates, .only(), components/content/, D1 'DB' binding, dev-server restart, etc.) are currently restated three times — and cut the 'Why this matters' commentary and 'Overview'/'What's New' marketing prose.

Fix the dangling `templates/blog-collection-setup.ts` reference (cited twice but no templates/ directory exists) and extend the 'When to Load References' section to list the four scripts/ and four assets/ files so the deploy/setup scripts and example configs are discoverable from SKILL.md.

Add explicit validation checkpoints to the workflows: e.g., confirm the collection query returns the page before wiring ContentRenderer, and verify the D1 binding/migration before `wrangler pages deploy`, instead of deferring all verification to the troubleshooting and reference sections.

DimensionReasoningScore

Conciseness

Mostly efficient code-first sections, but there is real padding: the same 10 rules are restated three times across "Critical Rules" (Always + mirrored Never lists), "Best Practices", and "Performance Tips"; "Why this matters" blocks explain what packages do; "Overview"/"What's New" carry marketing prose ("powerful Git-based CMS", "Ultra-fast data retrieval"); and pinned version numbers and dates ("@nuxt/content@^3.0.0...", two conflicting "Last Updated" dates) sit outside any deprecated section. Not anchor 2 because the bulk (Quick Start, Collections, Queries, MDC, Deployment, Studio, Issues) is lean and executable with no conceptual re-teaching.

3 / 5

Actionability

Fully executable and copy-paste ready throughout: install commands ("bun add @nuxt/content better-sqlite3"), complete content.config.ts with Zod schemas, query-builder chains, wrangler.toml with the case-sensitive "DB" binding, and exact error messages paired with fix commands ("rm -rf .nuxt && bun dev"). Coverage spans install → config → query → render → deploy → troubleshoot, matching the anchor-5 'common cases covered' bar; the only nit (unnamed Studio OAuth env vars) is negligible.

5 / 5

Workflow Clarity

Quick Start is a clearly numbered 4-step sequence, and "Top 5 Critical Issues" provides error→diagnosis→fix-command feedback loops, with deployment checklists delegated to references/deployment-checklists.md. It falls short of anchor 5 because the main workflows lack inline validation checkpoints (e.g., no 'verify the collection query returns the page' step before wiring up ContentRenderer, and deploy steps have no verification before going live) — anchor 4's 'most checkpoints present, minor validation gaps' fits best.

4 / 5

Progressive Disclosure

The "When to Load References" section explicitly signals all six existing one-level-deep reference files with per-file load conditions — exemplary signaling that rules out anchor 3. However, anchor 5 is blocked by real navigation gaps measured against the actual bundle: `templates/blog-collection-setup.ts` is referenced twice ("See Full Template", "Templates (templates/):...") but no templates/ directory exists, and the four scripts/ and four assets/ files (deploy-cloudflare.sh, deploy-vercel.sh, setup-nuxt-content.sh, setup-studio.sh, and the example configs) are never mentioned anywhere in the body, leaving them undiscoverable.

4 / 5

Total

16

/

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 strong, third-person description that clearly states a specific niche, explicit 'Use for' triggers, and a broad inventory of concrete capabilities. Its only weaknesses are feature-noun phrasing instead of action verbs and a few missing natural synonyms/extensions.

DimensionReasoningScore

Specificity

Lists several concrete capabilities — "type-safe queries, schema validation (Zod/Valibot), full-text search, navigation utilities", "Cloudflare D1/Pages deployment, Vercel deployment, SQL storage, MDC components, content collections" — but frames them as supported features (nouns) rather than the concrete action verbs of the anchor-5 example ("Extract text and tables... fill forms, merge documents"). Well above anchor 3 (only 1-2 actions), just short of anchor 5's comprehensive action coverage.

4 / 5

Completeness

Explicitly answers both: what ("Nuxt Content v3 Git-based CMS for Markdown/MDC content sites" plus the capability list) and when ("Use for blogs, docs, content-driven apps with type-safe queries...") with concrete trigger phrases, matching the anchor-5 pattern. Not anchor 4, because the 'when' clause is already explicit and specific rather than something that 'could be more explicit'.

5 / 5

Trigger Term Quality

Good natural keyword coverage: "blogs, docs, content-driven apps", "Markdown/MDC", "Nuxt Studio", "Cloudflare D1/Pages", "Vercel", "Zod/Valibot" are phrases users would plausibly say. A few natural terms and file extensions (e.g., ".md", "documentation site", "markdown CMS") are missing from the description itself, so it does not reach anchor 5's comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

Clear niche ("Nuxt Content v3") with highly distinct triggers — "MDC components", "Nuxt Studio production editing", "Cloudflare D1/Pages", "queryCollection"-style vocabulary — making wrong-skill triggering very unlikely. Only marginally overlaps with a generic Nuxt skill, fitting anchor 5's minimal-conflict profile.

5 / 5

Total

18

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (749 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

13

/

16

Passed

Repository

secondsky/claude-skills

Path

plugins/nuxt-content/skills/nuxt-content/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.