CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mdx-content-management

Manage, validate, compile, and render MDX (Markdown + JSX) content in modern web applications. Use when building content pipelines, technical documentation, blogs, component mappings, syntax highlighting, Zod frontmatter validation, or RSS feeds.

67

Quality

84%

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

73%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, highly actionable guide with a genuine seven-step workflow and a strong verification section, undermined mainly by token bloat: it explains MDX basics Claude already knows and inlines ~150 lines of styling, CSS, and test code that belongs in the existing 1300-line companion reference. A minor correctness gap (the undefined getAllPosts loader) is the only executable-code flaw.

Suggestions

Delete the opening conceptual paragraph explaining what MDX is, and move the Shiki CSS block and the vitest example from the Verification section into references/content-patterns.md, keeping only a one-line pointer plus the shell commands.

Trim the step-6 page.tsx to the MDX-relevant parts (generateStaticParams, generateMetadata wiring, MDXRemote usage) and drop boilerplate Tailwind markup Claude can generate, or move the full component to the companion reference.

Define `getAllPosts()` in the step-2 content.ts example (mirroring getPost) so the imported loader in step 6 actually exists, keeping the code assembly gap-free.

DimensionReasoningScore

Conciseness

The body opens by explaining a concept Claude already knows ("MDX blends standard Markdown formatting with executable React/JSX components..."), and several long inline blocks — the full ~50-line Tailwind-styled page.tsx, the complete Shiki CSS block, and an entire vitest test file — restate standard React/Next.js patterns Claude can produce unaided. This fits anchor 3 (mostly efficient but includes some unnecessary explanation or could be tightened); it is not anchor 2's pervasive padding, nor anchor 4 where only minor trims are needed.

3 / 5

Actionability

Guidance is largely copy-paste ready: install commands, a complete Zod schema, full loader/engine/plugin configs, and complete route handlers. However, step 6 imports and calls `getAllPosts` from "@/lib/content" but only `getPost` is ever defined, and `lib/content.ts` imports the type `PostFrontmatter` as a value-style import — real gaps a user would hit when assembling the files, matching anchor 4 (mostly executable with minor gaps) rather than 5.

4 / 5

Workflow Clarity

Seven numbered steps build in a coherent dependency order (schema → engine → plugins → highlighting → components → routing → feeds) and a dedicated Verification section provides explicit checkpoints with runnable commands (`npx tsc --noEmit`, `npm run build`), browser-inspection checks, feed/OG validation, and a unit test for the validate/reject loop. This matches the anchor-5 pattern of clear sequencing with explicit validation steps.

5 / 5

Progressive Disclosure

The single companion reference (references/content-patterns.md, which exists in the bundle) is clearly signaled early and one level deep, and the body is well-sectioned. However, substantial detail that belongs in the companion guide — the full Shiki CSS, the complete test file, and the fully styled page component — is inlined in SKILL.md, fitting anchor 4 (good structure, minor organization gaps) rather than 5's clean split.

4 / 5

Total

16

/

20

Passed

Description

88%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 with explicit what-and-when structure, third-person voice, and multiple concrete actions on a clearly named domain. The only weakness is trigger coverage: it lacks the .mdx file extension, "MDX files" as a natural phrase, and Next.js, while a few generic trigger terms create minor overlap risk with adjacent skills.

DimensionReasoningScore

Specificity

The description lists four concrete actions — "Manage, validate, compile, and render MDX (Markdown + JSX) content" — mirroring the anchor's comprehensiveness of multiple specific actions. It is not vague or padded; each verb names an operation on the named domain.

5 / 5

Completeness

It explicitly answers both questions: the "what" is "Manage, validate, compile, and render MDX (Markdown + JSX) content in modern web applications" and the "when" is an explicit "Use when..." clause enumerating concrete trigger scenarios (content pipelines, documentation, blogs, Zod validation, RSS feeds). This matches the anchor-5 example structure exactly; anchor 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

"Use when building content pipelines, technical documentation, blogs, component mappings, syntax highlighting, Zod frontmatter validation, or RSS feeds" offers good natural-keyword coverage, but common variations users would actually say are missing — notably the ".mdx" file extension, "MDX files", and "Next.js". This fits anchor 4 (good coverage, a few natural terms missing) rather than anchor 5's comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

The MDX (Markdown + JSX) niche is distinct and Zod frontmatter validation is a strong differentiator, but standalone triggers like "syntax highlighting", "RSS feeds", and "technical documentation" could each fire for non-MDX skills (Shiki/Prism skills, feed generators, general docs tools), giving minor overlap risk with closely related skills — anchor 4 rather than 5.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (538 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

administrakt0r/pro-skills-repo-administraktor

Path

skills/development-skills/mdx-content-management/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.