CtrlK
BlogDocsLog inGet started
Tessl Logo

markstream-nuxt

Integrate markstream-vue into a Nuxt 3 or Nuxt 4 app. Use when Codex needs client-only boundaries, SSR-safe setup, browser-only peer gating, worker-aware initialization, renderer `mode` selection, or a safe `MarkdownRender` integration inside pages, components, or Nuxt plugins.

66

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/markstream-nuxt/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, decision-rich integration guide that assumes Claude's competence and points cleanly to upstream docs, but it repeats several SSR/mode rules across sections, omits any executable plugin/page code skeleton, and gives only a generic validation step without an error-recovery loop.

Suggestions

Add one minimal executable example: a `.client` Nuxt plugin or `<client-only>` page snippet registering MarkdownRender with a representative mode prop set, so the guidance is copy-paste ready.

De-duplicate the SSR smooth-streaming and html-policy/Mermaid rules between the Workflow and Default Decisions sections—state each once and cross-reference.

Make the validation step concrete and add a feedback loop, e.g. name the command (`nuxt typecheck`) and specify 'on hydration mismatch, revert smooth-streaming to auto and re-run'.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence—no "what is SSR/Nuxt" explanations—and is dense with actionable prop guidance, but key SSR/mode rules are restated across Workflow (lines 29, 30) and Default Decisions (lines 37, 41, 42), adding redundant tokens. It is not level 3 because of this repetition; not level 1 because the content is lean and free of beginner padding.

2 / 3

Actionability

Concrete prop values (mode, smooth-streaming, fade, typewriter, html-policy, mermaid-props) and CSS import paths are specific, but there is no executable integration skeleton showing how to register a Nuxt plugin or place MarkdownRender in a page. It is not level 3 because nothing is copy-paste ready; not level 1 because the decision-level guidance is specific and actionable rather than abstract.

2 / 3

Workflow Clarity

A clear 6-step numbered sequence exists with a validation step (step 6: "Validate with the smallest relevant Nuxt dev, build, or typecheck command"), but the validation is generic with no named command and no error-recovery feedback loop for the risky SSR/hydration case. It is not level 3 because there is no explicit fix-and-revalidate loop; not level 1 because steps are clearly sequenced and validation is at least mentioned.

2 / 3

Progressive Disclosure

The under-50-line body is split into well-organized sections (Workflow, Default Decisions, Useful Doc Targets) with one-level-deep, clearly signaled doc paths (docs/nuxt-ssr.md, docs/guide/installation.md, etc.). Per the simple-skills note, this qualifies for level 3; it is not level 2 because navigation is clear and nothing is monolithic or nested.

3 / 3

Total

9

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, specific description that clearly states both the integration purpose and concrete Nuxt/SSR trigger conditions in third-person voice. It avoids vague fluff and is unlikely to fire for unrelated skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—"client-only boundaries", "SSR-safe setup", "browser-only peer gating", "worker-aware initialization", "renderer `mode` selection", "MarkdownRender integration"—matching the level-3 anchor of several specific concrete actions. It is not level 2 because the action set is comprehensive rather than partial, and uses third-person/ imperative voice with no first/second person.

3 / 3

Completeness

Explicitly answers what ("Integrate markstream-vue into a Nuxt 3 or Nuxt 4 app") and when ("Use when Codex needs client-only boundaries, SSR-safe setup, ...") with an explicit "Use when" trigger clause. It is not level 2 because the when-clause is explicit rather than implied.

3 / 3

Trigger Term Quality

Natural Nuxt-developer triggers are well covered: "Nuxt 3 or Nuxt 4 app", "client-only boundaries", "SSR-safe setup", "MarkdownRender", "Nuxt plugins". It is not level 2 because common variations are present rather than only some keywords; not below 3 even though "browser-only peer gating"/"worker-aware initialization" are technical, since the surrounding terms a user would actually say dominate.

3 / 3

Distinctiveness Conflict Risk

Narrow niche scoped to markstream-vue inside Nuxt 3/4 with SSR-specific triggers, making conflict with other skills unlikely. It is not level 2 because the trigger set is highly specific rather than broadly overlapping.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Simon-He95/markstream-vue
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.