CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

astro-project-starter

Scaffold an Astro 5.x project with content collections, islands architecture, framework integrations (React/Vue/Svelte), MDX, view transitions, and multi-adapter deployment.

Quality

73%

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 ./frontend/astro-project-starter/SKILL.md
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 highly actionable, executable reference with a clear scaffold-to-verify workflow, held back by monolithic structure (everything inlined, no reference files), duplicated command listings, and some concept re-explanation Claude does not need. It is a strong quick-start but not a lean overview with progressive disclosure.

Suggestions

Move long-tail detail (SSR/hybrid modes, API endpoints, view transitions, MDX example, Integration Notes) into references/ files (e.g., references/ssr.md, references/integrations.md) and keep SKILL.md as a lean overview with one-level-deep pointers.

Deduplicate: keep the "npx astro add ..." integration commands in one place only, and drop the concept re-explanations in "Key Conventions" that restate what the code examples already demonstrate.

Add an explicit error-recovery step after "npx astro check" (e.g., fix reported diagnostics in the editor and re-run until clean) to turn the final verification into a feedback loop.

DimensionReasoningScore

Conciseness

The body is mostly dense, useful code rather than padded prose, but includes some unnecessary material: the "npx astro add react/vue/svelte/mdx/tailwind" commands appear in full in both "Scaffold Command" and "Common Commands"; the "Key Conventions" section explains concepts Claude largely knows ("islands architecture", "static by default", file-based routing); and the View Transitions section opens with a frontmatter block containing only comments. This matches "mostly efficient but includes some unnecessary explanation or could be tightened".

3 / 5

Actionability

Nearly everything is copy-paste executable: the exact create command, a complete astro.config.mjs, full BaseLayout and page files, working React component, complete content collection schemas with Astro 5 glob loaders, query/render code, API endpoints, and SSR/hybrid config snippets. The common cases of an Astro scaffold are covered with runnable code, matching the fully-executable anchor.

5 / 5

Workflow Clarity

The sequence is clear — scaffold command, add integrations, then the numbered "First Steps After Scaffold" including validation checkpoints ("Verify the app loads at http://localhost:4321" and "Run npx astro check to confirm diagnostics pass"). It falls short of a 5 because there is no error-recovery guidance (what to do when astro check fails) and validation appears only at the end rather than as a feedback loop; this is not a destructive/batch skill so no cap applies.

4 / 5

Progressive Disclosure

The skill has no bundle files at all: all ~530 lines live inline in SKILL.md, including per-pattern detail (SSR snippets, integration notes, MDX example, API endpoints) that clearly belongs in separate reference files. Section headers provide good within-file structure, but there are no references to split content across — matching anchor 3 ("some structure... content that should be separate is inline") rather than anchor 2, since the content is well-sectioned and navigable.

3 / 5

Total

15

/

20

Passed

Description

66%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, specific description with good keyword coverage and a distinct Astro niche. Its main flaw is the absence of any "Use when..." trigger guidance, which caps completeness and weakens its ability to fire at the right moments.

Suggestions

Append an explicit trigger clause, e.g., "Use when starting a new Astro project, migrating a site to Astro 5, or when the user mentions Astro, .astro files, content collections, or islands architecture."

Add a second concrete action verb (e.g., "configure" or "deploy") to move specificity from a single scaffold action toward comprehensive multi-action coverage.

Include natural variations users actually say — "Astro site", "static site generator", ".astro" — to round out trigger term coverage.

DimensionReasoningScore

Specificity

"Scaffold an Astro 5.x project with content collections, islands architecture, framework integrations (React/Vue/Svelte), MDX, view transitions, and multi-adapter deployment" names a concrete action and comprehensively enumerates capabilities. It falls short of a 5 because there is only one action verb ("scaffold") rather than multiple distinct concrete actions, but the capability list is far beyond the 1-2 actions of a 3.

4 / 5

Completeness

The "what" is clear and concrete (scaffold an Astro 5.x project with the listed features), but there is no "Use when..." clause or any equivalent explicit trigger guidance. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3 even with a clear "what".

3 / 5

Trigger Term Quality

Good natural keyword coverage: "Astro", "content collections", "islands", "MDX", "React/Vue/Svelte", "view transitions", "deployment" — terms a user needing this skill would plausibly say. A few natural terms are missing (e.g., ".astro", "static site", "blog"), so it does not reach the comprehensive synonym-plus-extension coverage of a 5, but it clearly exceeds the partial coverage of a 3.

4 / 5

Distinctiveness Conflict Risk

"Astro 5.x" carves out a clear niche with distinct triggers, so conflict risk with unrelated skills is low. However, mentions of "framework integrations (React/Vue/Svelte)" create minor overlap risk with generic React/Vue/Svelte setup skills, matching anchor 4 rather than the minimal-conflict profile of a 5.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (532 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

achreftlili/deep-dev-skills

Path

frontend/astro-project-starter/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.