CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pwa-development

Progressive Web Apps - service workers, caching strategies, offline, Workbox

50

Quality

63%

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 ./skills/pwa-development/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%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 a dense, largely executable PWA reference with strong code examples, but it front-loads everything into one ~950-line SKILL.md with zero bundle files, inlines content that belongs in references, and spends significant tokens on generic web-performance and PWA-primer material Claude already knows. It reads as a reference dump rather than a guided, progressively disclosed skill.

Suggestions

Split the SKILL.md into an overview plus one-level-deep reference files (e.g. references/manifest.md, references/workbox.md, references/frameworks.md, references/offline-page.html) and link to them from a concise summary.

Cut or relocate generic non-PWA material Claude already knows: the "Three Pillars" ASCII primer, the Performance Optimization section (responsive images, code splitting, preload), and the fully styled offline.html.

Replace the topic-per-section layout with a short ordered build workflow (manifest -> SW registration -> caching strategies -> offline fallback -> Lighthouse verification) with explicit validation checkpoints, and de-duplicate the two full manifest JSONs into a minimal one plus a field-reference table.

DimensionReasoningScore

Conciseness

The ~950-line body includes substantial material Claude already knows: an ASCII "THE THREE PILLARS OF PWA" explainer of what HTTPS/service workers/manifests are, a generic "Performance Optimization" section (responsive images, code splitting, preload hints), two near-duplicate full manifest JSONs, and a complete offline.html page with inline CSS. Not score 1 because the PWA-specific sections (caching strategies, Workbox config, push) are on-topic and mostly unpadded.

2 / 5

Actionability

Mostly executable, copy-paste-ready code: a complete basic service worker with install/activate/fetch handlers, registration code, all five caching strategies implemented, Workbox routes with expiration plugins, install-prompt and push-notification handling. Not score 5 because a few examples reference undefined helpers (urlBase64ToUint8Array, showNotification) and the Vite/Workbox configs assume placeholder values without noting them.

4 / 5

Workflow Clarity

Content is organized by topic, not as a sequenced build process; there is no ordered path from manifest to service worker to caching to verification. Validation exists only as testing checklists ("Lighthouse PWA audit passes", manual testing checklist) rather than inline checkpoints, placing it at "sequence/checkpoints implicit". Not score 4 because no explicit ordered workflow ties the pieces together.

3 / 5

Progressive Disclosure

The skill is a monolithic single file: no references/, scripts/, or assets/ directories exist, and ~25KB of content that clearly belongs in separate files (two full manifest JSON examples, the complete offline.html page, framework-specific guides, the full Workbox manual SW) is inlined directly. Not score 1 because section headers (## Service Worker Patterns, ## Caching Strategies, ## Quick Reference) do provide real, navigable structure.

2 / 5

Total

11

/

20

Passed

Description

65%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.

The description identifies a well-scoped, distinctive domain and lists relevant technical keywords, but it reads as a topic list rather than a statement of capabilities, and it lacks an explicit "Use when..." trigger clause, capping completeness. Adding an action-oriented verb phrase and a trigger clause with terms like "PWA" would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when building PWA features, adding offline support, or configuring service workers, caching, or web app manifests."

State capabilities as actions rather than a topic list, e.g. "Builds Progressive Web Apps: implements service workers, configures caching strategies and offline support, and sets up Workbox builds."

Include the common abbreviation and adjacent trigger terms users naturally say: "PWA", "web app manifest", "installable app", "push notifications".

DimensionReasoningScore

Specificity

The description names the domain ("Progressive Web Apps") and several specific technical areas ("service workers, caching strategies, offline, Workbox"), but these are topic nouns rather than concrete actions, so it sits between the domain-plus-1-2-actions anchor and the several-specific-actions anchor. It is above score 2 because the areas enumerated are concrete and specific, not generic.

3 / 5

Completeness

It conveys a clear "what" (PWA topics: service workers, caching, offline, Workbox) but contains no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is above score 2 because the "what" is specific rather than vague.

3 / 5

Trigger Term Quality

Strong natural terms users would actually say: "service workers", "caching", "offline", "Workbox", "Progressive Web Apps". Missing common variations such as the abbreviation "PWA", "push notifications", "install/home screen", and "manifest" prevents a 5.

4 / 5

Distinctiveness Conflict Risk

"Progressive Web Apps - service workers, caching strategies, offline, Workbox" occupies a clear niche with distinct triggers (service workers, Workbox, offline support) unlikely to fire for unrelated skills. No overlap risk is evident.

5 / 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 (961 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

alinaqi/maggy

Path

skills/pwa-development/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.