CtrlK
BlogDocsLog inGet started
Tessl Logo

pwa-installability

Use when auditing PWA readiness, adding an install prompt, or preparing a web app for submission to Microsoft Store or Google Play via PWA Builder.

56

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-installability/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 lean overview with excellent progressive disclosure and a concrete criteria checklist, but it stops at telling Claude what to verify without how — no commands, audit tools, or field-level checks — and pads the intro with a known-concept explanation and an engagement statistic. The body reads as a table of contents rather than an actionable procedure.

Suggestions

Cut the 'Studies consistently show… 3× more time' sentence and the explanation of what installable PWAs are; Claude already knows this and it spends tokens without adding action.

Add executable verification means to the Check section, e.g. a Lighthouse PWA audit command or 'DevTools → Application → Manifest' inspection steps with expected outputs.

Turn Check/Fix into an explicit check → fix → re-verify loop ending with a validation checkpoint (all criteria pass before finishing), so the workflow has feedback rather than parallel task descriptions.

DimensionReasoningScore

Conciseness

The body is short and the Quick Reference earns its tokens, but the opening explains what an installable PWA is ('Installable PWAs appear in the browser's address bar install prompt and in app stores, giving users a native-app experience…') — a concept Claude already knows — and the 'Studies consistently show… 3× more time' sentence is motivational padding with no operational value.

3 / 5

Actionability

The Quick Reference criteria are concrete ('Provide a 192×192 and 512×512 icon; add a maskable variant'; 'Register a service worker that responds with 200 when offline'), but Check and Fix offer only high-level direction with no executable means — no Lighthouse/DevTools command, no audit URL, no field-level manifest checks — leaving key details delegated to the reference file.

3 / 5

Workflow Clarity

The body is organized by task mode (Check / Fix / Explain / Code Review) rather than as a sequence; there is no explicit check → fix → re-verify order and no validation checkpoint (e.g., re-run the audit and confirm all criteria pass after fixing). Anchor 3 (steps/criteria listed but checkpoints missing) fits better than 4.

3 / 5

Progressive Disclosure

A short, well-sectioned overview that delegates implementation details to a single, clearly signaled, one-level-deep reference ('For full implementation details, code examples, and framework-specific guidance, see references/rule.md'), which exists in the bundle (192 lines with a manifest code example). Content is appropriately split and navigation is easy.

5 / 5

Total

14

/

20

Passed

Description

70%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 well-scoped trigger description with concrete scenarios and good natural keywords, but it is purely a 'Use when' clause: it never explicitly states what the skill does. Adding a leading capability statement and a few more synonyms ('manifest', 'service worker', 'progressive web app') would lift it further.

Suggestions

Add an explicit 'what' clause before the trigger, e.g. 'Checks a web app against PWA installability criteria — manifest, service worker, HTTPS, and maskable icons — and fixes gaps. Use when…'.

Include additional natural trigger terms users would say: 'progressive web app' spelled out, 'web app manifest', 'service worker', and 'make my app installable'.

Mention the manifest.json file name and Lighthouse/PWA audit phrasing so the skill triggers on code-review and audit requests too.

DimensionReasoningScore

Specificity

Names three concrete actions in a specific domain — 'auditing PWA readiness', 'adding an install prompt', 'preparing a web app for submission to Microsoft Store or Google Play via PWA Builder' — but never states the underlying checks the skill performs (manifest, service worker, HTTPS, icons), so coverage has minor gaps.

4 / 5

Completeness

The 'when' is explicit and specific ('Use when auditing PWA readiness, adding an install prompt, or preparing…'), but no standalone 'what' statement exists — capabilities are only implied by the gerunds inside the trigger clause. This mirrors the anchor-3 pattern (one half explicit, the other weakly implied) rather than anchor 4, where both are present, and is far more concrete than the anchor-2 example.

3 / 5

Trigger Term Quality

Includes natural user terms 'PWA', 'install prompt', 'Microsoft Store', 'Google Play', and 'PWA Builder', but misses common variations users would say such as 'progressive web app' spelled out, 'manifest', 'service worker', or 'make my app installable'.

4 / 5

Distinctiveness Conflict Risk

'PWA', 'PWA Builder', 'install prompt', and the specific store names carve out a clear niche with distinct triggers and minimal risk of firing for unrelated skills.

5 / 5

Total

16

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
thedaviddias/Front-End-Checklist
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.