CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

push-notifications

Implement or debug local and APNs notifications, permissions, payloads, categories, actions, silent pushes, and notification extensions. Use for alerts, badges, sounds, background delivery, rich content, registration, or delivery diagnosis; route Live Activity updates to activitykit.

Quality

91%

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

86%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-engineered overview: executable code, exact APNs contracts, and disciplined externalization of depth into a genuine, verified reference bundle. The two weaker spots are the redundant Contents TOC and workflows that verify outcomes but never state what to do when a verification checkpoint fails.

Suggestions

Remove or shorten the 'Contents' section — its nine anchor links duplicate the section headers immediately below it and cost tokens without adding navigation the headers don't already provide.

Add a short failure-recovery note to the Core workflow or Review checklist (e.g., 'when a boundary check fails, re-run only the checks upstream of that boundary') to close the validate-without-retry gap in workflow_clarity.

DimensionReasoningScore

Conciseness

The body is contract-dense and assumes competence (e.g., the payload/delivery table, terse mistake lists) with no padding explaining known concepts, but the 9-link Contents TOC duplicates section headers and a few advisory sentences could be trimmed — efficient with minor over-explanation, anchor 4 rather than the fully lean anchor 5.

4 / 5

Actionability

Copy-paste-ready Swift snippets (token hex conversion, UNUserNotificationCenterDelegate), exact payload/header contracts ("content-available: 1", "mutable-content: 1", priority "5"), and concrete correction recipes ("download a supported file to disk, then construct UNNotificationAttachment") cover the common cases, matching the fully executable anchor.

5 / 5

Workflow Clarity

The 6-step core workflow ends in explicit per-boundary verification ("Verify each boundary independently: scheduling/provider acceptance, device receipt, extension execution, presentation, and response routing") and a 12-item review checklist exists, but there is no explicit failure-recovery path telling the reader where to loop back when a checkpoint fails, so it sits at anchor 4 rather than 5's validate-fix-retry loops.

4 / 5

Progressive Disclosure

Task-based routing ("For service-extension mutation and exactly-once completion, read service extensions") points to 11 verified one-level-deep reference files, bulk content is properly externalized (669/756-line 'complete' files stay out of SKILL.md), and explicit scoping guidance ("Do not read every reference for a narrow task") makes navigation easy — matching the top anchor; sibling cross-links are lateral hops from the hub, not buried nesting.

5 / 5

Total

18

/

20

Passed

Description

92%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 concrete, third-person capability statements, an explicit 'Use for' trigger clause, and clear boundary routing to sibling skills. The only weakness is that the ubiquitous phrase 'push notification' is never stated verbatim, slightly weakening trigger matching for the most common user phrasing.

DimensionReasoningScore

Specificity

"Implement or debug local and APNs notifications, permissions, payloads, categories, actions, silent pushes, and notification extensions" lists multiple concrete actions (implement, debug) with comprehensive coverage of sub-areas, matching the comprehensive anchor; anchor 4's 'minor gaps in coverage' does not apply.

5 / 5

Completeness

It explicitly answers both "what" (implement/debug notifications, permissions, payloads, categories, actions, extensions) and "when" ("Use for alerts, badges, sounds, background delivery, rich content, registration, or delivery diagnosis") with concrete trigger phrases, matching the top anchor; anchor 4's 'when could be more explicit' does not fit.

5 / 5

Trigger Term Quality

Natural user terms are present ("alerts, badges, sounds, background delivery, rich content, registration, or delivery diagnosis"), but the most common phrasing "push notification" appears only obliquely via "silent pushes" and "APNs notifications", so a few natural terms are missing (anchor 4, not 5).

4 / 5

Distinctiveness Conflict Risk

It occupies a clear notification niche and explicitly reduces conflict by routing adjacent domains out ("route Live Activity updates to activitykit"), giving distinct triggers with minimal overlap risk.

5 / 5

Total

19

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

thienqo/ios-skills

Path

skills/push-notifications/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.