CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-app-clip

Add an iOS App Clip target to an Expo app. Use when the user mentions App Clip, AASA, apple-app-site-association, appclips, smart app banner, or wants to ship a lightweight iOS Clip invoked from a URL alongside their parent app.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

80%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, well-structured walkthrough: concrete commands and complete config snippets throughout, with the optional native-module detail correctly pushed to a single well-signaled reference file. The main weaknesses are duplicated boilerplate at the top and bottom, and the absence of verification checkpoints around the Apple account and production operations, which the rubric caps at workflow clarity 3.

Suggestions

Add validation checkpoints after the consequential operations: verify registered bundle IDs and printed Team/iTunes IDs after bunx setup-safari, confirm the TestFlight build and Clip target status after bunx testflight, and re-run eas metadata:pull to confirm the pushed appClip metadata, with an if-fails fix-and-retry loop.

Trim duplication: the opening 'When to Use' paragraph restates the frontmatter description almost verbatim, and the generic Limitations section repeats boilerplate caveats already covered by the frontmatter risk note.

Consolidate the merged safety preamble (third paragraph) into the steps where each caution applies, e.g. the AASA merge guidance belongs in step 5 and the permission mirroring guidance in step 8.

DimensionReasoningScore

Conciseness

The body is mostly lean commands and config snippets with almost no explanation of concepts Claude already knows, but it contains trimmable material: the opening paragraph repeats the frontmatter description nearly verbatim, the third paragraph is a long merged safety preamble, and the generic Limitations section repeats boilerplate caveats. Not 5 because of that duplication, and not 3 because there is no padding beyond these minor instances.

4 / 5

Actionability

Every step gives copy-paste-ready shell commands (bun create target clip, bunx setup-safari, eas deploy, eas metadata:pull/push, curl verification) and complete JSON/JS/TSX/Swift/XML snippets with concrete example values. Not 4 because there are no gaps: even edge behaviors like the prebuild warning message and the 1800x1200 PNG constraint are specified.

5 / 5

Workflow Clarity

The ten numbered steps are clearly sequenced, but explicit validation exists only for the AASA deployment (curl check in step 7) and an implicit prebuild warning note; the operations that modify Apple account state and production (bunx setup-safari registration, eas metadata:push, bunx testflight submission) have no verification checkpoints or failure-recovery loops. Per the rubric's cap for workflows involving destructive/consequential operations with missing validation, this cannot exceed 3. Not 4 because the validation gaps are not minor — they cover the riskiest steps — and not 2 because a concrete sequence with two checkpoints is present.

3 / 5

Progressive Disclosure

The core walkthrough is appropriately inline, and the single piece of optional depth (native App Clip detection) is split into ./references/native-module.md, which exists, is one level deep, and is clearly signaled both inline ('See [./references/native-module.md]... for the Swift module, TypeScript interface, and usage') and in a References section. Not 4 because navigation and placement are clean with no organization gaps.

5 / 5

Total

17

/

20

Passed

Description

90%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: third-person, concise, with a comprehensive set of natural trigger terms and an explicit 'Use when' clause. The only gap is that the 'what' clause captures just the headline action rather than the range of concrete outcomes the skill delivers.

Suggestions

Enumerate one or two more concrete outcomes in the what clause (e.g., hosts the AASA file, adds the smart app banner, submits to TestFlight) so specificity matches the skill's actual scope.

Optionally add the term 'App Clip card' or 'invocation URL', which users configuring the launch experience may mention.

DimensionReasoningScore

Specificity

"Add an iOS App Clip target to an Expo app" names the domain and one concrete action, but the description does not list the several specific actions the skill actually performs (AASA hosting, smart app banner, TestFlight submission, store metadata). Not 4 because anchor 4 requires several specific actions listed, and not 2 because the action named is concrete rather than generic.

3 / 5

Completeness

"Add an iOS App Clip target to an Expo app. Use when the user mentions App Clip, AASA, apple-app-site-association, appclips, smart app banner, or wants to ship a lightweight iOS Clip invoked from a URL alongside their parent app" explicitly answers both what and when with concrete trigger phrases. Not 4 because the when clause is already fully explicit with enumerated triggers rather than merely serviceable.

5 / 5

Trigger Term Quality

"App Clip, AASA, apple-app-site-association, appclips, smart app banner" covers the natural phrasing, the abbreviation, the full technical filename, and the spacing/compound variants a user would naturally say. Not 4 because no common synonym or variation for this niche task is missing.

5 / 5

Distinctiveness Conflict Risk

"iOS App Clip target to an Expo app" with triggers like AASA and apple-app-site-association occupies a clear niche with essentially no overlap with other skills. Not 4 because the triggers are uniquely tied to this exact task, giving minimal conflict risk.

5 / 5

Total

18

/

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

boisenoise/skills-collections

Path

skills/antigravity-add-app-clip/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.