multi-platform-apps-multi-platform

Build and deploy the same feature consistently across web, mobile, and desktop platforms using API-first architecture and parallel implementation strategies.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/multi-platform-apps-multi-platform/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete multi-agent prompts and a clear phased structure, but it lacks validation checkpoints between phases and does not use progressive disclosure to split detailed per-platform guidance into references.

Suggestions

Add explicit validation/checkpoint steps between phases (e.g., 'Validate the API contract before starting parallel implementation' and 'Confirm feature parity before optimization') with feedback loops on failure.

Move detailed per-platform implementation prompts into separate reference files (e.g., references/web.md, references/ios.md) and keep SKILL.md as a concise overview with one-level-deep links.

Tighten the inline subagent prompts to reduce repetition of shared context that is already established in earlier phases.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete subagent prompts and no padding about concepts Claude already knows, but the long inline prompts could be tightened and some sections restate context unnecessarily.	2 / 3
Actionability	It provides concrete, copy-paste-ready Task tool invocations with explicit subagent_type values and detailed prompt specifications for each phase and platform.	3 / 3
Workflow Clarity	The phases are clearly sequenced (sequential design, parallel implementation, integration) but there are no explicit validation checkpoints or feedback loops between phases despite batch-style multi-agent operations.	2 / 3
Progressive Disclosure	The skill is a single monolithic file with no bundle files or external references; it is section-organized but content that could be split (per-platform specs, prompts) is kept inline.	2 / 3
	Total	9 / 12 Passed

Description

35%Weight 40%Scale 1-3

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 states what the skill does in a niche domain but omits any explicit trigger guidance and leans on technical jargon rather than natural user phrasing. It is distinct enough to be useful but not maximally clear about when to invoke it.

Suggestions

Add an explicit 'Use when...' clause with natural user phrasing (e.g., 'Use when the user asks to ship the same feature to web, iOS, Android, and desktop at once').

Replace jargon like 'API-first architecture and parallel implementation strategies' with concrete, user-facing trigger terms such as 'cross-platform feature', 'feature parity', or 'build for multiple platforms'.

Specify the kinds of features or the platforms more concretely to raise specificity and reduce overlap with generic full-stack skills.

Dimension	Reasoning	Score
Specificity	It names concrete actions ('Build and deploy') and the multi-platform domain (web, mobile, desktop) but does not enumerate the kinds of features involved, so it is not fully comprehensive.	2 / 3
Completeness	It answers 'what' the skill does but provides no explicit 'when to use it' guidance, so per the rubric it caps at 2.	2 / 3
Trigger Term Quality	It relies on technical jargon ('API-first architecture', 'parallel implementation strategies') rather than natural phrasing a user would say, and includes no 'Use when...' trigger terms.	1 / 3
Distinctiveness Conflict Risk	'Multi-platform feature development' is a recognizable niche, but the description is generic enough that it could overlap with general full-stack or cross-platform skills.	2 / 3
	Total	7 / 12 Passed

Validation

100%

Warnings & errors only

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: rmyndharis/antigravity-skills
Path: skills/multi-platform-apps-multi-platform/SKILL.md
Commit: e63f7dd

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

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.