CtrlK
BlogDocsLog inGet started
Tessl Logo

foundation-models-on-device

Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+. Use when adding on-device LLM features with Apple FoundationModels on iOS 26+.

72

Quality

87%

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

82%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.

An executable, well-structured reference covering FoundationModels patterns with complete Swift examples and explicit availability validation. Verbose at the margins (overlapping 'When to' sections and restated best-practice bullets) and lacks a feedback loop for retryable operations.

Suggestions

Merge the duplicate 'When to Activate' and 'When to Use' sections into one list to remove redundancy.

Trim best-practice bullets that restate what the code examples already demonstrate (e.g. 'Access response.content — not .output').

Add a brief validate/retry loop for tool errors and streaming failures so workflows involving batched or fallible calls have an explicit recovery checkpoint.

DimensionReasoningScore

Conciseness

Mostly lean with executable Swift snippets and a useful decisions table, but the 'When to Activate' and 'When to Use' sections overlap, and the instructions key-points and best-practices lists restate material already shown in code.

4 / 5

Actionability

Copy-paste ready, complete Swift code for every core pattern (availability check, session, @Generable, tools, streaming, SwiftUI integration), with specific API names like response.content and GenerationOptions(temperature:).

5 / 5

Workflow Clarity

Core patterns are presented as clearly sequenced numbered steps (define type -> request output; define tool -> create session -> handle errors), and the availability-check pattern is an explicit validation gate, but there is no validate/fix/retry feedback loop for batch or destructive operations.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections (When to Activate, Core Patterns, Key Design Decisions, Best Practices, Anti-Patterns) with no nested references and no bundle files, but a single 50-line skill could score higher with even tighter separation of quick-start from reference material.

4 / 5

Total

17

/

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 precise, third-person description that names concrete capabilities and an explicit trigger clause tied to a specific framework and platform. Minor improvement available by adding a few more natural synonyms (e.g. Apple Intelligence, structured output).

Suggestions

Add common user-facing synonyms like 'Apple Intelligence' or 'structured output' to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'text generation, guided generation with @Generable, tool calling, and snapshot streaming' — covering the framework's main capabilities comprehensively.

5 / 5

Completeness

Explicitly answers 'what' (text generation, guided generation, tool calling, snapshot streaming) and 'when' ('Use when adding on-device LLM features with Apple FoundationModels on iOS 26+').

5 / 5

Trigger Term Quality

Includes strong natural terms like 'on-device LLM', 'tool calling', 'FoundationModels', and 'iOS 26+', but lacks synonyms such as 'Apple Intelligence', 'structured output', or 'offline inference' a user might naturally say.

4 / 5

Distinctiveness Conflict Risk

Narrow niche tied to a specific framework and OS version (Apple FoundationModels on iOS 26+) with distinct triggers, making overlap with other skills minimal.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
affaan-m/ECC
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.