CtrlK
BlogDocsLog inGet started
Tessl Logo

create-litert-lm-android-demo-app

Guides the agent to orchestrate and implement a standalone LiteRT-LM Android demo app with backend selection and multi-modality support using Bazel 9. Use when asked to create a demo app for LiteRT-LM on Android. Don't use for general Android app development without LiteRT-LM, or for building the core library alone without an app.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

The content is a well-structured, highly actionable orchestration workflow with strong validation gates and clean progressive disclosure via real reference files. The main weakness is emphatic redundancy that inflates token cost without adding information.

Suggestions

Consolidate the compliance-gating rules stated in 'Core Constraints & Technical Rules' with the re-statements in the Execution Steps to remove duplicated rationale.

Reduce emphatic filler ('STRICTLY FORBIDDEN', repeated 'You MUST') — state rules once in imperative voice; the constraints section already establishes authority.

Trim explanatory phrasing around constraints (e.g., 'To prevent context pollution and early phase-leakage, you MUST NOT...') to lean imperatives that assume Claude's competence.

DimensionReasoningScore

Conciseness

The body is mostly efficient orchestration logic, but heavy emphatic redundancy ('STRICTLY FORBIDDEN', repeated 'You MUST') and re-stated compliance gating across the Core Constraints and Execution Steps could be tightened.

3 / 5

Actionability

Concrete artifacts and specifics throughout — exact files (task.md, compliance_review_*.md), NDK version 27.3.13750724, default model URL, Pixel 10 — but some steps defer detail to reference files or are user-prompt placeholders, leaving minor gaps.

4 / 5

Workflow Clarity

Seven sequenced steps with sub-steps, explicit validation checkpoints (3.3, 3.4/4.4/5.4 audits, 6.1-6.3 sign-off), feedback loops (verify-before-declaring-failure, re-validation), and compliance checklists for a complex process.

5 / 5

Progressive Disclosure

SKILL.md is a clear overview with well-signaled, one-level-deep references (dependency_source_build.md, dependency_maven_integration.md, ui_layout_and_state.md, inference_implementation.md, three compliance checklists), all of which exist in references/ and are loaded just-in-time.

5 / 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.

The description is specific, complete, and distinctive with a clear what/when structure plus negative boundary guidance. Trigger-term coverage is strong but could add common synonyms like 'sample app'.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete capabilities — 'orchestrate and implement a standalone LiteRT-LM Android demo app with backend selection and multi-modality support using Bazel 9' — giving comprehensive, specific action coverage.

5 / 5

Completeness

Explicitly answers both what ('orchestrate and implement... demo app') and when ('Use when asked to create a demo app for LiteRT-LM on Android'), plus a concrete negative boundary ('Don't use for...').

5 / 5

Trigger Term Quality

'Use when asked to create a demo app for LiteRT-LM on Android' supplies natural, relevant keywords, but misses common synonyms a user might say like 'sample app' or 'example app'.

4 / 5

Distinctiveness Conflict Risk

Targets a narrow, well-defined niche (LiteRT-LM Android demo with Bazel 9) and explicitly excludes general Android dev and core-library-only builds, minimizing conflict 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
google-ai-edge/LiteRT-LM
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.