automation

Automation and verification guide for running Native SDK apps. Use when the user asks to test a running app, inspect runtime state, list windows, wait for readiness, drive widgets, take deterministic screenshots, send bridge commands, debug why automation is not connected, create smoke tests, or verify a Native SDK example in a GUI-capable session.

Quality

86%

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

Quality

Content

81%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 body is highly actionable with executable commands, a clear validated workflow, and strong debugging guidance. It leans slightly verbose in the longer prose sections, and the reference-heavy material could be split into one-level-deep files to ease navigation.

Suggestions

Tighten the long compound sentences in workflow steps 6-16 (e.g., widget-hold, wheel, pinch) into shorter statements or a table of command/semantics/failure-reason columns to improve conciseness.

Move the dense file-protocol field descriptions (snapshot.txt/windows.txt/command.txt/bridge-response.txt) into a short reference table rather than inline prose paragraphs.

Consider extracting the detailed screenshot determinism semantics and the 16-step workflow into a one-level-deep reference file (e.g., references/commands.md) to keep SKILL.md as a lean overview pointing to detail.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes competence, but several sections (the 16-step workflow with long compound sentences, the file-protocol field descriptions) carry over-explanation that could be tightened into shorter prose or tables.	3 / 5
Actionability	Fully executable, copy-paste-ready commands throughout ("native automate wait", "native automate assert 'gpu_nonblank=true'", a complete bridge JSON example, screenshot commands), covering the common cases.	5 / 5
Workflow Clarity	A clear numbered Standard workflow is paired with explicit validation ("automate assert" polls and prints missing patterns, bridge error codes, protocol-mismatch rebuild guidance) and feedback loops for error recovery and stale-instance debugging.	5 / 5
Progressive Disclosure	Well-organized single file with clear section headers and a self-contained overview; structure is good but the ~250-line body is substantial for one file with no one-level-deep reference files to offload the denser 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.

The description is specific, complete, and distinct, clearly stating both what the skill does and when to use it with concrete natural-language triggers. Minor room to add a few synonyms, but overall very strong.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — "test a running app", "inspect runtime state", "list windows", "wait for readiness", "drive widgets", "take deterministic screenshots", "send bridge commands", "debug why automation is not connected", "create smoke tests" — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ("Automation and verification guide for running Native SDK apps") and when ("Use when the user asks to test a running app..." with concrete trigger phrases).	5 / 5
Trigger Term Quality	Good keyword coverage with natural user phrasings ("list windows", "take deterministic screenshots", "send bridge commands", "debug why automation is not connected", "create smoke tests"), but a few natural synonyms or variations are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Native SDK app automation via file-based IPC) with distinct triggers unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 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: vercel-labs/native
Path: skill-data/automation/SKILL.md
Commit: 80d1c46

Reviewed: 7 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.