vocello-ios-validation
Skill388 starsChanged 21 days agoMITView on GitHub
Validate an iOS change with the smallest repository compile or physical-iPhone XCUITest lane; use for iOS acceptance and targeted device UI verification.
In this repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- website/CLAUDE.mdCLAUDE.md
- vocello-benchmarkSkill
- vocello-debugSkill
- vocello-device-diagnosticsSkill
- vocello-macos-uiSkill
- vocello-release-readinessSkill
- vocello-ui-autonomySkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 0 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Read docs/reference/native-engineering.md, docs/reference/ios-device-testing.md and the applicable Axiom build/testing guidance.
- Very specific: line 13
Use scripts/dev.sh ios for a generic device-SDK compile.
- Very specific: line 15
Before a measured lane join/stop all workers, commit the checkpoint, use scripts/dev.sh doctor, and probe reachability with python3 …
- Very specific: line 17
Before any phone lane quit iPhone Mirroring (scripts/ios_device.sh mirroring stop): XCUITest breaks under it and ui-preflight refuses while …
- Very specific: line 19
When lifecycle tracking is unavailable, declare QVOICE_LEAD_ONLY=1 only after joining all workers.
- Very specific: line 21
Use installed models; new large downloads need specific authorization.
- Very specific: line 22
Read scripts/dev.sh triage <run-directory> --json (the read-only vocello-xcresult-triage agent can take the run directory).
- Very specific: line 24
Never retry silently; a justified rerun gets a new ID and explanation.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
iOS validation
Arguments: $ARGUMENTS
Read docs/reference/native-engineering.md, docs/reference/ios-device-testing.md and
the applicable Axiom build/testing guidance. Commands run from the repository root.
Use scripts/dev.sh ios for a generic device-SDK compile. Choose the smallest relevant existing
lane from scripts/ui_test.sh help for physical-iPhone acceptance; do not substitute another driver.
Before a measured lane join/stop all workers, commit the checkpoint, use scripts/dev.sh doctor,
and probe reachability with python3 scripts/lib/ios_coredevice_probe.py probe; never print device IDs.
Before any phone lane quit iPhone Mirroring (scripts/ios_device.sh mirroring stop): XCUITest breaks
under it and ui-preflight refuses while it runs; the phone must then be unlocked.
When lifecycle tracking is unavailable, declare QVOICE_LEAD_ONLY=1 only after joining all workers.
Explain the lane and expected device interaction, then run scripts/ui_test.sh ios <lane> <options>.
Use installed models; new large downloads need specific authorization. Preserve failed artifacts.
Read scripts/dev.sh triage <run-directory> --json (the read-only vocello-xcresult-triage agent can
take the run directory); report the actual verdict and evidence path.
Never retry silently; a justified rerun gets a new ID and explanation. No Simulator or third-party
UI-automation MCP; computer use through iPhone Mirroring covers what XCUITest cannot, never during a
lane (/vocello-ui-autonomy). After the lane, review <run>/screenshots/index.json.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

