callstackincubator/apex-software-factory / .agents/skills/agent-device
agent-device
VerifiedDrive the Apex Factory app on a leased iOS simulator or Android emulator with agent-device through .agents/scripts/device-lane.sh — open the app, read the accessibility snapshot, tap, type, scroll, verify with wait/is/get, take screenshots, record evidence, and write or replay agent-device .ad scripts (the e2e tests under apps/mobile/e2e/). Use for any interaction with a device, when writing an e2e: test, or when someone says "check it on the simulator", "tap through the app" or "dogfood the app".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.4 KB |
| SOURCE.md | markdown | 1.4 KB |
| references/android-emulator.md | markdown | 1.5 KB |
| references/dogfood.md | markdown | 933 B |
| references/ios-simulator.md | markdown | 1.6 KB |
references/dogfood.md
View on GitHub# Dogfood (exploratory QA)
Vendored from upstream `skills/dogfood/SKILL.md` (see `../SOURCE.md`) and adapted: the
upstream version check and its `allowed-tools` line are dropped, because the pinned
devDependency is the only agent-device here, and every device command goes through
`.agents/scripts/device-lane.sh ad …` on a leased device.
Use it when someone asks to QA, dogfood, bug hunt or explore the app on a device. Read the
current CLI guidance first:
```bash
pnpm exec agent-device help dogfood
```
Loop: open the app (`device-lane.sh ad open com.callstack.apexfactory --foreground`) →
`ad snapshot -i` and `device-lane.sh screenshot <name>` → explore flows → capture evidence per
issue → `ad close`. Findings come from runtime behaviour, not from reading source. Let
`help dogfood` provide the report shape and evidence commands; each issue found becomes its own
`bug:new` issue (delivery rule 8), never a fix.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |