Skip to content

poll-poll134/android-blackbox-analysis-skill

android-app-blackbox-competitive-analysis

Verified

Use when users request Android competitor research, systematic feature or interface mapping, evidence screenshots, interaction coverage, comparison-ready product dossiers, or Android system-boundary verification without APK decompilation.

FileKindSize
SKILL.mdskill md3.2 KB
examples/sanitized-complete-example/README.en.mdmarkdown2.0 KB
examples/sanitized-complete-example/README.mdmarkdown1.8 KB
examples/sanitized-complete-example/analysis/capability-matrix.csvother1.3 KB
examples/sanitized-complete-example/analysis/system-interface-evidence.csvother1.2 KB
examples/sanitized-complete-example/evidence/screen-summaries/DEMO-0001_empty-home.mdmarkdown254 B
examples/sanitized-complete-example/evidence/screen-summaries/DEMO-0002_app-picker.mdmarkdown253 B
examples/sanitized-complete-example/evidence/screen-summaries/DEMO-0003_instance-created.mdmarkdown254 B
examples/sanitized-complete-example/evidence/screen-summaries/DEMO-0004_instance-menu.mdmarkdown249 B
examples/sanitized-complete-example/evidence/screen-summaries/DEMO-0005_permission-diagnostics.mdmarkdown463 B
examples/sanitized-complete-example/indexes/control_coverage.csvother1.7 KB
examples/sanitized-complete-example/indexes/coverage_gaps.csvother1.2 KB
examples/sanitized-complete-example/indexes/interface_index.csvother1.1 KB
examples/sanitized-complete-example/indexes/screenshot_index.csvother1.4 KB
examples/sanitized-complete-example/input/capture-plan.csvother638 B
examples/sanitized-complete-example/input/scope.en.mdmarkdown849 B
examples/sanitized-complete-example/input/scope.mdmarkdown760 B
examples/sanitized-complete-example/reports/final-report.en.mdmarkdown3.6 KB
examples/sanitized-complete-example/reports/final-report.mdmarkdown3.1 KB
references/analysis-guide.mdmarkdown2.0 KB
references/evidence-model.mdmarkdown1.9 KB
scripts/build_indexes.mjsexecutablescript6.8 KB
scripts/capture_evidence.shexecutablescript4.8 KB
scripts/image_info.pyexecutablescript1.3 KB
scripts/init_case.shexecutablescript1.3 KB
scripts/package_release.pyexecutablescript2.6 KB
scripts/redact_check.mjsexecutablescript3.1 KB
scripts/scroll_sweep.shexecutablescript2.5 KB
scripts/smoke_test.shexecutablescript1.8 KB
scripts/tap_ui.shexecutablescript1.3 KB
scripts/ui_pick.pyexecutablescript1.9 KB
scripts/validate_example.mjsexecutablescript12.2 KB
scripts/validate_skill.mjsexecutablescript2.6 KB
templates/capability-matrix.csvother126 B
templates/report-template.mdmarkdown1.2 KB
templates/system-interface-evidence.csvother120 B

references/evidence-model.md

View on GitHub
# Evidence Model

## Case layout

```text
case-root/
├── scope.md
├── evidence/
│   ├── screenshots/
│   ├── raw_screenshots/
│   ├── ui_tree/
│   └── runtime/
├── indexes/
│   ├── screenshot_index.csv
│   ├── interface_index.csv
│   ├── control_coverage.csv
│   └── coverage_gaps.csv
├── analysis/
├── reports/
└── templates/
```

## Stable evidence ID

Use `<PREFIX>-<four digits>_<slug>`, for example `EV-0001_first-launch`.

The same base name binds:

- visual evidence;
- UI hierarchy;
- runtime snapshot;
- report statement;
- capability or interface row.

Do not reuse an ID for a different state. Preserve mistaken or partial captures as audit records when they influenced a conclusion; mark their validity instead of silently replacing history.

## Evidence labels

- `[OBSERVED]`: directly visible in a screenshot, UI hierarchy, Android command output, or reproducible state.
- `[COMPUTED]`: generated from evidence, such as a hash, image dimension, count, or coverage result.
- `[INFERRED]`: a bounded interpretation supported by cited observations.
- `[NOT_TESTED]`: visible or expected capability not exercised.
- `[OUT_OF_SCOPE]`: intentionally excluded, such as real payment.

## Separate proof layers

Keep these claims independent:

1. A page or control exists.
2. The control can be activated.
3. A visible result appears.
4. Android runtime state changes.
5. Data persists after restart.
6. External service or API success is proven.

One layer does not automatically prove the next.

## Capture quality

- Keep the original screenshot bytes.
- Record actual format, dimensions, byte size, and SHA-256.
- Treat UI-tree failure separately from screenshot validity.
- Record unavailable camera, login, network, or paid access as a boundary.
- Avoid publishing runtime dumps until identifiers and tokens are reviewed.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall