CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

artemis-android-testing

Testa aplicacoes Android em dispositivo ou emulador real. Trigger em: "testa esse apk no emulador", "roda isso no artemis", "abre o emulador e testa", "verifica isso no android", "testa a tela de", "no celular", "simula um usuário tocando", "testa no emulador com IA", "funcionando no android antes de", "antes de dar merge", "antes de commitar", "testa esse app no celular".

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A strongly operational skill file: exact commands, explicit validation steps, and a genuinely useful failure-diagnostics table grounded in a real installation. The only real weaknesses are mild repetition of the API-key caveat, some kit-process boilerplate, and dangling references to kit-level policy files not shipped in the bundle.

DimensionReasoningScore

Conciseness

The body is dense with operational specifics (paths, flags, log markers) and explains nothing Claude already knows, but repeats the sensitive-API-key caveat in three sections ('Governanca Global', 'Quando Nao Usar', 'Anti-Padroes') and includes kit-bookkeeping sections (Handoff, Integracao com Pipeline) that could be trimmed. Efficient with minor instances of over-explanation — anchor 4, not anchor 5's 'every token earns its place'.

4 / 5

Actionability

Fully executable, copy-paste-ready commands with real absolute paths ('"$HOME/AppData/Local/Android/Sdk/platform-tools/adb.exe" devices', 'uv run --env-file .env artemis run "<tarefa>" --profile flash --app-path ...'), exact log lines to look for ('✅ Automation \'<id>\' is success'), and exact error strings mapped to fixes. Covers the common cases (no APK, local APK, locked app, background run) — matches anchor 5.

5 / 5

Workflow Clarity

The 4-step Protocol is clearly sequenced with explicit validation checkpoints: wait for boot and 'checar adb devices de novo antes de prosseguir', and 'Ler o resultado real, não confiar só no exit code' with concrete success/failure log markers. The 'Diagnóstico Rápido de Falha' table (symptom → cause → fix) provides a feedback loop for error recovery, matching anchor 5.

5 / 5

Progressive Disclosure

Good structure: setup detail is correctly split into the real, one-level-deep, well-signaled 'references/setup-local.md', and the body stays an operational overview with clear section headers. Minor gap: 'GLOBAL.md', 'policies/execution.md', 'policies/tool-safety.md', and 'policies/handoffs.md' are referenced but not present in the bundle, matching anchor 4 rather than anchor 5's clean navigation.

4 / 5

Total

18

/

20

Passed

Description

86%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.

A strong description: explicit what-plus-when structure with an extensive list of natural Portuguese trigger phrases that make invocation highly predictable. The main gap is that the capability statement is a single action verb, leaving scope (APK install, video evidence, profile options) to the body rather than the description.

DimensionReasoningScore

Specificity

The 'what' is a single sentence — 'Testa aplicacoes Android em dispositivo ou emulador real' — naming the domain and one concrete action (testing on a real device/emulator) without listing several capabilities (APK install, video recording, trace-based reporting). Above anchor 2 (domain with generic action) but short of anchor 4 (several specific actions listed).

3 / 5

Completeness

Explicitly answers both questions: what ('Testa aplicacoes Android em dispositivo ou emulador real') and when ('Trigger em:' followed by concrete trigger phrases). This matches the anchor requiring both what and when with concrete trigger phrases, so the missing-'Use when' cap does not apply.

5 / 5

Trigger Term Quality

Twelve natural trigger phrases with strong synonym coverage users would actually say: 'testa esse apk no emulador', 'roda isso no artemis', 'no celular', 'testa a tela de', 'simula um usuário tocando', 'antes de dar merge', 'antes de commitar'. Matches anchor 5's comprehensive natural-term coverage; no common phrasing category is visibly missing.

5 / 5

Distinctiveness Conflict Risk

The Android-emulator/Artemis niche is clear ('roda isso no artemis', 'testa esse apk no emulador'), but unqualified triggers like 'antes de dar merge', 'antes de commitar', and 'no celular' could overlap with other testing/verification skills in the same kit. Mostly distinct with minor overlap risk — anchor 4, not anchor 5's minimal conflict risk.

4 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

16

Passed

Repository

felvieira/claude-skills-fv

Path

skills/81-artemis-android-testing/SKILL.md

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.