Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

revyl-mcp-analyze

Sterne499

Forks23

Aktualisiert20. Februar 2026 um 22:02

Analyze failed Revyl MCP test executions and classify them as real bugs, flaky tests, infra issues, or test-design improvements.

Installation

Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.

In Manus ausführen

Quelle

RevylAI

RevylAI/revyl-cli

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

Softwarequalitätssicherungsanalysten und -testerInformatik- und Mathematikberufe·SOC 15-1253

SKILL.md

readonly

name	revyl-mcp-analyze
description	Analyze failed Revyl MCP test executions and classify them as real bugs, flaky tests, infra issues, or test-design improvements.

Revyl MCP Analyze Skill

Evidence Flow

Start from task ID after run_test.
Pull status payload:
- get_test_status(task_id="...")
Inspect failed step expectations and observed reasoning.
Classify:
- REAL BUG
- FLAKY TEST
- INFRA ISSUE
- TEST IMPROVEMENT
Recommend exact next tool/action.

Classification Rules

REAL BUG: actions complete but app behavior contradicts expected outcome.
FLAKY TEST: app behavior is acceptable but validation is too brittle.
INFRA ISSUE: no meaningful app steps executed or setup/device/build failure.
TEST IMPROVEMENT: test structure is weak or allows ambiguity.

Required Output

Task: <task-id>
Classification: <REAL BUG | FLAKY TEST | INFRA ISSUE | TEST IMPROVEMENT>
Confidence: <HIGH | MEDIUM | LOW>
Evidence:
- Expected: <summary>
- Observed: <summary>
- Why: <short rationale>
Next action:
- <specific update_test / rerun / bug filing action>

Mehr aus diesem Repository

gleiches Repository

revyl-ci-sync

RevylAI/revyl-cli

Keep a repo's Revyl remote build mirrored with its CI pipeline - update both in the same PR and debug drift between them.

2026-07-22499

revyl-cloud-agent

RevylAI/revyl-cli

Revyl conventions for Cursor Cloud/background agents - headless VM rules, remote builds, artifact evidence, session cleanup, and PR flow.

2026-07-22499

revyl-mcp-dev-loop

RevylAI/revyl-cli

MCP dev-first mobile loop for reliable screenshot-observe-action execution and grounded interactions.

2026-07-22499

revyl-cli-auth-bypass

RevylAI/revyl-cli

Set up test-only auth bypass for Revyl runs across Expo, React Native, native iOS, native Android, and Flutter apps.

2026-07-22499

revyl-cli-dev-loop

RevylAI/revyl-cli

Generic CLI-first Revyl dev loop for hot reload, rebuild-loop, and device exploration.

2026-07-22499

revyl-cli-create

RevylAI/revyl-cli

Create robust Revyl E2E tests using CLI commands from app source analysis or exploratory sessions.

2026-05-25499

name	revyl-mcp-analyze
description	Analyze failed Revyl MCP test executions and classify them as real bugs, flaky tests, infra issues, or test-design improvements.

Revyl MCP Analyze Skill

Evidence Flow

Start from task ID after run_test.
Pull status payload:
- get_test_status(task_id="...")
Inspect failed step expectations and observed reasoning.
Classify:
- REAL BUG
- FLAKY TEST
- INFRA ISSUE
- TEST IMPROVEMENT
Recommend exact next tool/action.

Classification Rules

REAL BUG: actions complete but app behavior contradicts expected outcome.
FLAKY TEST: app behavior is acceptable but validation is too brittle.
INFRA ISSUE: no meaningful app steps executed or setup/device/build failure.
TEST IMPROVEMENT: test structure is weak or allows ambiguity.

Required Output

Task: <task-id>
Classification: <REAL BUG | FLAKY TEST | INFRA ISSUE | TEST IMPROVEMENT>
Confidence: <HIGH | MEDIUM | LOW>
Evidence:
- Expected: <summary>
- Observed: <summary>
- Why: <short rationale>
Next action:
- <specific update_test / rerun / bug filing action>