integration-test — end-to-end testing for CommonKnowledgeScout integration-test, CommonKnowledgeScout, community, end-to-end testing for CommonKnowledgeScout, ide skills, integration-test install, integration-test for AI agents, CommonKnowledgeScout testing, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for Testing Agents needing comprehensive end-to-end integration testing for directories with various file formats. Integration-test is a skill that automates end-to-end testing for the CommonKnowledgeScout project, utilizing a dev server and Secretary Service to ensure thorough testing of directories and files.

Features

Runs end-to-end integration tests for the CommonKnowledgeScout project
Supports testing of various file formats, including PDF, Audio, and Markdown
Utilizes a dev server via `pnpm dev` command
Requires Secretary Service to be reachable
Enables test-loop functionality for iterative testing and analysis

# Core Topics

bCommonsLAB bCommonsLAB
[0]
[0]
Updated: 3/8/2026

Agent Capability Analysis

The integration-test skill by bCommonsLAB is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for end-to-end testing for CommonKnowledgeScout, integration-test install, integration-test for AI agents.

Ideal Agent Persona

Perfect for Testing Agents needing comprehensive end-to-end integration testing for directories with various file formats.

Core Value

Empowers agents to test PDF, Audio, and Markdown files, among others, using a dev-server and Secretary Service, enabling a test-loop of Test → Analyse → Fix → Repeat with protocols like pnpm dev.

Capabilities Granted for integration-test

Automating end-to-end integration tests for CommonKnowledgeScout projects
Testing directories with multiple file formats
Initiating test-loops for continuous analysis and fixing

! Prerequisites & Limits

  • Requires dev-server to be running (pnpm dev)
  • Secretary Service must be reachable
  • Limited to specific file formats like PDF, Audio, and Markdown
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

integration-test

Unlock seamless integration testing with our AI agent skill. Learn how to set up end-to-end tests for your CommonKnowledgeScout project and start testing...

SKILL.md
Readonly

Integration-Test Skill

Dieser Skill führt End-to-End Integration-Tests für das CommonKnowledgeScout Projekt aus.

Wann verwenden

  • Wenn der Benutzer "Integrationstest", "teste dieses Verzeichnis" oder ähnliches sagt
  • Wenn der Benutzer ein Verzeichnis mit Dateien (PDF, Audio, Markdown, etc.) testen möchte
  • Wenn der Benutzer den Test-Loop starten möchte (Test → Analyse → Fix → Repeat)

Voraussetzungen

  1. Dev-Server muss laufen (pnpm dev)
  2. Secretary Service muss erreichbar sein (localhost:5001)
  3. MongoDB muss verfügbar sein

Parameter sammeln

Bevor du Tests startest, sammle folgende Informationen vom Benutzer:

ParameterErforderlichBeschreibung
libraryIdJaDie Library-ID (UUID)
folderIdJaDie Folder-ID (Base64-encoded)
userEmailJaE-Mail des Benutzers
fileKindNeinpdf, audio, markdown, txt, website
testCaseIdsNeinKomma-getrennte Liste von Test-IDs

Verfügbare Testcases

Audio

  • audio_transcription.happy_path - Einfache Audio-Transkription
  • audio_transcription.gate_skip_extract - Überspringt Extract wenn Shadow-Twin existiert
  • audio_transcription.force_recompute - Erzwingt Neuberechnung
  • audio_transcription.template_and_ingest - Template + Ingestion nach Transkription

PDF

  • pdf_mistral_report.happy_path - PDF-Extraktion + Template
  • pdf_mistral_report.gate_skip_extract - Überspringt Extract
  • pdf_mistral_report.force_recompute - Erzwingt Neuberechnung
  • pdfanalyse.hitl_publish - Human-in-the-Loop Publishing

Markdown/TXT/Website

  • markdown_ingest.happy_path - Markdown → Template → Ingest
  • txt_normalize.happy_path - TXT → Normalize → Template → Ingest
  • website_normalize.happy_path - Website → Normalize → Template → Ingest

Test-Befehl

Führe Tests mit folgendem Befehl aus:

bash
1pnpm -s test:integration:api -- \ 2 --libraryId <LIBRARY_ID> \ 3 --folderId <FOLDER_ID> \ 4 --userEmail <USER_EMAIL> \ 5 --fileKind <FILE_KIND> \ 6 --testCaseIds <COMMA_SEPARATED_IDS>

Beispiel

bash
1pnpm -s test:integration:api -- \ 2 --libraryId 7911fdb9-8608-4b24-908b-022a4015cbca \ 3 --folderId YXVkaW8= \ 4 --userEmail peter.aichner@crystal-design.com \ 5 --fileKind audio \ 6 --testCaseIds audio_transcription.happy_path,audio_transcription.template_and_ingest

Agent-Loop (Definition of Done)

Führe folgende Schleife aus bis failed = 0:

1. Tests starten

Führe den Test-Befehl aus und warte auf das Ergebnis (JSON).

2. Ergebnis analysieren

Prüfe im JSON:

  • summary.failed - Anzahl fehlgeschlagener Tests
  • results[].messages - Validierungsnachrichten (type: error/warn/info)

3. Bei Fehlern

a) Fehler clustern: Gruppiere ähnliche Fehler nach Message-Text

b) Root-Cause analysieren:

  • Lies den Job via MongoDB oder API
  • Prüfe Trace-Events und Step-Status
  • Identifiziere die fehlerhafte Code-Stelle

c) Minimalen Fix implementieren:

  • 1 Fehler-Cluster → 1 Fix
  • Ändere so wenig Code wie möglich
  • Füge hilfreiche Kommentare hinzu

d) Unit-Tests prüfen:

bash
1pnpm test

4. Wiederholen

Starte die Tests erneut und wiederhole bis alle grün sind.

Globale Contracts (immer prüfen)

Diese Regeln müssen IMMER erfüllt sein:

  1. Leeres Markdown ist ein Fehler - Keine leeren Transcripts/Transformationen
  2. completed ⇒ keine pending Steps - Alle aktivierten Phasen müssen abgeschlossen sein
  3. completed ⇒ keine running Steps - Keine hängenden Steps
  4. phases.X = true ⇒ Step X muss completed sein - Aktivierte Phasen dürfen nicht pending bleiben

Referenz-Dokumentation

Detaillierte Dokumentation findest du in:

  • docs/guides/integration-tests.md - Hauptdokumentation
  • docs/analysis/integration-tests-agent-mode.md - Agent-Modus Details
  • src/lib/integration-tests/test-cases.ts - Testcase-Definitionen
  • src/lib/integration-tests/validators.ts - Validierungslogik

Beispiel-Interaktion

Benutzer: "Teste mir die Audio-Dateien im Testfolder"

Agent:

  1. Fragt nach Library-ID und Folder-ID (falls nicht bekannt)
  2. Führt aus: pnpm -s test:integration:api -- --libraryId ... --folderId ... --fileKind audio
  3. Analysiert das JSON-Ergebnis
  4. Bei Fehlern: Identifiziert Root-Cause, implementiert Fix, wiederholt
  5. Meldet: "Alle X Tests bestanden" oder "Y Fehler gefunden, analysiere..."

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is integration-test?

Perfect for Testing Agents needing comprehensive end-to-end integration testing for directories with various file formats. Integration-test is a skill that automates end-to-end testing for the CommonKnowledgeScout project, utilizing a dev server and Secretary Service to ensure thorough testing of directories and files.

How do I install integration-test?

Run the command: npx killer-skills add bCommonsLAB/CommonKnowledgeScout. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for integration-test?

Key use cases include: Automating end-to-end integration tests for CommonKnowledgeScout projects, Testing directories with multiple file formats, Initiating test-loops for continuous analysis and fixing.

Which IDEs are compatible with integration-test?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for integration-test?

Requires dev-server to be running (pnpm dev). Secretary Service must be reachable. Limited to specific file formats like PDF, Audio, and Markdown.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add bCommonsLAB/CommonKnowledgeScout. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use integration-test immediately in the current project.

Related Skills

Looking for an alternative to integration-test or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI