Dialogflow Cx Agents

Manage agents in Google Dialogflow CX via REST API. Use for creating, listing, updating, and deleting chatbot agents. Supports v3beta1 API.

Security Scan

The skill's code and instructions match its stated purpose (managing Dialogflow CX agents); it requires Google Cloud credentials (gcloud or a service account) and the google-cloud-dialogflow-cx library, which is coherent with the functionality.

Purpose & Capability

Name and description (Dialogflow CX agent management) align with the included scripts and SKILL.md. The Python CLI uses the google-cloud-dialogflow-cx client and exposes list/get/create/update/delete/export/validate operations — all expected for this purpose.

Instruction Scope

SKILL.md contains concrete curl examples and a CLI usage for the included script. It instructs using gcloud auth or a service account and to provide PROJECT_ID, LOCATION, AGENT_ID, or full agent names. It does not attempt to read unrelated system files or send data to non-Google endpoints. Note: SKILL.md references the environment variable GOOGLE_APPLICATION_CREDENTIALS and a TOKEN variable (from gcloud) — these are normal but are not declared in the registry metadata.

Install Mechanism

No install spec in registry; the script recommends installing standard PyPI packages (google-cloud-dialogflow-cx, google-auth) via pip. No downloads from unknown URLs or extraction of remote archives are present.

Credentials

The skill requires Google Cloud credentials to operate (gcloud auth / bearer token or GOOGLE_APPLICATION_CREDENTIALS pointing to a service account JSON). Those credentials are appropriate and necessary for Dialogflow management, but the registry metadata lists no required env vars — SKILL.md uses environment variables that the metadata did not declare.

Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. It does not modify other skills or system-wide settings. Exporting agents writes to a local file (as expected) or references a GCS URI, which is within scope.

Assessment

This skill appears to do only Dialogflow CX agent management. Before installing: (1) Be prepared to authenticate with gcloud or provide a service-account JSON (GOOGLE_APPLICATION_CREDENTIALS) — treat that JSON like sensitive credentials and use least-privilege roles. (2) Install the listed Python packages in an isolated environment (venv) so third-party libs don't affect system packages. (3) Review the included scripts locally if you want to verify behavior; exports write agent content to disk. (4) Note the registry metadata did not list the env vars referenced in SKILL.md (TOKEN and GOOGLE_APPLICATION_CREDENTIALS), so ensure you supply credentials only when you trust the runtime.

Manage Google Dialogflow CX agents via REST API.

Prerequisites

• Google Cloud project with Dialogflow CX API enabled
• Service account or OAuth credentials with Dialogflow API access
• gcloud CLI authenticated OR bearer token

Authentication

Option 1: gcloud CLI (recommended)

gcloud auth application-default login
TOKEN=$(gcloud auth print-access-token)

Option 2: Service Account

export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account.json"
TOKEN=$(gcloud auth application-default print-access-token)

API Base URL

https://dialogflow.googleapis.com/v3beta1

Regional endpoints available:

• https://{region}-dialogflow.googleapis.com (e.g., us-central1, europe-west1)

Common Operations

List Agents

curl -X GET \
  "https://dialogflow.googleapis.com/v3beta1/projects/${PROJECT_ID}/locations/${LOCATION}/agents" \
  -H "Authorization: Bearer ${TOKEN}"

Create Agent

curl -X POST \
  "https://dialogflow.googleapis.com/v3beta1/projects/${PROJECT_ID}/locations/${LOCATION}/agents" \
  -H "Authorization: Bearer ${TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "displayName": "My Agent",
    "defaultLanguageCode": "en",
    "timeZone": "Asia/Kolkata"
  }'

Get Agent

curl -X GET \
  "https://dialogflow.googleapis.com/v3beta1/projects/${PROJECT_ID}/locations/${LOCATION}/agents/${AGENT_ID}" \
  -H "Authorization: Bearer ${TOKEN}"

Update Agent

curl -X PATCH \
  "https://dialogflow.googleapis.com/v3beta1/projects/${PROJECT_ID}/locations/${LOCATION}/agents/${AGENT_ID}" \
  -H "Authorization: Bearer ${TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "displayName": "Updated Agent Name"
  }'

Delete Agent

curl -X DELETE \
  "https://dialogflow.googleapis.com/v3beta1/projects/${PROJECT_ID}/locations/${LOCATION}/agents/${AGENT_ID}" \
  -H "Authorization: Bearer ${TOKEN}"

Key Resources

Resource	Description
Agents	Top-level container for flows, intents, entity types

Quick Reference

For detailed API reference:

• Agents: See references/agents.md

Scripts

• scripts/agents.py — CLI wrapper for agent management operations

Usage

python scripts/agents.py list --project PROJECT_ID --location LOCATION
python scripts/agents.py create --project PROJECT_ID --location LOCATION --name "My Agent"
python scripts/agents.py get --project PROJECT_ID --location LOCATION --agent AGENT_ID
python scripts/agents.py update --agent AGENT_NAME --name "New Name"
python scripts/agents.py delete --agent AGENT_NAME

Tips

• Use locations/global for multi-region agents
• Agent IDs are generated automatically on creation