agentleFS
iblaiiblai/financial-services-agents/skills/servicenow/SKILL.md

servicenow

Skill15 starsChanged 5 months agoMITView on GitHub

ServiceNow IT service management platform; lets an agent create, update, route, and close IT incidents and fraud investigation cases, track SLA compliance, and retrieve asset and configuration records.

  • Reads credentials

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a new IT incident or service request ticket on behalf of a staff member

    line 13
  2. Distinctive:

    Update an existing incident with investigation steps, evidence, or resolution notes

    line 14
  3. Distinctive:

    Check SLA compliance status and flag cases approaching breach

    line 16

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ServiceNow

What it is

ServiceNow is the enterprise IT service management (ITSM) and workflow automation platform used across financial services firms to manage IT incidents, service requests, change management, and business-process case management. In this segment, it serves both the IT Help Desk agent (IT tickets and access requests) and the Fraud Detection agent (fraud investigation case lifecycle management).

When to use this skill

  • Create a new IT incident or service request ticket on behalf of a staff member
  • Update an existing incident with investigation steps, evidence, or resolution notes
  • Route a ticket or fraud case to the appropriate team or owner
  • Check SLA compliance status and flag cases approaching breach
  • Retrieve asset records and configuration items (CIs) for troubleshooting
  • Manage change requests for access provisioning or system modifications
  • Close a resolved case with disposition rationale and final notes

Credentials

This skill authenticates using env vars declared in metadata above. Set them in ~/.openclaw/.env (see .env.example at the config root). Required variables:

  • SERVICENOW_INSTANCE_URL - ServiceNow instance base URL (e.g. https://yourfirm.service-now.com)
  • SERVICENOW_CLIENT_ID - OAuth2 client ID for the integration application
  • SERVICENOW_CLIENT_SECRET - OAuth2 client secret
  • SERVICENOW_API_USER - Service account username (Basic Auth fallback)
  • SERVICENOW_API_PASSWORD - Service account password (Basic Auth fallback)

Key operations

  • POST /api/now/table/incident — create a new incident record
  • GET /api/now/table/incident/{sys_id} — retrieve incident details
  • PATCH /api/now/table/incident/{sys_id} — update incident fields (state, notes, assignment)
  • POST /api/now/table/sn_si_incident — create a security incident (fraud/SOC use cases)
  • GET /api/now/table/cmdb_ci — retrieve configuration items from the CMDB
  • GET /api/now/table/task?sysparm_query=assigned_to=... — list tasks assigned to a user or group

Notes

  • ServiceNow tables and fields are highly customized per deployment; confirm field names (e.g. u_fraud_typology) with your ServiceNow admin before wiring
  • OAuth2 is preferred over Basic Auth; Basic Auth should be disabled in production instances per security policy
  • ServiceNow enforces role-based access at the table level; the integration service account needs the itil role for incident management and a custom role for fraud case tables
  • Sub-production environments (dev, test) are separate instances with independent URLs and credentials

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.