agentleFS
ozgurkarahanozgurkarahan/salesforce-meta-tool-identity-propagation/skills/servicenow-itsm/SKILL.md

servicenow-itsm

Skill4 starsChanged 9 months agoMITView on GitHub

How to read and write ServiceNow ITSM data with the servicenow_mcp tools (discover, query, write). Use for any question about incidents, problems, change requests, requested items, approvals or companies in ServiceNow, and before any ServiceNow write.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use mode="names" to validate names only.

    line 17
  2. Very specific:

    If discover returns 403, fall back to the standard fields.

    line 20
  3. Very specific:

    ALWAYS pass fields= with only the columns you need.

    line 29
  4. Distinctive:

    Do not issue separate exact and LIKE queries.

    line 38
  5. Very specific:

    Before ANY write call, show the table, record (number + sys_id), operation and exact field values, then wait for an explicit "yes".

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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 ITSM

Workflow

  1. Pick the table. Common tables need no lookup: incident, problem, change_request, sc_req_item, sysapproval_approver, core_company. Otherwise call discover(filter=...) once.
  2. Learn the fields.
    • Reads: skip discover(table=...) when the standard fields below are enough. Use mode="names" to validate names only; mode="compact" (default) for types and references.
    • Writes: discover(table=..., include_choices=True) is REQUIRED first.
    • If discover returns 403, fall back to the standard fields.
  3. Query with query(table, query, fields, limit).
  4. Summarize in plain language. Never dump raw JSON.

Standard fields: number, short_description, description, priority, state, urgency, impact, category, assignment_group, assigned_to, company, opened_at, sys_created_on. Change requests add: type, risk, start_date, end_date.

Query rules

  • ALWAYS pass fields= with only the columns you need.
  • Encoded query syntax: field=value, fieldLIKEvalue, fieldSTARTSWITHvalue, field!=value, field>value, fieldINa,b, fieldISEMPTY; AND ^, OR ^OR, sort ^ORDERBYfield / ^ORDERBYDESCfield.
  • Priority: 1 Critical (P1), 2 High (P2), 3 Moderate, 4 Low. Incident state: 1 New, 2 In Progress, 3 On Hold, 6 Resolved, 7 Closed. Open incidents: state<6 (or active=true).
  • Company lookups: company references core_company. Use ONE query that covers exact and variant names: company.name=Contoso Ltd^ORcompany.nameLIKEContoso. Do not issue separate exact and LIKE queries.
  • Several companies: combine in one query with ^OR: company.name=Acme Corp^ORcompany.name=Contoso Ltd.
  • Keyword search: query(table, text_search="api gateway", fields=...).
  • Counts/breakdowns: aggregate=True, group_by="priority" instead of fetching rows.

Writes and approvals — mandatory confirmation

  • Updates/deletes need the 32-char sys_id (query it first).
  • Approvals: update sysapproval_approver with state=approved|rejected.
  • Before ANY write call, show the table, record (number + sys_id), operation and exact field values, then wait for an explicit "yes". Never delete without a separate explicit confirmation.

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.