Menu

Individual skill

crm-service-ticket-sop

Use this skill for CRM/support-console tasks that ask Codex to resolve or classify support tickets, mobile service cases, queue snapshots, or enterprise export complaints using customer, account, line, bill, plan, device, outage, diagnostic, SLA, or incident records. Trigger whenever the task says to use a shared support console API and return JSON matching an answer template.

experiments/codex_gpt5_5_xhigh/reports/skills/task_group_003/self/self_attempt_01/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
Yes
Observed behavior
Instructions only
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
121
Repository last updated
Oct 29, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# CRM Service Ticket SOP

## Operating Loop

1. Read the prompt, every input payload, and the answer template before querying records.
2. Use the support-console base URL from the harness/prompt; if a staged `environment_access.md` provides `GDPEVO_ENV_BASE_URL`, use that. Check `/health` only to confirm the service is reachable.
3. Do not inspect local environment source, evaluator files, train answers, judge feedback, or other attempts. Resolve from payloads plus support-console records.
4. Prefer targeted lookups for known IDs:
   - `/api/tickets/<ticket_id>`, `/api/accounts/<account_id>`, `/api/diagnostics/<ticket_id>`
   - `/api/cases/<case_id>`, `/api/lines/<line_id>`, `/api/devices/<device_id>`, `/api/customers/<customer_id>`
   - `/api/bills/<bill_id>`, `/api/plans/<plan_id>`
5. Use `/api/search?q=<exact id or keyword>` to gather cross-record evidence. Search ticket IDs, account IDs, service areas, incident IDs, enterprise account IDs, client names, products, channels, owners, and important failure keywords. Filter search results back to the exact case/account/incident so nearby generated records do not leak into the decision.
6. Return only JSON conforming to the answer template. No prose, markdown, comments, or extra keys.