Individual skill

support-console-analyst

Resolve support-console tickets, cases, and enterprise incidents by calling the shared API and applying structured decision rules. Covers ticket triage, mobile-case handling, enterprise export complaints, queue quality, and mobile data recovery.

experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_003/fewshot/naive/fewshot_attempt_03/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

# Support Console Analyst Skill

When a task prompt references a shared support console API at `<TASK_ENV_BASE_URL>`, use the catalog at `GET /api/catalog` to discover available endpoints and record counts. The console provides structured JSON responses for all `GET` calls; there are no mutation endpoints. Follow the decision flows below for each task domain.

## General Workflow

1. Read the task prompt and every file in `payloads/`.
2. If the prompt mentions `<TASK_ENV_BASE_URL>`, substitute it with the actual base URL provided in the task environment.
3. Call `GET /api/catalog` to confirm the available endpoints and understand the record counts. This helps scope parallel lookups.
4. Identify the task domain from the prompt and payload structure, then follow the domain-specific decision flow.
5. Construct the answer JSON to match exactly the `answer_template.json` provided in the payloads. Preserve payload ordering (e.g., ascending `ticket_id` or `case_id` order as encountered in the input).
6. Validate that every enum value, summary count, and calculated numeric field is consistent with the API evidence collected.

## Task Domain: Ticket Batch / Queue Quality (Internet, Voice, Video)