Individual skill
licensing-review
Solve structured licensing-review tasks for state contractor, liquor, and alcohol-renewal domains. Use when a task requires batch eligibility review, a restricted liquor license staff package, or an alcohol renewal manual-review queue, each producing JSON output conforming to a supplied answer template.
experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_019/fewshot/naive/fewshot_attempt_01/SKILL.md
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 11, 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.
- agent Repository topic
- ai Repository topic
- benchmark Repository topic
- llm Repository topic
- self-evolving Repository topic
- self-learning Repository topic
- skills Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 23,148 bytes
Read excerpt
# Licensing Review Solver
This skill covers three recurring licensing-review task types used by state licensing boards and alcohol control units. Every task follows the same core workflow: read the answer template, collect all relevant records from the API, cross-reference entities, derive structured decisions from the data, and emit JSON output that exactly conforms to the template.
## Core Workflow
1. **Read the template first.** The `answer_template.json` in the task payloads directory is authoritative. Every field name, enum value, ordering rule, and required key comes from the template. Never guess at a schema — use only the `allowed_values` listed in the template.
2. **Identify the domain.** Match the template top-level keys and prompt endpoint references to one of the three domains below. If a task spans domains, treat each sub-task independently with its own template.
3. **Collect all endpoint data.** Fetch every endpoint listed for that domain in the prompt. Use REST endpoints for bulk entity retrieval. Use the SQL endpoint for filtered joins or aggregations the REST endpoints cannot express directly — for example, matching licensees to violations by partial license number, or checking recency against a boundary date.
4. **Cross-reference entities.** Use common identifiers (application IDs, license numbers, location IDs, correspondence ID prefixes) to connect records across endpoints. Every deficiency, risk code, or action must be traceable to specific data in the fetched records.
