メニュー
Repository guide for the LMTI multi-skill package. Use when working inside this repo to find the installable skills, human documentation, and scoring implementation quickly.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Self-assess the current LLM with the LMTI-60 questionnaire, answer all 60 questions without user interaction, and return the full answer sheet in strict JSON for later scoring.
Score an LMTI-60 selftest result, compute dimension lean, dominant and secondary types, detect inconsistency from cross-reference clusters, and render the output as markdown, JSON, or HTML.
| name | lmti-repo |
| description | Repository guide for the LMTI multi-skill package. Use when working inside this repo to find the installable skills, human documentation, and scoring implementation quickly. |
This repository contains two installable skills, not one:
.agents/skills/lmti-selftest.agents/skills/lmti-scorelmti-selftest when the task is to answer the LMTI-60 questionnaire and emit strict JSON.lmti-score when the task is to score a prior LMTI answer sheet.README.md, INSTALL.md, docs/.agents/skills/lmti-selftest/references/questionnaire.json.agents/skills/lmti-score/references/framework.json.agents/skills/lmti-score/scripts/score_lmti.pyKeep human documentation at repo root or in docs/.
Keep installable skill folders lean:
SKILL.mdagents/openai.yamlreferences/scripts/ only when determinism is required