home/roleplay/cot-v5

Cot v5

GPTClaudeGemini··1,192 copies·updated 2026-07-14
cot-v5.prompt
Evaluate CEFR proficiency using systematic reasoning. KEY PRINCIPLE: Proficiency = linguistic complexity, NOT text length.

ANALYSIS SEQUENCE:

Phase 1 - GRAMMATICAL COMPLEXITY (Independent of length):
- Tense system: limited (A2) vs. full range (B2+)?
- Clause structure: coordination only or complex embedding?
- Modal/conditional use: absent, present, or sophisticated?

Phase 2 - LEXICAL ANALYSIS (Quality over quantity):
- Vocabulary: survival, functional, or specialized?
- Word choice: generic (B1) or precise (C1)?
- Idiomatic/colloquial language present?

Phase 3 - DISCOURSE CAPACITY (Structure vs. length):
- Cohesion method: explicit linkers or implicit flow?
- Argumentation: simple listing or developed reasoning?
- Register variation: fixed or flexibly controlled?

Phase 4 - ADVANCED FEATURE CHECK (Prevent under-prediction):
- B2 indicators: Does text show subordination complexity + hypotheticals + abstract concepts?
- C1 indicators: Does text show register control + sophisticated reasoning + cohesive discourse?
- C2 indicators: Does text show idiomatic authenticity + pragmatic subtlety?
- WARNING: Don't default to B1 if these exist!

Phase 5 - CLASSIFICATION (Feature presence determines level):
When features suggest adjacent levels, select the more advanced.
Brevity with complexity = high proficiency.
Length without complexity = low proficiency.

Essay text:
{essay_text}

Conclude with ONLY: A2, B1, B2, C1, or C2

fill the variables

This prompt has 1 variable. Pro fills them into a ready-to-paste prompt for you — no manual find-and-replace.

{essay_text}
Unlock with Pro →

when to use it

Community prompt sourced from the open-source GitHub repo SiemonCha/ECM3401-LLM-Essay-Scoring (MIT). A "Cot v5" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

roleplaycommunitygeneral

source

SiemonCha/ECM3401-LLM-Essay-Scoring · MIT