home/writing/cot-v6

Cot v6

GPTClaudeGemini··1,193 copies·updated 2026-07-14
cot-v6.prompt
Assess CEFR level through methodical analysis. CRITICAL: Length and proficiency are independent dimensions.

EVALUATION STEPS:

Stage 1 - SYNTACTIC EXAMINATION (Complexity ≠ length):
- Verb morphology: basic forms or full paradigm including modals?
- Sentence architecture: simple/compound or complex subordination?
- Structural sophistication evident regardless of essay length?

Stage 2 - LEXICAL EVALUATION (Precision over size):
- Semantic range: concrete only or including abstract concepts?
- Lexical precision: approximate or exact meaning?
- Authentic idiom/collocation use?

Stage 3 - DISCOURSE ASSESSMENT (Quality over quantity):
- Textual cohesion: conjunctions (B1) or implicit links (C1)?
- Rhetorical development: enumeration or argumentation?
- Register management: fixed or situationally appropriate?

Stage 4 - LEVEL-SPECIFIC DIAGNOSTICS (Avoid B1 bias):
- B2 requirements: Complex subordination + conditionals + abstraction capacity
- C1 requirements: Register flexibility + argumentative depth + discourse-level control
- C2 requirements: Native-like idiom + pragmatic awareness
- ALERT: If present, do NOT assign B1 by default!

Stage 5 - FINAL DETERMINATION (Feature-driven):
Between adjacent levels with mixed features, assign higher level.
Concise but complex text indicates advanced proficiency.
Elaborate but simple text indicates intermediate proficiency.

Essay:
{essay_text}

Final output 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 v6" 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

writingcommunitygeneral

source

SiemonCha/ECM3401-LLM-Essay-Scoring · MIT