Skip to content
Skill

Linguistic Review

by bukzor

AI Summary

Linguistic Review is a skill that helps developers understand the behavioral patterns and linguistic choices in Claude's responses by analyzing interpretive possibilities rather than correctness. It's useful for prompt engineers and developers debugging unexpected AI behavior.

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to install the "Linguistic Review" skill in my project.

Please run this command in my terminal:
# Install skill into the correct directory (6 files)
mkdir -p .claude/skills/commands && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/commands/SKILL.md "https://raw.githubusercontent.com/bukzor/dotfiles/main/.claude/commands/why.md" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/commands/breakdown.md "https://raw.githubusercontent.com/bukzor/dotfiles/main/.claude/commands/breakdown.md" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/commands/claude-workshop.md "https://raw.githubusercontent.com/bukzor/dotfiles/main/.claude/commands/claude-workshop.md" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/commands/curl.md "https://raw.githubusercontent.com/bukzor/dotfiles/main/.claude/commands/curl.md" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/commands/frustration.md "https://raw.githubusercontent.com/bukzor/dotfiles/main/.claude/commands/frustration.md" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/commands/lets-commit.md "https://raw.githubusercontent.com/bukzor/dotfiles/main/.claude/commands/lets-commit.md"

Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.

Description

Analyze behavioral causes of Claude responses - linguistic patterns, not correctness

Linguistic Review

You are a reviewer analyzing the previous response to understand what caused unexpected behavior. Focus on what linguistic or contextual elements led to this particular response pattern. Avoid apologetic language, performance judgment, or correctness evaluation.

Analysis

• what happened -- describe the response pattern that occurred • interpretive possibilities -- what different ways could the original prompt have been read? • the path taken -- which interpretation did the previous response follow, and what specific linguistic elements guided this choice? • prevention strategy -- how could the prompt be structured differently to avoid this pattern in future interactions?

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 1mo ago
Active
AdoptionUnder 100 stars
32 ★ · Niche
DocsREADME + description
Well-documented

GitHub Signals

Stars32
Forks6
Issues1
Updated1mo ago
View on GitHub
No License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Claude Code