critique

The official repo for “Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem” [EMNLP25]

Cogito: Computational framework employing a Syncretic Catalyst (synthesis) & rigorous Critique System (analysis) autonomously. Deeply accelerates your expert research on scientific literature via LLMs/ArXiv.

智能选择 17 套分析方案的图像分析分流 Skill：先判断该怎么读图，再输出定向分析和学习建议。

A Claude Code skill that injects aesthetic principles from painting, photography, graphic design, and Eastern visual tradition into UI/design decisions.

Critique a database schema for best practices

PromptPotter: AI optimization engine for automated prompt engineering (APE). Searches and tunes prompts and parameters against your data using a generate-evaluate-critique cycle. Improve AI outputs, automate prompt optimization, and fine-tune your pipeline.

Critical Analysis of "Clean Code" by Robert Martin

Code Critics Bar Chart for Pharo Smalltalk

Kant's Critique of Pure Reason: A mind map.

This is the repo for our proposed Feedback Preference corpus

Automatic and zero-shot critique of outputs using the OpenAI API with json outputs

系统拆解 colleague-skill（赛博永生/AI同事克隆）概念缺陷的 Skill。基于心理学偏差、第一性原理和历史教训的反驳武器。

Critarchy is an engine for helping artists improve

Cogito: Computational framework employing a Syncretic Catalyst (synthesis) & rigorous Critique System (analysis) autonomously. Deeply accelerates your expert research on scientific literature via LLMs/ArXiv.

Hierarchical task planning with an LLM critic — a planner decomposes a goal into a typed plan, a critic audits each subtask for feasibility, risk, missing steps, unsafe sequencing, and weak rollback, revising until approval or human escalation.

Multi-agent discussion kit for Claude Code — 27 personas × 4 critique modes, recommendation-first customize

WordShop is a tool for workshopping your writing projects

Evidence-aware adversarial review skill for AI agents

Adversarial code review for pi — a separate model reviews the last work step and feeds the review back as advisory feedback. Independent reviewer, structured Markdown verdict.

A app that lets the users around the world rate products based on the online shop they came from.