No description provided.
Structured AI critique for writing and code. Pairs well with annotated-reply and markdown-preview but works standalone.
Self-critique and learning persistence for SovereignClaw agents.
Ingest service for Critique
Multi-model AI verification with adversarial critique. No AI can verify itself — so they verify each other.
Iterative goal-achievement loop for pi — Generator→Critique→Judge, streaming output as it happens
AI design studio for AI RPG Engine — scaffolding, critique, guided workflows, tuning, experiments, studio UX
Multi-model adversarial plan review — orchestrates AI agents to critique and refine implementation plans
Local stdio wrapper for Critique MCP Gateway with API key validation
n8n node for Critique AI search and content API. https://critique-labs.ai/search
MCP server for LLM focus groups to analyze and critique other MCP servers
Multi-model, multi-modal agent harness on top of the GitHub Copilot SDK. Built-in Playwright MCP, screenshot-and-critique loop, pluggable skills.
Structured AI planning with cross-model critique — gigaplan as a pi extension
Claude Code skill que construye landings cinemáticas para cualquier negocio — personal brand, SaaS, agencia, producto, curso, clínica — con Seedance, anti-AI-slop critique y web audit integrados. Made by Carlos Domínguez.
ThreadWeaver — Multi-Agent Debate Plugin for OpenCode. Grok 4.20-style parallel analysis, cross-critique, and weighted synthesis.
Adversarial 3-round marketing review with discipline foreman. Pitcher / Skeptic / Hormozi / Foreman. Claude Code skill for asset-level critique of pages, copy, offers, hooks, ads, and emails. Output under 1,700 tokens.
Continuous code-improvement cycle. Confirms intent + green baseline, scores quality metrics in parallel, snapshots the baseline, hardens findings via a Senior-Principal critique, looks up best practices, triages with a human gate, then iterates through ea
MCP server for pitch deck design — slide structure templates, visual design systems, content frameworks, investor psychology patterns, and deck critique/scoring across seed to Series C stages
Pass-specific text context packs (analysis, critique, synthesis) from a minimal graph-shaped retrieval payload — no DB or engine dependencies.
suggest improvements to Common Forms
The Order of the Agents - multi-model deliberation for consequential decisions. Anonymized critique, aggregator synthesis, rubric-scored review, and shareable HTML decision artifacts.
Critique Common Forms for insensitive language
Refine a change request into an approved plan: analyse intent, draft to a per-execution draft file, critique it in place, promote to plans/, then take it through codeowner approval (either in-session or via an assigned MR).
CSL style for Law and Critique
Distributed project management and code review for Jujutsu
Quality-first AI coding army: single Rust binary that generates production-grade projects via a 9-stage TDD pipeline with a complexity-scaled quality gate (up to 9.2/10)
Interface to the SensCritique API
LLM amplification engine — MCP server with Lua scripting
algocline application layer — execution orchestration, package management
algocline domain model and metrics — pure execution state machine
algocline Lua execution engine — VM, session, bridge
algocline MCP server adapter — thin tool/handler layer over algocline-app
Self-evaluation and reflection loop for LLM agent outputs
CLI for consulting stronger LLMs from your agent workflow
Production-grade AI Agent framework for Rust — ReAct engine, multi-agent, memory, streaming, MCP, IM channels, workflows
The Reasoning Engine — Auditable Reasoning for Production AI | Rust-Native | Turn Prompts into Protocols
critiques your code
zen-and-musashi is a Ruby CLI that gives local, structured terminal wisdom in two modes: calm Zen-style reflection and fierce Musashi-style critique. It works without an API key by default, and can optionally use an LLM when explicitly enabled.
Drop-in Rack middleware that injects a toggle button to render the current page as a hand-drawn-looking lo-fi wireframe. Useful for design reviews, screenshots, and concept critique.