project-review

A portable project-planning skill for Codex, Claude Code, pi, Hermes, and Agent Skills-compatible harnesses. Evidence before build advice.

Evidence-based review skill for diff, project, and artifact review across code, readiness, architecture, requirements, and risk.

Project-agnostic iterative review with evidence-backed YES, NO, or MAYBE dispositions and mandatory delivery.

Self-hosted AI-native project management for small teams, with MCP project data tools and agent-assisted project review.

北晨 Claude 技能库 — 对抗性项目评估(Advocate→Skeptic→Judge) + 多维产品分析

Transfer all projects, Codex threads, failure reviews, and half-finished ideas into AgentWorkOS: Agents, Memory, Skills, MCP, Workflow, and Rules.

A brutally honest, multi-phase project evaluation tool that systematically dismantles developer enthusiasm. Supports Hermes Agent and OpenClaw.

A modest library of cognitive and analytical exercises for use with Claude Code and expert workflows. Each protocol is designed to help uncover blind spots, reduce bias, and foster deeper insight at key project milestones—complementing routine testing and review processes.

One-command shakedown. Find what breaks before you ship - architecture, security, performance, resilience, docs. Claude Code skill.

A portable Agent Skill for evidence-first project defense review, follow-up questioning, answer scoring, and material repair.

Platform-agnostic AI+X Vibe Coding project review agent package with rubrics, workflows, templates, and human-in-the-loop guidance.

An AI that understands your entire software project—not just your code. It studies your system, turns implementation into architecture-level concepts, and helps you defend, explain, and improve it in interviews, audits, and demos.

Codex project reviews with GPT-6 Sol, Luna high, mandatory Astra xhigh adjudication, scoped repairs, and independent verification.

alphaX source for agent-native research and engineering collaboration with evidence, scope, and review boundaries.