Big Picture Reviewer — Data & AI agent for Claude Code
Reviews PRs for alignment with stated goals, detects "CI chasing" anti-patterns, and ensures AI agent/skill instructions stay up to date with code changes.
How to install Big Picture Reviewer
Installs to ~/.claude/agents/freenet-freenet-agent-skills-big-picture-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/freenet/freenet-agent-skills/HEAD/agents/big-picture-reviewer.md -o ~/.claude/agents/freenet-freenet-agent-skills-big-picture-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Big Picture Reviewer does
name: big-picture-reviewer description: Reviews PRs for alignment with stated goals, detects "CI chasing" anti-patterns, and ensures AI agent/skill instructions stay up to date with code changes. Critical for catching removed tests/fixes and stale automation rules. tools: Read, Grep, Glob, Bash, WebSearch model: sonnet
Big Picture Reviewer Agent
You are a strategic reviewer who ensures PRs actually solve their stated problems and don't inadvertently remove important code.
Backgro
Alternatives in Data & AI
- GitHub Issues Specialist — GitHub Issues and Pull Requests specialist optimized for AI-agent workflows 1.5k ★
- Anti AI — 去 AI 味管线——读 writer 的 draft,经 Phase 1-4 检测和清除 AI 痕迹,不改剧情只改表达 669 ★
- Anti AI Detector — AI痕迹检测器,专门识别和消除程式化、机械化的AI写作痕迹 234 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
AI Author
The team's maintainer of agent instructions (Emily). Author and maintain a repository's agent instructions — A
Mp Goal Assessor
Read-only, fresh-context assessment of a completed masterplan run's declared goals. Consumes goals.md as QUOTE
Source Acquisition
Run all search rounds, citation chasing, triage, and downloads for a deep research session. Returns a compact
Problem Framer
Turns an idea, feature request, or complaint into a stated problem with a named ICP, a dated why-now, and a fa
John Sterman
System Dynamics modeler and reviewer in the manner of Prof. John D. Sterman (MIT). Two modes: modeler-blind bu
Claude Advisor
Second-opinion advisor running Claude's most capable model (Fable 5). Consult at commitment boundaries — befor
Related Skills
Big Picture
Answers you can judge and act on without reading code — Claude Code plugins that keep implementation detail be
Gsd 2 Next
A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work
Intent Drift Skill
Detects intent drift in AI-assisted development by comparing original goals against current execution plans us