Readme Reviewer — Data & AI agent for Claude Code
Strict README / repo top-page reviewer.
How to install Readme Reviewer
Installs to ~/.claude/agents/shimo4228-claude-harness-readme-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/shimo4228/claude-harness/HEAD/agents/readme-reviewer.md -o ~/.claude/agents/shimo4228-claude-harness-readme-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Readme Reviewer does
name: readme-reviewer description: "Strict README / repo top-page reviewer. Reviews READMEs for LLM-read floor recovery, lead clarity, human hook, scannability, length discipline, and visual effectiveness. Use PROACTIVELY after drafting or substantially revising a README, as a panel reviewer (findings) alongside readme-clarity-reviewer, after the readme-judge draft gate, before the binding final judgment and the human gate." tools: ["Read", "Grep", "Glob", "Bash"] model: sonnet origin: shimo
Alternatives in Data & AI
- Visual Explainer — Agent skill + prompt templates that generate rich HTML pages for visual diff reviews, architecture overviews 6.8k ★
- LLM AI Hunter — LLM and Agentic AI vulnerability specialist 812 ★
- Multi Agent Systems Architect Agent — Systems architect specializing in the design, coordination, and governance of multi-agent AI pipelines — cover 669 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Task Reviewer
Strict quality reviewer for implementation task files. Validates completeness, self-containment, and clarity f
Performance Analytics
Analyzes learning effectiveness, generates performance insights, visualizes skill/agent trends, and provides o
Figure Engineer
Produces every code-rendered figure: diagrams (Mermaid, D2, Graphviz), charts from data (matplotlib, Vega-Lite
SOUL
You are Iris, a personal AI assistant built for speed and simplicity. Be direct: match the length of your repl
Context Quality Reviewer
Reads CLAUDE.md and .claude/rules/ for a project and evaluates quality via LLM-judgment: length, internal cont
Part 11: Auto-Capture Hook (Stop Manually Writing Memory)
By Terp - Terp AI Labs --- The vault system from Part 9 is powerful, but there's a gap: you have to manually w
Related Skills
Portable Agent Project Operating Protocol
Portable Markdown rules and shell tools for agent discipline: two governance modes (strict approval / autonomo
Find Company Name
Generate short brand-name candidates, score each (length, memorability, brandability, cross-language safety, s
Meta
Evaluate a prompt for clarity and effectiveness