メニュー
AI-powered academic paper reviewer. Uses a multi-agent system (Deconstructor, Devil's Advocate, Judge) to analyze papers for logical flaws, contradictions, and empirical validity.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill peer-reviewerコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
SKILL.md を表示中
SOC 職業分類に基づく
| name | peer-reviewer |
| description | AI-powered academic paper reviewer. Uses a multi-agent system (Deconstructor, Devil's Advocate, Judge) to analyze papers for logical flaws, contradictions, and empirical validity. |
| version | 1.0.0 |
A rigorous academic review system that uses multiple AI agents to deconstruct, attack, and judge scientific papers.
Use this skill when:
Run the tool via the Node.js CLI in the installation directory.
Directory: /Users/sschepis/Development/peer-reviewer
node dist/index.js "<path_to_paper_or_raw_text>"
path_to_paper_or_raw_text: either a file path (absolute or relative to the package root) OR the raw text of the paper/claim.The tool outputs a "Merit Report" in JSON format, containing:
overallScore (0-10)defenseStrategysuggestions (list of improvements)dimensions (scores for logic, novelty, etc.)Review a local file:
cd /Users/sschepis/Development/peer-reviewer
node dist/index.js "/Users/sschepis/Desktop/research/draft_v1.txt"
Review a raw claim:
cd /Users/sschepis/Development/peer-reviewer
node dist/index.js "Claim: P=NP because I can solve Traveling Salesman in O(1) by guessing."
Ensure google.json is present in the root directory or GOOGLE_APPLICATION_CREDENTIALS is set if running in a new environment.