Skills and agents designed for academic research workflows, econ-flavored. Made by Claude, for Claude. For Codex, see below for installation instructions.
| Skills | Description |
|---|---|
worktree-data-sync | multi-agent work in parallel in different worktrees with isolated data |
work-journal | Teach agents how to document and report the results |
draft-reviewer | Comprehensive review of a paper draft. Even better, it can fixes things |
review-doc-commit | Make sure we commit the right stuff |
zotero-connector | Read papers from Zotero library |
pdf2markdown-converter | Convert PDFs to markdown via Mistral OCR |
uv — Python scripts use PEP 723 inline metadata for auto-installing dependencies# Add marketplace
/plugin marketplace add FuZhiyu/AgentContract
# Install individual plugins
/plugin install zotero-connector@FuZhiyu-AgentContract
/plugin install pdf2markdown-converter@FuZhiyu-AgentContract
/plugin install work-journal@FuZhiyu-AgentContract
/plugin install ./plugins/zotero-connector
# Update marketplace listing
/plugin marketplace update FuZhiyu-AgentContract
Create .claude/agent-contract.yaml (per-project) or ~/.config/agent-contract/config.yaml (global):
paper-reader:
mistral_api_key: "sk-..."
zotero_api_key: "..."
zotero_library_type: "user"
zotero_library_id: "12345"
work-journal skill: formal, fact-checked journal entries with citations and report-checker verificationreport-in-markdown skill: pure IO tool for saving markdown reports (no content rules)Tell Codex:
Fetch and follow instructions from https://raw.githubusercontent.com/FuZhiyu/AgentContract/main/CODEX_INSTALL.md
Detailed docs: CODEX_INSTALL.md
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub fuzhiyu/agentcontract --plugin worktree-data-syncDisciplined AI Research Assistant for economists: plan-implement-integrate workflow with implementer–reviewer pair, data-analysis discipline, and drift-test-verified integration.
Convert PDFs to Markdown using Mistral OCR API with image extraction
Working journal entries and markdown report generation for academic research
Read and analyze academic papers from Zotero library
Review code, update documentation, and create well-organized topical git commits
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.