By fuzhiyu
Working journal entries and markdown report generation for academic research
Review analysis code for correctness and adherence to project guidelines. Focus on data integrity, merge correctness, and empirical research best practices. Check if implicit data handling (like missing values) aligns with analytical objectives.
Verify work journal reports are factually accurate and follow guidelines. Checks that all claims are supported by code/output evidence, no speculation or economic interpretation without context, and proper citations throughout.
Use this agent when you need to create a comprehensive markdown summary of analysis results after outputs have been generated and saved. Pass the objective of the analysis and the outputs to the agents and let them to write the summary.
Report back to the user in a well-formatted markdown file for readability. Use this skill PROACTIVELY when the output is lengthy or refers to figures/tables/or latex math, or when users request a markdown report.
Create formal, fact-checked work journal entries after completing analysis work. Use when user asks to "summarize work", "document results", or "create work journal entry". Ensures code is committed, copies figures to attachments, and creates objective summaries with mandatory citations and report-checker verification. For quick reports without fact-checking, use the `report-in-markdown` skill.
Uses power tools
Uses Bash, Write, or Edit tools
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.
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
npx claudepluginhub fuzhiyu/agentcontract --plugin work-journalDisciplined 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
Read and analyze academic papers from Zotero library
Review code, update documentation, and create well-organized topical git commits
Multi-agent academic paper review with mathematical, writing, consistency, and proofreading analysis
Personal skills: scholar-agent, web-fetcher, cmux, codex-review, codex-task, daily-summary, init-project, notion-lifeos, paper-analyzer, paper-self-review, project-review, experiment-registry, handoff, sync-docs, remote-cluster-agent, context-audit, bibtex-fetch, todo-worker
11 research-hub skills: literature triage matrix, context compression, project orientation, design dialog, multi-AI routing, NotebookLM brief verification, paper-memory builder, paper summarizer, Zotero curator, the gap-to-topic decision dossier, and the research-hub orchestrator. Auto-discovered from skills/<name>/SKILL.md.
Semi-automated research assistant for academic research and software development, with skills for literature review, experiments, analysis, writing, and project knowledge management
Manage your academic publication pipeline from Claude Code — list, search, create, move, analyse, export BibTeX, track reminders, and sync papers (GitHub + Overleaf) via the Kabbo MCP server.
A research infrastructure for AI agents. Search, read, and analyze papers from your local knowledge base while coding. Includes arXiv discovery, layered reading, ingestion, topic modeling, citation graphs, insights analytics, Office document inspection, scientific tool docs, and academic writing workflows. Requires Python 3.10+ and pip install.
Academic research agents — hypothesis generation, experiment design, paper drafting, peer review simulation, and more.