Automate PhD/MRes/MPhil application workflows: analyze/polish CVs from files, match professors/universities to your profile via searches, draft personalized cold emails/follow-ups, generate SOPs/proposals/PPTs/interview Q&A, identify research gaps from papers/Zotero.
npx claudepluginhub xujingchen1996/research-app-toolkitGenerate or optimize cold emails for professor outreach
Analyze CV and generate structured profile for research applications
Polish and improve CV for research applications
Assist with application documents (SOP, motivation letter, research proposal, recommendation letter)
Analyze papers for research gaps and generate research ideas
Build or refine a professor-meeting or PhD interview slide deck
Prepare for research program interviews with mock Q&A
Search and match professors for research applications
Recommend and compare schools for research applications
This skill should be used when the user asks to "write a cold email", "draft a 套磁信", "compose outreach email", "follow up professor", "write thank you email", "negotiate offer", or runs /ra:cold-email. It generates and optimizes various types of emails for research application communication.
This skill should be used when the user asks to "analyze my CV", "extract CV profile", "review my resume", "parse my CV", or runs /ra:cv-analyze. It reads a CV/resume and produces a structured capability profile stored in .local.md for other skills to reference.
This skill should be used when the user asks to "polish my CV", "improve my CV", "tailor my CV", "optimize my resume", or runs /ra:cv-polish. It improves CV content, structure, and wording for specific applications.
This skill should be used when the user asks to "write SOP", "draft personal statement", "write motivation letter", "write research proposal", "draft recommendation letter", "help with application essay", or runs /ra:doc-assist. It assists with various application documents.
This skill should be used when the user asks to "analyze research gaps", "find research gaps", "generate research ideas", "discover research opportunities", "analyze papers for gaps", or runs /ra:gap-analysis. It reads a collection of papers, identifies research gaps, and proposes novel research ideas.
This skill should be used when the user asks to prepare a PhD interview deck, professor meeting slides, research presentation PPT, slide-by-slide speaking notes, or to reorganize project materials into interview-friendly slides. It structures CV, project files, and supervisor fit into a concise academic presentation for professor meetings and formal interviews.
This skill should be used when the user asks to "prepare for interview", "practice interview questions", "mock interview", "interview preparation", or runs /ra:interview-prep. It prepares the user for research program interviews.
This skill should be used when the user asks to "find professors", "search for supervisors", "match professors", "find research supervisors", or runs /ra:professor-match. It searches for professors matching the user's research interests and evaluates fit.
This skill should be used when the user asks to "recommend schools", "select universities", "find PhD programs", "choose MRes programs", "compare universities", or runs /ra:school-select. It recommends schools based on user profile and preferences.
Research Application Toolkit is a single repository that ships host-specific integrations for both Claude Code and Codex.
It covers:
npm install -g @xujingchen1996/research-app-toolkit
ratk install
Optional host selection:
ratk install --claude
ratk install --codex
ratk install --all
Default behavior:
ratk install installs to the hosts detected on the current machineratk install --claude installs only the Claude Code pluginratk install --codex installs only the Codex pluginratk install --all installs to every detected host and skips hosts that are not installedYou can also run the installer without a global install:
npx @xujingchen1996/research-app-toolkit install
After installation into Claude Code, use the slash commands:
/ra:cv-analyze
/ra:cv-polish
/ra:professor-match
/ra:cold-email
/ra:doc-assist
/ra:school-select
/ra:interview-prep
/ra:interview-ppt
/ra:gap-analysis
After installation into Codex, use the plugin in chat with prompts such as:
Analyze my CV and extract a research application profile
Match supervisors and schools for my target research area
Draft a bilingual outreach email to a potential supervisor
Help me prepare a professor meeting or PhD interview PPT
The Codex host keeps its own codex/memory.md state and supports zh, en, and bilingual output modes.
research-app-toolkit/
├── .claude-plugin/ # Claude Code manifest
├── .codex-plugin/ # Codex manifest
├── .local.md # Claude Code shared state template
├── assets/ # Shared assets such as the Codex icon
├── commands/ # Claude Code slash commands
├── hooks/ # Claude Code hooks
├── agents/ # Claude Code helper agents
├── skills/ # Claude Code skills
├── codex/
│ ├── memory.md # Codex shared state
│ └── skills/ # Codex skills and bundle manifest
├── bin/ # npm CLI entrypoint
├── lib/ # Installer helpers
├── test/ # Installer tests
├── package.json
└── README.md
ratk CLI rather than host auto-discovery from a cloned repository.~/.claude, ~/.codex, ~/.agents, and Codex caches should not be committed to this repository.npm test
MIT
AI-powered resume builder with job discovery, dual ATS + HR scoring, and cover letter generation. Finds and ranks live job listings by fit, tailors your resume to any JD, auto-detects 6+ professional domains, and produces Workday-compatible DOCX output.
Share bugs, ideas, or general feedback.
Scientific research brainstorming partner: survey the literature, find good problems, and shape concrete research ideas together
Tailored resumes with company research, branching experience discovery, and multi-format output
Interactive 7-level resume coaching process. Transforms generic resumes into compelling, personalized documents through recruiter perspective analysis, gap comparison, and expression discovery.
Intelligence-driven job application system - resume development, interview prep, OSINT intelligence, career strategy, and crisis management using HAM-Z methodology
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.