MCP App StoreMCP App Store
from auto-claude-code-research-in-sleep10,964
Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including...
Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including...
Use when user asks for: Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says , , , ai-research, ai-tools, aris, autonomous-agent
Scripts: none
References: none
Sibling files: SKILL.md
Claude Code, Codex, OpenAI/GPT
A comprehensive grant proposal drafting skill supporting 9 international grant agencies (KAKENHI, NSF, NSFC, ERC, DFG, SNSF, ARC, NWO, plus generic). Well-structured 5-phase workflow with checkpoints, state persistence, and Codex MCP integration for external review. No scripts to run — purely instruction-based. SKILL.md is very long and detailed with agency-specific templates, cultural norms, and drafting guidelines. Minor security concern: references to `mcp__codex__codex` and `mcp__codex__codex-reply` tools which could exfiltrate proposal content to external APIs, and shell commands in style-ref section with `git rev-parse` and fallback paths.
Well-crafted skill for an academic audience. Heavy reliance on chaining other skills in the same ecosystem (auto-claude-code-research-in-sleep repo). Security deductions: -5 for mcp__codex tool usage sending proposal content externally (consent-based, but still data leaving), -5 for shell command execution in style-ref section with path traversal patterns. Architecture is good but SKILL.md is monolithic — should use references/ for grant-type specs. Usefulness is moderate: niche academic audience, specific to researchers writing grant proposals, requires the full skill ecosystem to function.
arXiv Paper Search & Download
Search arXiv, fetch paper metadata, download PDFs, and produce concise summaries for academic papers (ID or query).
Paper Writing Pipeline
Orchestrates a complete pipeline to go from a research narrative to a polished LaTeX PDF, including planning, figure generation, LaTeX writing, compilation and
Paper Claim Audit
Zero-context auditor that verifies every numeric claim in a paper against raw result files to catch rounding, cherry-picks, and config mismatches.
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
Codex Collab
Bridge Claude and Codex to run tasks, perform code reviews, and run background jobs for research or implementation workflows.
Smalltalk MCP
Connects an LLM (Claude/OpenAI/etc.) to a live Smalltalk (Squeak/Cuis) image over MCP for browsing, evaluating and modifying Smalltalk code.
Cross-Project Analytics
Query local, privacy-safe cross-project analytics to report on agent, skill, hook, and team performance; replay sessions and estimate token costs.
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
Claude Code (Clawdbot)
Wrapper to run the local Claude Code CLI in headless or interactive (tmux) modes for code analysis, refactors, tests, and structured output.