MCP App StoreMCP App Store
from auto-claude-code-research-in-sleep10,964
Orchestrates a complete pipeline to go from a research narrative to a polished LaTeX PDF, including planning, figure generation, LaTeX writing, compilation and
A full end-to-end paper writing workflow: it generates a paper plan, creates data plots and architecture figures, writes section-by-section LaTeX, compiles the PDF, and runs multi-round automated improvement and audit checks (proof, numeric claims, citations). Designed for research teams that want an automated, reproducible path from narrative or results to submission-ready PDF.
Use this skill when you have a narrative report, experimental results, or a paper plan and want to produce a submission-quality LaTeX paper. It is ideal for ML research papers (ICLR/NeurIPS/ICML/CVPR/ACL) where figures, reproducible plots, and claim audits are needed.
Best suited to agents that can run shell/python helpers and orchestrate sub-skills (Claude Code, Codex, or other LLM agents with Bash and file access).
A comprehensive ML paper writing pipeline skill that orchestrates 5+ sub-skills (planning, figure generation, LaTeX writing, compilation, improvement loop) into a full submission workflow. Extremely detailed SKILL.md with strong documentation, error handling patterns, and assurance levels (draft vs submission). No bundled scripts to test. Requires significant external dependencies (multiple sub-skills, GPT-5.5, Codex MCP, LaTeX toolchain).
Well-architected pipeline skill with thorough documentation. Shell snippets use proper quoting and safe fallbacks. No security concerns. Main weakness is heavy dependency on external skills and tools that may not be available in a standard environment.
arXiv Paper Search & Download
Search arXiv, fetch paper metadata, download PDFs, and produce concise summaries for academic papers (ID or query).
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.
Grant Proposal
Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including...
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
Minimal Run & Audit (repro reporting)
Execute a README-first smoke test and produce standardized reproducibility outputs (`repro_outputs/`) and PATCHES.md — trusted reporting for repo reproduction r
Skill Issue — Skill Auditor
Scan and audit installed agent skills to produce a health report covering inventory, usage, dependency checks, version status, and actionable recommendations.
GRC & Compliance (ServiceNow)
Guides Governance, Risk & Compliance (GRC) work in ServiceNow: policies, controls, risk records, audits and ES5 script examples for automating GRC workflows.
Ubiquitous Language Glossary
Extract a DDD-style ubiquitous language glossary from conversation: identify domain terms, flag ambiguities, propose canonical terms, and write the result to UB
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
Humanize AI Text
Rewrite AI-generated text into more natural, human-like prose using the HumanizerAI API, with before/after scores and credit tracking.
ToolUniverse Gateway
Unified agent gateway to 1000+ scientific tools (bioinformatics, drug discovery, genomics) via Harvard's ToolUniverse, returning JSON for downstream workflows.