MCP App StoreMCP App Store
from auto-claude-code-research-in-sleep10,964
Zero-context auditor that verifies every numeric claim in a paper against raw result files to catch rounding, cherry-picks, and config mismatches.
A zero-context evidence auditor for research papers. The skill spawns a fresh reviewer agent that reads only the paper source files (.tex) and raw result files (JSON/CSV/etc.) and checks each numeric claim (percentages, comparisons, deltas) against the raw data. It reports exact matches, acceptable rounding, and material mismatches with precise locations and recommended fixes.
Use before submission, after a paper-writing loop, or any time you need an independent verification that reported numbers, tables, and captions faithfully reflect raw outputs. Trigger when preparing to submit, during final review, or after automated result-generation.
Best used with high-reasoning models and agent runners — example families: Claude Code, GPT-5.x (codex-like reviewer threads), and other LLM agents capable of structured audit runs.
Paper Claim Audit is a zero-context verification skill for ML research papers that cross-checks numeric claims against raw result files. It has no bundled scripts — purely instructional SKILL.md with a detailed audit protocol, verdict decision table, and JSON artifact schema. The skill is well-documented with clear failure modes but requires a specific agent infrastructure (Codex, shared-references, review tracing) to function end-to-end.
No scripts to execute — static analysis only. Well-structured skill with clear audit protocol. Niche audience (ML researchers verifying paper claims). The spawn_agent pattern for cross-model review is interesting but creates a hard dependency on specific agent orchestration infrastructure.
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
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.
CTF Write-up Generator
Generate a concise, reproducible submission-style CTF writeup with a one-path solution script, metadata, and a short checklist for fast verification.
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.
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
CTX Link Check — Documentation Link Auditor
Scan project markdown for broken internal links, missing images, and unreachable external URLs; produce a clear report and suggested fixes before docs releases.
Symbol — Policy Tagging / Semantic Marker
Define and apply named policy 'symbols' (machine-readable tags) that trigger enforcement actions like audit logging, throttling or compliance gates when conditi