by InternScience · Codex Skill · ★ 276
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/InternScience/ResearchClawBench.gitTaken from the project's README on GitHub.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 276 |
| Forks | 27 |
| Language | Jupyter Notebook |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 61/100 |
| Open Issues | 1 |
| Last Updated | 2026-10-28 |
| Created | 2026-03-18 |
| Platforms | claude-code, codex |
| Est. Tokens | ~24k |
ResearchClawBench         Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery Quick Start Add Your Agent ResearchClawBench is a benchmark that measures
Looking for a ResearchClawBench alternative? If you're comparing ResearchClawBench with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk
AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk
De-Anthropocentric Research Engine — AI-powered academic research automation with deep literature survey, gap
AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Manage MCP servers, skills and plugins across Claude Code, Codex, Cursor and more. Built-in marketplace, one-c
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: