Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.
Quelle
GitHub
Sprache
Python
Letzte Aktivität
17.10.2026
Sterne166Gemessen · 21.10.2026
Momentum22,47 Tage · Gemessen · +1,84% relative Änderung
Run a company of AI agents on a server you own. Spin up named agents (claude, codex, pi…), put them on an org chart with a shared backlog, let them hand off work and ping your phone only when a human must decide. MIT.
Quelle
GitHub
Sprache
Shell
Letzte Aktivität
21.10.2026
Sterne73Gemessen · 21.10.2026
Momentum22,27 Tage · Gemessen · +2,82% relative Änderung
42 SEO commands for Claude Code — site audits, Ahrefs backlinks, GSC analytics, SERP research, content briefs, technical SEO, schema validation, and more
Quelle
GitHub
Sprache
Python
Letzte Aktivität
11.06.2026
Sterne22Gemessen · 21.10.2026
Momentum21,97 Tage · Gemessen · +4,76% relative Änderung
A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols.
Quelle
GitHub
Sprache
HTML
Letzte Aktivität
27.09.2026
Sterne1.667Gemessen · 21.10.2026
Momentum21,57 Tage · Gemessen · +0,36% relative Änderung
CMMC 2.0 compliance advisor as a Claude Code skill. All 3 levels, 14 domains, 110 practices; CUI scoping, SSP + POA&M; modern IT mapping for cloud, productivity, AI services, endpoints; contractor profiles and anti-patterns. Built from public DoD and NIST sources.
Quelle
GitHub
Sprache
Python
Letzte Aktivität
22.04.2026
Sterne23Gemessen · 21.10.2026
Momentum21,57 Tage · Gemessen · +4,55% relative Änderung