Avoid Ai Writing vs Open Code Review
Open Code Review leads on trust: 93.8/100 (Grade A) against 88.1/100 (Grade A), a 5.7-point gap. Avoid Ai Writing leads on maintenance; Open Code Review leads on supply-chain integrity and adoption.
Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, Codex, and Hermes.
Choose Avoid Ai Writing if maintenance matters most.
- +0.9Maintenance
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
Choose Open Code Review if supply-chain integrity and adoption matter most.
- +4.7Adoption: 85.1k weekly downloads against 1.4k
- +3.9Safety / Integrity: 100% of recent commits signed, against 33%
Where they differ
1 dimension identical: Identity 18.0 · Full evidence table
An independent, evidence-based trust comparison of Avoid Ai Writing and Open Code Review, two Agent Skills projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | Avoid Ai Writingconorbronsdon/avoid-ai-writing | Open Code Reviewalibaba/open-code-review |
|---|---|---|
| HVTrust score | 88.1 | 93.8 |
| Evidence grade | A | A |
| Coverage grade | B | B |
| Overall rank | #6 | #1 |
| Rank in Agent Skills | #6 | #1 |
| GitHub stars | 5.2k | 47.9k |
| Last updated | 1d ago | 1d ago |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 7.1 / 10 | 7.5 / 10 |
| License | MIT | Apache-2.0 |
| Downloads | 1k/wk | 85k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 18.0 | 21.9 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 14.5 | 14.9 |
| Maintenance / 20 | 19.9 | 19.0 |
| Adoption / 20 | 13.1 | 17.8 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 1 — Anthropic | 1 — Anthropic |
| Requires API keys | No | No |
| Plugin surface | plugins | plugins |
| Provenance drift | Match | Match |
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →