Skill comparison
Use this as a shortlist, then open the skill detail page before adopting.
Decision summary
Strongest overall
Humanizer
Use this as a leading candidate, then validate the README and install path in your own agent stack.
Fastest prototype
Humanizer
Best first install candidate based on install readiness and adoption.
Freshest repo
unslop
Most recent maintenance signal among this shortlist.
| Signal | pr-writer Create or refresh reviewer-facing PR titles and descriptions. Use when opening a PR, updating its title or body, or preparing branch changes for review. | stop-slop Eliminates predictable AI writing patterns from prose while preserving specific meaning and reader trust. | unslop Applies Cursor's prose-discipline rules to remove filler and AI writing tells from agent-facing and user-facing text. | Humanizer Rewrites AI-sounding text so it reads naturally while preserving every factual claim and matching the writer's voice. |
|---|---|---|---|---|
| Quality | 77/100 Strong | 100/100 Excellent | 100/100 Excellent | 100/100 Excellent |
| Decision verdict | 88/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack. | 100/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack. | 100/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack. | 100/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack. |
| Adoption | 979 stars Verified outcomes are shown on each skill page | 16K stars Verified outcomes are shown on each skill page | 4.8K stars Verified outcomes are shown on each skill page |
| 37K stars Verified outcomes are shown on each skill page |
| Freshness | Aug 25, 2026 | Sep 2, 2026 | Sep 7, 2026 | Jun 7, 2026 |
| Use-case fit |
| Workflow fit |
| Platform hints | Claude Code | Codex, Claude Code, Cursor, OpenAI Agents | Codex, Claude Code, Cursor, OpenAI Agents | Codex, Claude Code, Cursor, OpenAI Agents |
| Warnings | No critical security issues found. The skill relies on standard git and gh commands, and explicitly instructs to avoid including secrets or PII. · No OpenAgentSkill engagement data yet | No OpenAgentSkill engagement data yet | Repository license is unclear and requires review before redistribution. · No OpenAgentSkill engagement data yet | A current third-party Snyk audit reports a failure; inspect the audit before installation. · No OpenAgentSkill engagement data yet |
| Best for | GitHub automation workflows · Claude Code teams · teams that value GitHub adoption signals | Coding agents workflows · Claude Code teams · teams that value GitHub adoption signals | Coding agents workflows · Claude Code teams · teams that value GitHub adoption signals | Coding agents workflows · Claude Code teams · teams that value GitHub adoption signals |
| Not ideal for | teams that need a vendor-supported SLA · production agents without a repository review | teams that need a vendor-supported SLA · high-compliance environments without internal security review | teams that need a vendor-supported SLA · production agents without a repository review | teams that need a vendor-supported SLA · production agents without a repository review |
| OpenAgentSkill engagement | 0 views 0 install copies | 0 views 0 install copies | 0 views 0 install copies | 0 views 0 install copies |
| Install | $ npx skills add getsentry/skills --skill pr-writer | $ npx skills add hardikpandya/stop-slop --skill stop-slop | $ npx skills add cursor/plugins --skill unslop | $ npx skills add blader/humanizer --skill humanizer |