LeoYeAI/agent-master-skills / skills/ai-humanizer
humanizer
VerifiedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 15.8 KB |
| SKILL.md | skill md | 7.8 KB |
| assets/banner.md | markdown | 331 B |
| docs/CONTRIBUTING.md | markdown | 2.0 KB |
| docs/EXAMPLES.md | markdown | 5.3 KB |
| docs/PATTERNS.md | markdown | 2.4 KB |
| eslint.config.js | script | 559 B |
| package.json | manifest | 1.3 KB |
| references/ai-vocabulary.md | markdown | 5.5 KB |
| references/patterns.md | markdown | 10.0 KB |
| references/style-guide.md | markdown | 3.9 KB |
| scripts/analyze.sh | script | 301 B |
| scripts/humanize.sh | script | 315 B |
| src/analyzer.js | script | 14.8 KB |
| src/cli.js | script | 19.6 KB |
| src/humanizer.js | script | 14.2 KB |
| src/patterns.js | script | 28.1 KB |
| src/stats.js | script | 9.5 KB |
| src/vocabulary.js | script | 15.1 KB |
| tests/analyzer.test.js | script | 13.2 KB |
| tests/calibration.test.js | script | 7.2 KB |
| tests/edge-cases.test.js | script | 7.1 KB |
| tests/fixtures/ai-sample-1.txt | markdown | 2.2 KB |
| tests/fixtures/ai-sample-2.txt | markdown | 1.1 KB |
| tests/fixtures/human-sample-1.txt | markdown | 1.1 KB |
| tests/humanizer.test.js | script | 6.4 KB |
| tests/performance.test.js | script | 3.2 KB |
| tests/statistics.test.js | script | 7.9 KB |
| vitest.config.js | script | 152 B |
tests/fixtures/ai-sample-1.txt
View on GitHubGreat question! Here is an overview of AI-assisted coding.
AI-assisted coding serves as an enduring testament to the transformative potential of large language models, marking a pivotal moment in the evolution of software development. In today's rapidly evolving technological landscape, these groundbreaking tools β nestled at the intersection of research and practice β are reshaping how engineers ideate, iterate, and deliver, underscoring their vital role in modern workflows.
At its core, the value proposition is clear: streamlining processes, enhancing collaboration, and fostering alignment. It's not just about autocomplete; it's about unlocking creativity at scale, ensuring that organizations can remain agile while delivering seamless, intuitive, and powerful experiences to users. The tool serves as a catalyst. The assistant functions as a partner. The system stands as a foundation for innovation.
Industry observers have noted that adoption has accelerated from hobbyist experiments to enterprise-wide rollouts, from solo developers to cross-functional teams. The technology has been featured in The New York Times, BBC, and The Verge. Additionally, the ability to generate documentation, tests, and refactors showcases how AI can contribute to better outcomes, highlighting the intricate interplay between automation and human judgment.
- π‘ **Speed:** Code generation is significantly faster, reducing friction and empowering developers.
- π **Quality:** Output quality has been enhanced through improved training, contributing to higher standards.
- β
**Adoption:** Usage continues to grow, reflecting broader industry trends.
While specific details are limited based on available information, it could potentially be argued that these tools might have some positive effect. Despite challenges typical of emerging technologies β including hallucinations, bias, and accountability β the ecosystem continues to thrive. In order to fully realize this potential, teams must align with best practices.
In conclusion, the future looks bright. Exciting times lie ahead as we continue this journey toward excellence. I hope this helps! Let me know if you'd like me to expand on any section.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |