soundshuman
aashaexo/soundshuman
An anti-slop toolkit and AI skill designed to remove generic AI patterns and robotic prose from text and repositories. It combines a 41-pattern humanizer skill, a rule pack, and a zero-dependency linter CLI.
229 12No licenseUpdated 2026-08-07
74
GoodOverview
Soundshuman is a comprehensive editing and auditing kit that helps AI coding agents and human writers produce natural, human-sounding prose. It merges pattern-based editing guidelines with a mechanical linter (`sloplint`) to catch robotic phrasing, stylistic clichés, and statistical uniformity. The kit includes voice calibration, structured review loops, rule-based scanning for continuous integration, and automated fixes for common AI writing tells.
Capabilities
- ▸41-pattern humanizer skill catalog covering content, rhetoric, and filler
- ▸Explainable 0-100 scoring system measuring pattern density and statistical tells like burstiness
- ▸Zero-dependency Node.js CLI scanner for auditing files and directories
- ▸Automated mechanical fixes for safe text cleanup
- ▸Voice calibration based on user-provided writing samples
- ▸Git hook installation for pre-commit linting
Best for
Rewriting AI-generated documentation or blog posts to sound like a natural human author, Auditing repositories or documentation folders for AI writing patterns and enforcing quality gates in CI pipelines, Calibrating an AI agent's writing style to match a specific human author's sample text, Running pre-commit checks to catch and fix common AI stylistic tics and filler phrases automatically
Works with
Claude CodeCursorGitHub CopilotCodexChatGPTGemini CLIOpenCode
Evoa Score breakdown= Σ (score × weight)
74Task usefulness20%100 → +20.0
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%100 → +15.0
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%40 → +4.8
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%100 → +15.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%60 → +4.8
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total86.6 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
The skill operates locally on text and files using a static rule pack, posing no remote data security or execution risks.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.