skills-claude-code

Name: skills-claude-code
Rating: 57 (1 reviews)
Author: madeinlowcode

madeinlowcode/skills-claude-code

An anti-vibe coding methodology skill that enforces a disciplined, spec-driven development process with 7 sequential phases for AI-assisted software creation.

7 4No licenseUpdated 2026-04-07

Fair

View on GitHub Open source file

Overview

The anti-vibe-coding skill guides developers through a rigorous 7-phase process—from isolation and architectural foundation to spec-driven development, test-driven development, and optimization—ensuring AI coding agents remain disciplined and under control rather than generating unverified code.

Capabilities

▸Enforces sequential phase gates for project development
▸Generates structured SDD artifacts like proposal.md, design.md, and specs
▸Guides test-driven development workflows and constraint management via CLAUDE.md
▸Calibrates technical depth based on developer experience level

Best for

Building a new software project, SaaS, or MVP from scratch with AI assistance, Adding major features to existing projects in a structured, test-driven manner, Establishing strict architectural foundations and specifications before writing code

Works with

Claude Code

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%77 → +15.4

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%70 → +10.5

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%28 → +3.4

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%80 → +12.0

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%30 → +2.4

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%25 → +1.3

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 total66.9 / 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

Encourages environment isolation such as Docker or VMs to prevent untrusted AI command execution.