claudelint
stbenjam/claudelint
Claudelint is a configurable, rule-based linter designed to validate Claude Code plugins and plugin marketplaces. It detects structural issues, checks metadata correctness, and supports custom validation rules.
7 4Apache-2.0Updated 2026-05-07
73
GoodOverview
Claudelint is a specialized developer tool and utility for validating the structure, metadata, commands, and configurations of Claude Code plugins and plugin marketplaces. It automatically distinguishes between single plugins and complex marketplace repositories, offering customizable rule sets, severity adjustment, extension via Python scripts, and seamless CI/CD integration through pip, uvx, or Docker.
Capabilities
- ▸Context-aware detection of single plugins and marketplace structures
- ▸Rule-based validation with configurable error, warning, and info severity levels
- ▸Support for custom rules written in Python
- ▸Validation of plugin manifests, commands, skills, agents, hooks, and MCP configurations
- ▸Strict mode support to treat warnings as errors
- ▸Configuration management via .claudelint.yaml
Best for
Validating single Claude Code plugins and plugin marketplaces for correct folder layouts, JSON structures, and frontmatter., Enforcing naming conventions, required sections in command markdown files, and proper agent/hook configurations., Integrating into CI/CD pipelines (GitHub Actions, GitLab CI) to catch malformed Claude plugins before deployment.
Works with
Claude Code
Evoa Score breakdown= Σ (score × weight)
73Task 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%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%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%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 total73.0 / 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 tool reads local repository files and can load custom Python rule scripts specified in configuration files, which could execute arbitrary code if untrusted configuration or rule files are used.
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.