skillsaw
stbenjam/skillsaw
Skillsaw is a configurable, rule-based linter designed for validating agentic contextual building blocks, prompts, and plugins across various AI ecosystems.
48 11Apache-2.0Updated 2026-08-13
78
GreatOverview
This skill definition and developer guide outlines the architecture, rules, and best practices for developing and maintaining the skillsaw linter repository. It covers strict checklists for pre-push and pre-PR workflows, performance optimization techniques for AST parsing and linting trees, autofix invariants, and ecosystem provenance handling for multi-platform AI agents.
Capabilities
- ▸Configurable rule-based linting for agent configs
- ▸AST-based markdown reading and token-level code splicing
- ▸Ecosystem provenance detection and scoping
- ▸Automated and safe autofix generation with idempotency guards
- ▸Performance-tuned pattern scanning and memoized node finding
Best for
Developing and linting custom AI agent skills, prompts, and markdown-based instructions, Running performance-optimized static analysis on agentic contextual configurations, Ensuring ecosystem provenance and compliance for multi-platform AI agent plugins
Works with
Claude CodeCodexCursor
Evoa Score breakdown= Σ (score × weight)
78Task usefulness20%88 → +17.6
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%31 → +3.7
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%46 → +3.7
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%75 → +3.8
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 total77.8 / 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 codebase interacts directly with filesystem parsing and executes automated fixes, requiring strict adherence to safe parsing practices to prevent arbitrary code execution or malformed file outputs.
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.