agentic-playwright
idavidov13/agentic-playwright
Acts as the primary intent router and workflow orchestrator for an AI-assisted Playwright test automation scaffold. Manages an 8-phase execution protocol that enforces strict confidence gates, exploratory evidence gathering, and task-specific routing.
14 11MITUpdated 2026-08-13
81
GreatOverview
This skill serves as the single entry-point router for complex, AI-driven development workflows within a Playwright-based testing framework. It controls an 8-phase operational lifecycle ranging from intent classification and mandatory evidence exploration to confidence scoring, human authorization gates, execution, and verification. By defining clear routing tables and anti-hallucination guardrails, it prevents the agent from making unsupported assumptions, utilizing placeholders, or executing speculative changes without explicit verification.
Capabilities
- ▸Intent classification and specialized skill routing
- ▸Mandatory 8-phase workflow enforcement
- ▸Confidence-gated execution planning and trade-off analysis
- ▸Premise verification to prevent speculative code modifications
- ▸Structured human-in-the-loop validation gates
Best for
Routing user requests to specialized downstream testing, mocking, or refactoring skills., Enforcing confidence-gate evaluations and halting execution when exploration data is incomplete., Orchestrating multi-step Playwright test generation, debugging sessions, and framework maintenance tasks.
Works with
Claude CodeCursorGitHub CopilotCodexChatGPTGemini CLIOpenCode
Evoa Score breakdown= Σ (score × weight)
81Task 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%95 → +14.3
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%44 → +5.3
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%39 → +3.1
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 total80.8 / 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
Enforces strict input verification and prevents the blind acceptance of credentials, secret-shaped strings, or unverified endpoints by requiring active exploration and user confirmation.
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.