Summary
透過 local Playwright MCP(headed 模式)執行「verify → fix」迭代迴圈:每輪以 snapshot + console + network 為證據驗證網頁行為,若 FAIL 則修正程式碼後重試。完成 2 輪後(Round 3 起)每輪強制 HITL 詢問是否繼續,避免盲目迭代。適合…
ashe-li/agent-skills
透過 local Playwright MCP(headed 模式)執行「verify → fix」迭代迴圈:每輪以 snapshot + console + network 為證據驗證網頁行為,若 FAIL 則修正程式碼後重試。完成 2 輪後(Round 3 起)每輪強制 HITL 詢問是否繼續,避免盲目迭代。適合…
npx skills add https://github.com/ashe-li/agent-skills
透過 local Playwright MCP(headed 模式)執行「verify → fix」迭代迴圈:每輪以 snapshot + console + network 為證據驗證網頁行為,若 FAIL 則修正程式碼後重試。完成 2 輪後(Round 3 起)每輪強制 HITL 詢問是否繼續,避免盲目迭代。適合…
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, includ…
810.4K installsConfigure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: sem…
566.3K installsAzure VM/VMSS router. WHEN: create / provision / deploy / spin-up VM, recommend VM size, compar…
510K installsPostgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill …
391.6K installsPrisma ORM CLI commands reference covering init, generate, migrate, db, dev, complete, studio, …
267K installsUse when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge F…
263K installsOther skills from ashe-li/agent-skills · top by installs.
npx skills add https://github.com/ashe-li/agent-skills
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
main