同時搜尋技能包和技能

團隊需要一種方式來探索並執行託管的 AI 模型，而不必管理 GPU。此技能會引導 Claude、Codex 和 Claude Code 使用 inference.sh CLI 工作流程。

Coding agents can change repositories without clear scope or reliable evidence. Gravitas provides task contracts, adaptive planning, and verification guidance tied to observed results.

Job searches require repeated assessment, form completion, and accurate tracking. This skill organizes authorized applications with verified candidate data and submission safeguards.

Building and operating Valet agents requires coordinated CLI, credential, connector, channel, and deployment steps. This skill guides those workflows with explicit confirmation, validation, and testing.

手動部署設定可能會拖慢發布速度，並讓預覽工作流程變得混亂。此技能會引導 Claude、Codex 和 Claude Code 完成 Vercel CLI 部署、連結，以及沙盒備援路徑。

Electron 應用程式測試通常需要手動點擊、螢幕截圖和重複設定。此技能會示範 Claude、Codex 和 Claude Code 如何將 agent-browser 連接到 Electron 應用程式，並自動化這些工作流程。

以趨勢為基礎的內容工作流程通常需要分開進行探索、撰稿與審查步驟。此 skill 會協調 Defou Workflow Agent pipeline，讓草稿從 TopHub 主題推進到爆紅驗證。

Agent skills are difficult to evaluate from configuration alone. This skill reviews local conversations, scores outcomes, and drafts evidence-based improvements.

Finding the right finance data or analysis skill can be difficult. This router matches requests to cataloged Wind skills and guides approved installation.

Skill marketplaces require different repository layouts, package formats, and submission steps. This skill provides local preparation tools, supported API submissions, and channel-specific publishing guidance.

Bug bounty research can become fragmented across tools, payloads, and reporting workflows. This skill organizes authorized testing into scoped, evidence-focused playbooks.

團隊通常會為 Claude、Codex 和其他代理維護不同的指令檔案。此技能透過手動同步、監看模式和輔助腳本，讓這些檔案保持一致。