Capafy AI - Agent Skills 마켓플레이스
당신의 작업에 바로 투입되는 전문가 Agents.
Picova는 비즈니스 아이디어, 제품 요구사항 또는 창의적인 구상을 실제로 배포하고 운영할 수 있는 완성형 웹사이트로 만들어 줍니다. 랜딩 페이지, 온라인 스토어, SaaS 제품, 대시보드, 포트폴리오, 다중 페이지 사이트를 만들 수 있으며 검색, 양식, 계정, 즐겨찾기, 쇼핑, 예약 기능도 추가할 수 있습니다. 결과물은 스크린샷이나 목업이 아니라 실제로 온라인에 배포할 수 있는 프로젝트입니다.
Build review-ready Capafy Skills from idea to submission. This independent publisher assistant designs the architecture, writes SKILL.md and Agent Card content, applies sector guardrails, plans integrations and data disclosures, recommends monetization and pricing, creates test criteria and brand assets, validates the package, and prepares runtime and submission ZIPs. Not affiliated with or endorsed by Capafy.
Stop guessing why short-form videos work. ViralLens reverse engineers Instagram Reels, TikToks, YouTube Shorts and short-form ads to uncover their: Hook Retention mechanics Proof Desire Visual selling Creative structure Then it rebuilds those principles into original hooks, angles and ready-to-film scripts for your own business. Steal the DNA, not the video.
Claude Codeのhooks設定を対話形式で生成するスキルです。自動フォーマット・テスト実行・危険コマンドブロック・完了通知など、settings.jsonに書くべきhookを正しく構成します。レシピ集付きですぐに使えます。
Generate a data-grounded Astro restaurant website from a Google restaurant link
MCPサーバーの雛形を対話形式で生成するスキルです。ツール・リソース定義、登録設定(.mcp.json)、起動確認手順まで一式出力。Python(FastMCP)対応。自分のAPIやDBをClaudeから使えるようにしたい時に。
사진 한 장으로 나만의 데스크톱 펫을 만들어 보세요. Kapi는 당신을 바라보고, 반응하고, 함께 놀며 성장합니다. 함께한 추억을 간직하고, 새로운 동작과 전용 대사, 의상, 생활 습관도 하나씩 배워 갑니다.
Paste rough notes, a transcript, or chat log. Get confirmed decisions, owner-and-deadline actions, blockers, open questions, a follow-up email, and next agenda without invented commitments.
Paste tickets, FAQs, or policy text. Get a volume-ranked macro library, policy-safe replies, escalation rules, routing tags, knowledge-base drafts, and a pre-publish QA checklist.
Evidence-driven intelligence for finding the right Capafy Skills, uncovering what developers should build next, and matching buyers with solutions that truly meet their needs.
Create parent-guided English practice plans from materials you provide: reading prompts, phonics drills, vocabulary review, speaking games, writing practice, and safety notes.
Claude CodeのCLAUDE.md設計・運用を100プロジェクト以上で経験。肥大化したCLAUDE.mdが無視される原因（トークン浪費・矛盾・曖昧指示）を体系化し、最小トークンで最大効果を得る設定ファイルの書き方をスキルに落とし込みました。
PDFやAIファイルを自動面付けします。（きりっ子対応）A4に10面（検知ベタ付き）、A4に8面、A3ノビ16面〜20面 テスト的に使ってみてください。無料公開
Describe your idea in 2 sentences. In 5 minutes, get a complete project plan (audience, features, MVP, monetization) and a Master Build Prompt ready to paste into Lovable, Bolt, Cursor, or hand to a developer.
Check whether your AI initiative has enough traceable evidence for a credible value review, and receive a readiness score, evidence gaps, and clear next steps.
This agent helps Python teams using the Anthropic or OpenAI SDK safely cut LLM spend without risking regressions. With zero code changes, it maps call sites and runs your test scenarios to rank token waste from missed prompt caching or heavy model tiers. It tests fixes in isolated git worktrees, enforcing a strict "do-no-harm" gate that reverts any patch failing to preserve behavior. It delivers a clear savings audit that converts into verified, behavior-preserving code patches upon opt-in.
Diagnose software project risk, uncover the real blockers, and turn messy delivery problems into executable recovery plans.