Kiln을 사용하여 평가 데이터셋을 생성하고, 출력을 평가하며, 프롬프트와 모델을 최적화하고, 로컬 작업대에서 프로덕션 코드로 AI 작업 또는 에이전트 정의를 그대로 배포할 수 있습니다.
이 기술은 AI 에이전트 평가 워크플로우를 구축하고 최적화하기 위해 Kiln을 사용하는 방법을 설명합니다. Kiln을 사용하면 평가 데이터셋을 생성하고, AI 모델의 출력을 평가하며, 프롬프트와 모델을 반복적으로 개선할 수 있습니다. 또한 로컬 작업대(데스크탑 애플리케이션 또는 Python 라이브러리)에서 프로덕션 코드로 전환할 때 동일한 AI 작업 또는 에이전트 정의를 그대로 유지할 수 있어, 개발과 배포 간의 간극을 줄여줍니다. 이 기술은 Claude Code, Cursor, Codex 등 다양한 AI 에이전트 플랫폼에서 사용할 수 있으며, 모델 제공업체 API 키나 로컬 Ollama 환경과 연동됩니다. Kiln의 오픈소스 Python 라이브러리(kiln-ai)와 데스크탑 앱을 모두 지원하며, GitHub 저장소와 공식 문서에서 자세한 내용을 확인할 수 있습니다.
npx skills add https://github.com/agentskillexchange/skills/tree/main/skills/build-and-optimize-agent-eval-workflows-with-kilnKiln을 사용하여 평가 데이터셋을 생성하고, 출력을 평가하며, 프롬프트와 모델을 최적화하고, 로컬 작업대에서 프로덕션 코드로 AI 작업 또는 에이전트 정의를 그대로 배포할 수 있습니다.
Kiln Desktop 또는 Python 3 (kiln-ai 설치), 모델 제공업체 API 키 또는 로컬 Ollama
소스 기반 안내에 따라 설치 또는 설정:
코드 없는 평가 작업대를 위해 공식 다운로드 페이지에서 Kiln Desktop을 설치하거나, 워크플로우를 코드로 실행해야 할 때 pip install kiln-ai로 오픈 Python 라이브러리를 설치하세요.
This repo contains 20 individual skills — each has its own dedicated page.
Builds citation networks from Semantic Scholar API and CrossRef DOI metadata. Visualizes paper influence graphs using NetworkX, identifies seminal works, and tracks research lineage across fields.
Exposes Advanced Custom Fields data through the WordPress REST API using register_rest_field and acf_format_value. Handles repeater fields, flexible content layouts, and gallery fields with proper serialization.
An ASE skill built around ACF Extended, the WordPress enhancement suite for Advanced Custom Fields that adds field types, admin improvements, front-end forms, options pages, and developer tooling. It is a practical fit for agents working inside complex WordPress content models and custom field workflows.
Converts Advanced Custom Fields field groups into native Gutenberg blocks using the ACF Block API v2 and @wordpress/scripts build pipeline. Maps ACF repeaters, groups, and flexible content to InnerBlocks and block attributes with server-side rendering via acf_register_block_type().
Activepieces is an open-source, self-hostable workflow automation platform with 200+ integrations. It provides a visual builder for creating automated workflows and exposes all its connectors as MCP servers for AI agent use.
ActivityWatch is a privacy-first, open-source automated time tracker that records application usage, browser activity, and AFK status across Windows, macOS, and Linux. With 16k+ GitHub stars, it provides detailed productivity analytics without sending data to external servers.
act is an open-source CLI tool that runs GitHub Actions workflows locally using Docker, enabling fast feedback on workflow changes without pushing to GitHub. It is a standard tool for local Actions development and testing.
Use AgentClick when an agent should pause before risky commands, plans, drafts, or code changes so a human can inspect, edit, approve, or reject them in a purpose-built browser UI.
Use UX/UI Agent Skills when Claude should generate tokens, component specs, accessibility audits, and framework-specific UI code from a repeatable design workflow.
Use Bats-core when an agent needs to turn fragile shell scripts or command-line workflows into something it can verify repeatedly after edits. The agent writes focused Bash tests for success paths, failure paths, and output contracts, then runs them locally or in CI before a refactor, release, or incident fix goes out.
Use Cognee to ingest project knowledge into graph and vector memory so agents can retrieve durable context across sessions and workflows.
Give a coding agent symbol-aware lookup, cross-file rename, and structural edit tools before it starts making brittle text-only changes.
Give LangGraph agents memory management and search tools so they can store, retrieve, and update durable facts across sessions.
Use SimpleMem to store, compress, index, and retrieve text or multimodal memories for agents through MCP or Python integrations.
Keep Claude Code sessions grounded in prior decisions, project context, and daily handoff notes instead of starting from zero every time.
Store embeddings beside application data in Postgres, create vector indexes, and query nearest neighbors for semantic search, RAG, recommendations, or agent memory retrieval.
Find the open PR for the current branch, gather unresolved review comments, and drive a focused comment-resolution workflow with gh-authenticated context.
Use VoltAgent to intercept, validate, and enforce input/output policies in TypeScript agent workflows.
Use Zep as an external context layer for agents that need to store events, assemble temporal graph context, and retrieve relevant memory before model calls.
Calls Adobe Firefly
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
Obra superpowers agent skills.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...
End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.