Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

model-evaluation-specialist

Advanced model evaluation covering LLM benchmarks, evaluation frameworks (lm-evaluate-harness, HELM, RAGAS), leaderboard interpretation, custom metrics design, human evaluation protocols, automated LLM-as-judge patterns, and evaluation pipeline architecture for both traditional ML and generative AI systems. Use when the user asks about model evaluation specialist, model evaluation specialist best practices, or needs guidance on model evaluation specialist implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

543 repo starsObserved in 2 repos

Agent Building

GitHub

openclaw-setup

OpenClaw usage expert: Helps you install, deploy, configure, and use OpenClaw personal AI assistant. Can diagnose issues, create bots, execute automated tasks, etc. Use when users need to install OpenClaw, configure Gateway, set up Channels, create Agents, troubleshoot issues, or perform OpenClaw-related operations.

543 repo starsObserved in 2 repos

Agent Building

GitHub

prompt-translation

Translates AI image generation prompts between Midjourney, DALL-E, and Stable Diffusion by mapping source structure to target syntax, identifying direct transfers, and noting model-specific alternatives. Use when the user asks to convert a prompt from one AI model to another, adapt a Midjourney prompt for Stable Diffusion, or translate between prompt formats. Do NOT use for creating prompts from scratch (use model-specific skills), debugging a single-model prompt (use ai-image-prompt-debugging), or style analysis (use ai-image-style-transfer).

543 repo starsObserved in 2 repos

Agent Building

GitHub

rag-pipeline-design

Guides expert-level rag pipeline design implementation: ai-ml and database decision frameworks, production-ready patterns, and concrete templates for rag pipeline design workflows. Use when the user asks about rag pipeline design, rag pipeline design configuration, or ai-ml best practices for rag projects. Do NOT use when the user needs a different ai ml engineering capability -- check sibling skills in the ai ml engineering subcategory.

543 repo starsObserved in 2 repos

Agent Building

GitHub

story-roleplay

Parse and apply character cards and world info files in multiple formats (PNG, WebP, JSON), fully compatible with SillyTavern format. Supports automatic parsing, keyword triggering, and dynamic updates.

543 repo starsObserved in 2 repos

Agent Building

GitHub

concierge

Wayland's own how-to guide: explains what Wayland can do and gives the exact steps to operate it. Covers what can Wayland do, connecting an AI provider or model, creating an assistant, building and launching a workflow, setting up a team, scheduling a task, connecting an MCP server or outside tool, and switching models or using Flux Auto. Use when the user asks what Wayland can do, what features exist, how do I connect a provider or model, how do I add Claude or OpenAI or Gemini, how do I create or edit an assistant, how do I build or run a workflow, how do I set up a team of assistants, how do I schedule a task or set up a recurring job, how do I connect an MCP server or outside tool, or how do I switch models or turn on Flux Auto automatic model routing. Do NOT use when the user wants help with a non-Wayland task (writing, coding, research, document creation) — those have their own skills; this skill is only about operating Wayland itself.

543 repo starsObserved in 1 repos

Agent Building

GitHub

stable-diffusion-prompting

Crafts Stable Diffusion SDXL and Flux prompts with positive and negative prompt structure, CFG scale recommendations, sampler selection, resolution settings, and LoRA reference syntax. Use when the user asks to create a Stable Diffusion prompt, generate images with SDXL or Flux, write prompts for ComfyUI or Automatic1111, or optimize generation parameters. Do NOT use for Midjourney prompting (use midjourney-prompting), DALL-E prompting (use dalle-prompting), or translating prompts between models (use prompt-translation).

543 repo starsObserved in 1 repos

Agent Building

GitHub

calibrate_query_mapper

基于参考文本校准问答对中的查询（问题）。当用户提到校准问题、校准查询、语言风格校准、问题优化等需求时使用此skill。即使用户没有明确说出"校准"，只要任务涉及根据参考文本调整问答对中的问题，就应该使用此skill。

541 repo starsObserved in 1 repos

Agent Building

GitHub

calibrate_response_mapper

基于参考文本校准问答对中的响应。当用户提到校准回答、校准响应、语言风格校准、回答优化等需求时使用此skill。即使用户没有明确说出"校准"，只要任务涉及根据参考文本调整问答对中的回答，就应该使用此skill。

541 repo starsObserved in 1 repos

Agent Building

GitHub

piflow-skill-generator

PiFlow 技能生成器。当用户完成了一次完整并成功的数据处理任务时调用，根据当前 skills/generated 的本地约定和 references/piflow_skill_template.md 通用模板创建、更新或校验 PiFlow-compatible skill，包括 UTF-8 编码的 SKILL.md、DAG 可读的 input_params/output_params、version/category/tag 元数据、skill.json、scripts/references/assets 资源目录，以及本地校验脚本。仅在用户明确要求生成或保存 skill，或某次数据处理任务已经完成并需要把已验证成功的操作流程沉淀为 skill 时使用；默认不要因为“可能需要 skill”或“当前能力不足”而优先触发此 skill。

541 repo starsObserved in 1 repos

Agent Building

GitHub