Agent Building skills

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

run-history-skill-builder

Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. Use when the user asks to make a new skill from real run history, extract a reusable workflow from conversation/logs/files, summarize lessons into a new skill, or produce a plan before writing files. Do not use to upgrade an existing skill or to execute the business workflow itself.

625 repo starsObserved in 3 repos
Agent Building
GitHub

run-history-skill-upgrader

Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed platform behavior, or validated workflow feedback. Do not use to create a brand-new skill or to execute the business workflow itself.

625 repo starsObserved in 3 repos
Agent Building
GitHub

user-profile-keeper

Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses. Use only when the user explicitly invokes this skill or asks to create, initialize, update, query, correct, delete, export, or audit a local persistent user profile. Also use to extract durable collaboration preferences, requirement-expression habits, capability boundaries, recurring omissions, risk preferences, privacy boundaries, and typical events from the current session into auditable, confirmable, retractable local profile data. Do not auto-invoke, upload profile data, or replace task-clarifier's normal clarification flow.

625 repo starsObserved in 2 repos
Agent Building
GitHub

mcp-tool-creator

MCP 工具创建器。当用户需要为系统添加新的 MCP 工具时使用此技能。

625 repo starsObserved in 1 repos
Agent Building
GitHub

model-provider-creator

为多模型支持创建新的 AI 模型提供商。当用户想要添加对新的 AI 模型（OpenAI、Claude 等）的支持时使用此技能。

625 repo starsObserved in 1 repos
Agent Building
GitHub

skill-workbench-mermaid-guard

Skills 工作台的默认技能：当用户想为某个目标 Skill 生成、回显、修复或重写「工作流程图」或「输入交互表单」时使用——即使没有直接说出 "Mermaid"、"流程图"、"FLOWCHART"、"A2UI"、"表单" 等词。覆盖两类产物：(1) 把 SKILL.md 的工作流整理成符合 FLOWCHART.md 规范、可直接渲染的彩色 Mermaid 流程图（语义化配色 + classDef，支持单图总览与多子图拆分，并在写入前做语法归一化与自检）；(2) 生成目标 Skill 的首次交互表单 ui.json，以及运行期 a2ui HITL 表单。典型请求如"画出这个 Skill 的流程""整理成流程图""修一下 FLOWCHART""给这个 Skill 做个输入表单""第一次运行要问哪些参数"。不负责与 Skill 工作台无关的业务流程图、通用绘图或产品 UI 设计。

625 repo starsObserved in 1 repos
Agent Building
GitHub

spring-ai-chat

集成 Spring AI 聊天功能。当用户想要与 AI 模型对话、创建聊天端点或处理 AI 对话流程时使用此技能。

625 repo starsObserved in 1 repos
Agent Building
GitHub

skill-curator

中文 Skill 收录评估器。用于核验 GitHub 上的 Claude Code、Codex、Agent Skills、Plugin、MCP、CLI 或 Agent 工作流是否值得加入精选列表；检查真实资产、安装方式、活跃度、重复项和安全边界，并生成分类、中文描述与可追溯证据。

623 repo starsObserved in 2 repos
Agent Building
GitHub

skillgrade-graders

Authors deterministic and LLM rubric graders for skillgrade evaluations. Use when creating scoring scripts, writing evaluation rubrics, or combining multiple graders with weighted scoring. Don't use for setting up eval pipelines, configuring eval.yaml defaults, or general test writing.

622 repo starsObserved in 1 repos
Agent Building
GitHub

yolobox-orchestrator

Use when the agent is outside yolobox and needs to start, inspect, or control yolobox sessions, choose the right yolobox subcommand or flags, read merged config, decide between scratch, readonly, docker, or network options, or debug how a yolobox launch should be configured.

620 repo starsObserved in 1 repos
Agent Building
GitHub