Agent Building skills

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

generate-openenv-env

Builds an OpenEnv (Meta) variant of an RL environment. Use whenever someone asks to scaffold an OpenEnv server, port an existing env to OpenEnv, add MCP tools to an env, or deploy an OpenEnv to HF Spaces. OpenEnv is the right framework when the user wants HTTP+MCP, structured tool calls discovered via `list_tools()`, an optional Gradio UI, sandbox-backed sessions, or deployment as a Docker container / HF Space. Output is a runnable `<env_dir>/openenv/` folder with `server/app.py`, `server/<env>_environment.py`, `pyproject.toml`, `Dockerfile`, and `rollout.py`. Use for prompts like "wrap my game in OpenEnv", "make an MCP env for X", or "add the openenv variant".

154 repo starsObserved in 1 repos

Agent Building

GitHub

generate-ors-env

Builds an Open Reward Standard (ORS) variant of an RL environment using the official `openreward` Python package. Use whenever someone asks to scaffold an ORS env, port to OpenReward, add per-tool-call rewards, deploy to OpenReward.ai, or wrap an existing env in the ORS protocol. ORS is the right framework when the user wants HTTP+REST+SSE, rewards arriving inline with each tool call (not post-episode), task-spec-driven sessions, splits (train/val/test), or deployment to OpenReward.ai or HF Spaces. Output is a runnable `<env_dir>/ors/` folder with `server.py`, `tasks.py`, `pyproject.toml`, `Dockerfile.spaces`, and `rollout.py`. Use for prompts like "wrap my env in ORS", "make an OpenReward env for X", or "add per-call reward to my env".

154 repo starsObserved in 1 repos

Agent Building

GitHub

loopany

Create, update, and evolve scheduled Loopany agent loops from a coding session. Use when the user wants to turn a task they just did into a recurring/scheduled loop, edit an existing loop's schedule or instructions, or asks to build a Loopany loop. A loop can carry a goal (a finish line) and completes itself when the goal is met; without one it runs indefinitely as a monitor.

154 repo starsObserved in 1 repos

Agent Building

GitHub

payram-openclaw-integration

Functional how-to for integrating PayRam into an OpenClaw (or NemoClaw, Claude Desktop, Copilot, n8n, LangChain, Cursor, Windsurf) agent. Register the PayRam MCP server, list discovered tools, walk through a full payment flow from create_payment → webhook → fulfilment, and debug common issues. Includes a testnet walkthrough on Base Sepolia, agent configuration for WhatsApp/Telegram/Discord bot runtimes, and patterns for subscription access grants, pay-per-request API monetization, and agent-to-agent commerce. Use when building an OpenClaw skill that needs to accept or send money, connecting an existing bot to PayRam, or troubleshooting an MCP registration that's not picking up tools.

154 repo starsObserved in 1 repos

Agent Building

GitHub

rl-env-from-description

Turns a user's plain-English description of an RL training environment into runnable code across the four target frameworks — OpenEnv, OpenReward (ORS), Verifiers, and NeMo Gym. Use whenever someone describes an environment they want to build ("I want to train an agent that does X", "make an env where the model has to Y"), asks to scaffold a new env, asks to port an existing env to one of these frameworks, or asks how to design tools/rewards/state for a new env. Use even when the user does not explicitly say "RL environment" — descriptions like "agent that browses the web", "tool-calling agent for SQL", or "game-playing agent" all qualify. Drives the full flow — clarifying interview, env-name selection, shared-domain extraction, per-framework implementation, and rollout-based smoke tests.

154 repo starsObserved in 1 repos

Agent Building

GitHub

skill-dev

Skill 全生命周期管理：创建 → 反思优化 → 评测 → 成熟度判断 → 发布到市场 → 检索多版本 → 选择/安装 → 融合迭代 → 卸载。触发场景：(1) 用户要求创建/修改 skill (2) 发现可提取为 skill 的重复模式 (3) skill 执行出错或用户纠正后需要反思改进 (4) 用户要求发布/搜索/安装/合并社区 skill (5) 反思后自动检查成熟度并建议发布

154 repo starsObserved in 1 repos

Agent Building

GitHub

wxa-skills-eval

微信小程序 AI Skill 端到端评测引擎；当需要评测一个或多个 wxapp Skill 的意图理解、轨迹生成与最终答案质量时加载本 Skill。

154 repo starsObserved in 1 repos

Agent Building

GitHub

wxa-skills-generate

分析小程序项目源代码（含压缩/混淆），识别核心业务步骤，提取网络接口与 JSAPI 调用，生成符合 wx.modelContext 规范的技能分包（含原子接口 + 原子组件），并完成 app.json / project.config.json 配置集成。在以下场景触发：把小程序页面能力改造为小程序 AI 原子接口、生成 skills/ 分包代码、从源项目派生 MCP 工具、小程序 AI 的开发模式代码生成。仅负责静态生成，生成完成后必须交棒 wxa-skills-validate 做校验。

154 repo starsObserved in 1 repos

Agent Building

GitHub

agent-restore-context-setup

Set up the restore-context hook so skills can resume workflows after /clear and /compact. Use when setting up a new project or after cloning a repo that uses restore-context skills.

153 repo starsObserved in 1 repos

Agent Building

GitHub

c-schedule

Smart scheduling — automate recurring Claude tasks with cost control. Deliver results to Telegram, file, or notification. Built into OpenPaw.

153 repo starsObserved in 1 repos

Agent Building

GitHub