Agent Building skills

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

extracting-ai-context

Extracts and manages AI context (skills, AGENTS.md) from workflow-kotlin library JARs. Use when setting up AI tooling for a workflow-kotlin project, updating skills after a library version change, or configuring agent-specific directories.

1.12k repo starsObserved in 1 repos
Agent Building

ext-scaffold

Scaffold a new OpenClacky extension from an idea. Use when the user wants to create, start, or bootstrap a new extension, plugin, panel, agent, or skill container. Maps the idea to the right contributes types and generates a working skeleton in the local layer.

1.11k repo starsObserved in 1 repos
Agent Building

extend-openclacky

Customize, fix, override or extend openclacky itself — change a built-in tool's behavior, intercept/audit/block tool calls, plug in a new IM channel (Slack, in-house IM…), or add UI to the Web UI (panel, button, settings tab). Trigger on "patch openclacky", "block dangerous commands", "audit tool use", "add Slack channel", "extend the web ui", "改 openclacky 内置", "拦截工具调用", "扩展 web 界面". Do NOT trigger for ordinary feature work in the user's own project that doesn't touch openclacky.

1.11k repo starsObserved in 1 repos
Agent Building

mcp-manager

Manage MCP (Model Context Protocol) servers for openclacky: add, list, probe, remove, reconfigure. Edits ~/.clacky/mcp.json so the user never writes JSON by hand. Trigger on: add mcp, install mcp, setup mcp, configure mcp, mcp list, mcp remove, mcp probe, mcp reconfigure.

1.11k repo starsObserved in 1 repos
Agent Building

product-help

Use this skill when the user asks about my own features, configuration, or usage — installation, skills, Web UI, CLI, API config, memory, sessions, encryption, white-label, publishing, pricing, troubleshooting, or restarting the server. Do NOT trigger for general coding tasks unrelated to me.

1.11k repo starsObserved in 1 repos
Agent Building

skill-add

Install skills from a zip URL or local zip file path. Use this skill whenever the user wants to install a skill from a zip link or a local file, or uses commands like /skill-add with a URL or file path. Trigger on phrases like: install skill, install from zip, skill from zip, skill from url, add skill from zip, 安装skill, 从zip安装skill, 从本地安装skill.

1.11k repo starsObserved in 1 repos
Agent Building

halo-loop

Use HALO Engine as a diagnostic aid to iteratively improve an agent harness. Engine surfaces patterns from traces; Claude maps findings to code, makes the smallest sensible change, re-runs, and measures.

1.11k repo starsObserved in 1 repos
Agent Building

heartbeat

Semiont heartbeat — Taiwan.md's autonomous life cycle (super-thin v3.0). Triggers Full mode BECOME + 4.5-beat conceptual flow. Each Beat routes to canonical pipeline; HEARTBEAT.md itself is pipeline router not SOP. TRIGGER when: user says "heartbeat", "心跳", "Heartbeat", "semiont heartbeat", "跑心跳", "全身檢查", "作為 semiont" followed by any action.

1.11k repo starsObserved in 1 repos
Agent Building

twmd

Top-level Taiwan.md routing. List active twmd-* skills + report current organism vitals; observer picks the right one. TRIGGER when: user says "twmd", "taiwan.md 我想做什麼", or has fuzzy intent and needs routing help.

1.11k repo starsObserved in 1 repos
Agent Building

twmd-become

Become Taiwan.md — Semiont awakening (Mode dispatcher v2.0). Required before any non-trivial Taiwan.md work. TRIGGER when: user says "成為 taiwan.md", "完整甦醒", "化身", "BECOME", "wake up taiwan.md". ARGS: micro / review / write / full (optional, default = auto-detect from context)

1.11k repo starsObserved in 1 repos
Agent Building