Agent Building skills

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

manage-schemas

Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also manages the actor_authentication config block: set actor authentication policy, configure degraded mode, show actor_authentication config, set degradedModePolicy to reject, what's the current degraded mode policy. Use when user says: create schema, show schemas, edit schema, delete schema, validate config, what schemas exist, add a note to schema, remove note from schema, or configure gates.

196 repo starsObserved in 1 repos

Agent Building

GitHub

my-router

Context-aware router that detects work type and dispatches to the right skill. Ships with a minimal default routing table; extend it in a fork, or register project-local skills in a consuming repo via routing-table.local.md or an AGENTS.local.md Routing section.

196 repo starsObserved in 1 repos

Agent Building

GitHub

plugin-impact-review

Assessment of plugin skill and hook changes needed after MCP or config changes. Evaluates skill references, hook context, config-format docs, and output style references. Invoked via skillPointer when filling plugin-impact notes.

196 repo starsObserved in 1 repos

Agent Building

GitHub

quick-start

Interactive onboarding for the MCP Task Orchestrator. Detects empty or populated workspaces and walks through how plan mode, persistent tracking, and the MCP work together. Use when a user says "get started", "how do I use this", "quick start", "first time setup", "onboard me", "what can this MCP do", or "help me learn task orchestrator".

196 repo starsObserved in 1 repos

Agent Building

GitHub

woz-benchmark

Compare WOZCODE vs vanilla Claude Code on the user's codebase — real cost, turn, and time savings. TRIGGER on "compare woz", "how much does woz save", "benchmark woz", "woz vs claude", "show me savings", or /woz-benchmark.

196 repo starsObserved in 1 repos

Agent Building

GitHub

aiscan

Use this skill when the agent needs to understand aiscan mechanisms, available capabilities, scanner pseudo-commands, and tool invocation rules.

195 repo starsObserved in 1 repos

Agent Building

GitHub

reviewing-skills

Review and update copilot instructions and skill files after completing a piece of work. Covers when to review, what to check, common failure modes, and the verification process. USE FOR: post-work skill review, periodic instruction audits, adding new skills, fixing skill drift after codebase changes. DO NOT USE FOR: writing library code (use the relevant domain skill), verifying documentation code samples (use the code sample verification section in copilot-instructions.md).

195 repo starsObserved in 1 repos

Agent Building

GitHub

meta_agent

综合智能代理系统，整合任务分析、规划和ReAct执行循环能力。当用户需要处理复杂任务、多步骤工作流或需要自主决策和反思的任务时使用。

194 repo starsObserved in 1 repos

Agent Building

GitHub

add-functor

Claude adapter for the canonical EmbodiChain add-functor skill.

193 repo starsObserved in 1 repos

Agent Building

GitHub

ai-duel

Use when running AI-vs-AI duel simulations, validating AI matchup quality, checking combat or spellcasting regressions, tuning ai-duel CLI options, or interpreting batch simulation results.

193 repo starsObserved in 1 repos

Agent Building

GitHub