Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Answers AI agent evaluation methodology questions with practical, opinionated guidance grounded primarily in Microsoft's agent evaluation ecosystem (MS Learn, Eval Scenario Library, Triage & Improvement Playbook, Eval Guidance Kit) supplemented by select industry sources.
Analyzes Copilot Studio evaluation results using Practical Guidance on Agent Evaluation's 10-step playbook (Steps 6, 7, and 9) plus Microsoft's triage diagnostics. Returns a gate-based SHIP / ITERATE / BLOCK verdict with root cause classification, remediation, and pattern analysis.
Use this skill when the user's Copilot Studio agent evaluations have come back and they need to interpret scores, diagnose root causes of underperforming test cases, find remediation steps, or analyze patterns to improve their agent. Always use this skill when the user mentions: "eval failed", "why did this fail", "triage", "diagnose failure", "low pass rate", "fix evaluation results", "not passing", "failing test cases", "evaluation results", "improve my eval scores", or any situation where eval scores need interpretation and action.
Gate for deciding whether to adopt an external pattern (skill/agent/rule/plugin/MCP/prompt) into your system. Triggers: '/integration-intake [name]', 'should I integrate this', 'is this worth adopting', or sharing a GitHub repo link and asking what to do with it.
Use when the user needs to synchronize local AI agent skills across Codex, Claude, Qoder, QoderWork, Cursor, Kiro, Lingma, CoPaw, OpenClaw, ~/.agents/skills, ~/.skills, and optionally a Nacos Skill Registry. Handles skill-sync setup, add/start/status/resolve/stop flows, Nacos mode and local mode, non-interactive agent execution, conflict triage, auto-upload state, Upload blocked handling, and safe human decision points.
Use when saving session state before context compaction, switching tasks, or ending a session. Runs 5-phase pipeline: context extraction → handoff write → memory save → preservation check → compact guidance.
Convert Claude Code commands (.claude/commands/*.md) to standard Agent Skills (skills/*/SKILL.md). Use when migrating slash commands to portable skill format, creating skills from existing commands, or standardizing command definitions across AI runtimes.
Review the current chat session and distill any new conventions, file layouts, frontmatter fields, or workflow rules that emerged into the repo's agent docs. Proposes updates to AGENTS.md/CLAUDE.md and to skills (in `.agents/skills` or `.claude/skills`), then runs a sub-agent simplification pass over the changes before committing.
This guide covers the design philosophy, core concepts, and practical usage of the AgentScope framework. Use this skill whenever the user wants to do anything with the AgentScope (Python) library. This includes building agent applications using AgentScope, answering questions about AgentScope, looking for guidance on how to use AgentScope, searching for examples or specific information (functions/classes/modules).