Browse reusable Agent Skills, each with a clear purpose and practical guidance.
MDA compatibility demonstration skill for Codex CLI. Compiled from compat/codex-cli/source.mda. Loading this skill confirms that an MDA-emitted SKILL.md is discovered and parsed by Codex CLI with the envelope subset of agentskills.io v1 fields honored.
MDA compatibility demonstration skill for Hermes Agent. Compiled from compat/hermes/source.mda. Loading this skill confirms that an MDA-emitted SKILL.md is discovered, parsed, and listed by Hermes Agent under its `~/.hermes/skills/<category>/<name>/SKILL.md` layout.
MDA compatibility demonstration skill for Claude Code. Compiled from compat/claude-code/source.mda. Loading this skill confirms that an MDA-emitted SKILL.md loads in Claude Code with the envelope subset of agentskills.io v1 fields honored.
MDA compatibility demonstration skill for OpenCode. Compiled from compat/opencode/source.mda. Loading this skill confirms that an MDA-emitted SKILL.md is discovered and parsed by OpenCode with the envelope subset of fields documented at opencode.ai/docs/skills/ honored.
Use when analyzing rank_llm evaluation outputs across runs or models. Covers aggregated trec_eval JSONL files, response-analysis metrics, retrieval-cache handoff files, and side-by-side comparison of stored evaluation artifacts.
Skills for using Docker Model Runner to run local LLM inference
胥克谦式AI-Native产品开发方法论。适用于：(1) 使用AI Agent（Claude Code、Codex、Cursor等）进行产品级软件开发，(2) 设计和优化Harness/Skill体系，(3) 文档驱动开发(SDD)流程，(4) 构建自动化质量门禁和eval机制，(5) Token成本优化与缓存策略，(6) 产品人转型开发者的AI编程实践。触发场景包括"帮我设计开发流程"、"怎么降低token成本"、"怎么提高AI编码质量"、"文档驱动"、"质量门禁"、"harness设计"、"单agent vs multi-agent"、"自动化迭代"、"AI产品开发"、"SDD"、"eval机制"等。即使用户只是说"帮我用AI写代码"或"怎么让agent干活更靠谱"也应触发。注意：如果产品是行为开放、用户输入不可穷举的AI-native类型，请改用 xuefeng-method skill。不用于：单个bug修复或小改动（无需方法论）、PRD需求文档写作（用product-manager）。
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
雪峰式AI-Native产品开发方法论。适用于：(1) 用户行为开放、不可穷举的AI-native产品（AI日历、AI助手、AI推荐、对话式产品等），(2) 强模型依赖型场景，AI驱动核心决策而非仅辅助，(3) 多专精Agent架构设计与分工，(4) 上线后快速校准、行为审计与漂移检测，(5) 模型选择和智能路由策略，(6) 概率性输出的质量评估。触发场景包括"AI-native产品怎么做"、"用户行为不可预测怎么办"、"多agent怎么分工"、"模型漂移怎么处理"、"校准到95%太难了"、"唯快不破"、"怎么选模型"、"agent并行分工"、"AI产品上线后怎么迭代"。注意：如果产品是场景明确、边界可定义的+AI类型，请改用 keqian-method skill。即使用户没有明确说"AI-native"，但在讨论AI驱动决策、用户行为不可预测、概率性输出等话题时也应触发。
Use the swarm KV store (Redis-like, namespaced) for cross-task / cross-session / per-page state. Auto-scoped to your context (Slack thread / PR / Linear issue / agent / page). Use for counters, cursors, page state. Do NOT use for secrets (`swarm_config`), embedded knowledge (`memory`), or files (`agent-fs`).