Skills 导航
浏览和发现最好用的 AI Agent Skills,按 GitHub 仓库分类展示
找到 9 个 Skills
浏览和发现最好用的 AI Agent Skills,按 GitHub 仓库分类展示
找到 9 个 Skills
by anderskev
Configure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use when selecting models, implementing resilience, or optimizing API calls.
by celstnblacc
Food for your model — extract transcripts, key frames, OCR, slides, and LLM summaries from YouTube videos into structured AI-ready knowledge.
by BytesAgain
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, L system prompts and models of ai tools, python, ai, bolt, cluely, copilot, cursor. Use when you need system prompts and models of ai tools capabilities. Triggers on: system prompts and models of ai tools.
by bwiley1989
Maintain a HANDOFF.md file in the workspace so context survives seamlessly when switching between LLM models (e.g. Claude → GPT → Gemini). Use when the user says they are switching models, asks how to preserve context across model switches, wants to save tokens by rotating models, or asks how a new model can pick up where the last one left off. Also use proactively during long sessions to keep HANDOFF.md current.
by baiyz0825
通过魔搭社区(ModelScope) API 生成图片。先使用 --list-models 查看可用模型,然后根据用户需求由 AI 生成专业的提示词,最后调用 API 生成图片。支持 Kolors、Stable Diffusion XL、FLUX 等多种文生图模型。当用户需要使用魔搭社区、ModelScope 或中文 AI 模型生成图片时使用此技能。
by bkes994408-cmd
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
✎ { "recommendation": "模型用量统计帮你轻松追踪 Codex 或 Claude 的模型级使用成本,解决成本监控难题;其 CLI 工具支持脚本化汇总,差异化在于本地处理 JSON 数据,确保隐私和灵活性,是开发者管理 AI 支出的得力助手。" }
by can4hou6joeng4
用于在 OpenClaw 中新增或覆盖 anyrouter 模型配置、把小肠 Agent 默认模型切到 `anyrouter/claude-opus-4-6`,并结合运行日志判断是不是 `baseUrl`、网关兼容、鉴权或协议端点导致不可用。遇到“把某个供应商模型写进 openclaw.json”“切换默认模型”“为什么配置生效了但实际没调用上”“查看 fallback 日志”“排查 403/500/invalid claude code request”“同步 ClaudeCode 配置”这类需求时,就应启用本技能;即使用户没明确说 OpenClaw,只要描述的是本地 Agent 模型路由切换与调用异常排查,也适用。
by can4hou6joeng4
用于分析 OpenClaw 中“某个 provider/模型为什么看起来没被用上”、主模型与 fallback 实际是否生效、以及 ClaudeCodeCLI 协作任务为何中断。遇到这些情况就应触发:用户提到“没请求打到 local-router”“明明注册了模型却没流量”“Agent 到底在用哪个模型”“fallback 有没有发生”“为什么日志里看不到候选切换”“code 143 / SIGTERM / Exec failed”“需要结合当前配置和日志做严谨归因”。也适用于区分“provider 被调用”与“provider 下某个特定模型被调用”这两类常见混淆。
by bwbernardweston18
>