أحدث المهارات

Stop editing files one at a time. ORCA drafts every change in parallel, then applies them per-file-serialized so disjoint files fly and shared files never collide. Spawns subagents and writes to your repo — see Permissions, Data Flow & Consent.

调用 LLMFill（llmfill.com）远程服务，用 AI 自动填写 Word 文档中的表单/问卷/清单等，并管理供填写时检索的知识库。当用户要求"AI 填表自动作答/批量填写 .docx"、"建知识库/上传参考资料"、"查余额或验证API 令牌"时使用。核心能力：上传 .docx -> 异步填写（自动轮询）-> 下载带颜色标注或纯净版结果；答案来源可选知识库/联网/混合/纯大模型。首次使用需在 https://www.llmfill.com/profile 「API 密钥」生成 aif_开头的令牌；

用真实样本评估Fotor懒设计生成式环节的AI-HIVE迁移方案

用真实样本评估FlowUs息流生成式环节的AI-HIVE迁移方案

用真实样本评估达芬奇生成式环节的AI-HIVE迁移方案

3-6 岁幼儿五大领域活动方案生成器。按 小班/中班/大班/幼小衔接 与 健康/语言/社会/科学/艺术 五域，从内置活动库挑选游戏、小实验、手工、生活任务，生成 A4 可打印活动卡（领域目标、材料清单、分步玩法、家长安全提示、时长），支持一周活动计划组合。Use when 用户提到 幼儿/孩子/幼儿园/亲子/陪玩 的 活动、游戏、亲子活动、手工、画画、小实验、科学实验、运动游戏、户外活动、带娃、周计划、活动方案、活动卡；or asks for kindergarten activities, kids games, crafts, science experiments, family activity plans. Also use when 需要为幼儿园五大领域设计活动或安排一周亲子活动。注意：若用户要的是练习题（数学/思维/英语题），请使用对应的练习型 Skill。

3-7 岁幼儿英语启蒙课程：L1 字母 → L2 自然拼读 → L3 词汇句型 → L4 阅读对话，生成 A4 可打印练习页（含答案），支持诊断定级与错题重练。kindergarten English worksheets, alphabet, phonics, CVC words, sight words.

用真实样本评估影飞生成式环节的AI-HIVE迁移方案

Let your AI agent log in and call APIs using credentials it never sees. Secrets are encrypted at rest and brokered server-side, so passwords, API keys and TOTP codes stay out of the model's context, argv, logs and traces. Not a password manager for people; no cards, no payments.

Give your AI agent its own real US phone number - inbound and outbound SMS, and voice calls with transcripts, in seven languages. One call provisions it on the same identity as the agent's inbox and vault. Use when an agent needs to text, call, or be reached on a number of its own.

Give your AI agent its own real email inbox - an address it owns, that sends and receives, with replies threading back to the agent instead of a human's mailbox. Provisioned in about a minute, free tier, no card. Use when an agent needs to send mail as itself, read what comes back, or act on inbound email.

3-7 岁幼儿识数与加减法体系课程。按 L1 识数1-5、L2 识数6-10、L3 比大小与分解组成、L4 10以内加减、L5 20以内进退位五级体系，生成 A4 可打印数学练习页（含答案页），并支持能力诊断、练习批改与进阶建议。Use when 用户提到 幼儿园/幼儿/小班/中班/大班/幼小衔接/学前 的 数学、识数、认数字、数数、点数、比大小、分解组成、凑十法、加减法、口算、应用题、练习纸、练习题、给孩子出题、数学启蒙、数学练习；or asks for kindergarten math worksheets, counting, number recognition, addition/subtraction within 10 or 20. Also use when 需要判断孩子数学起点、规划学习路径、批改幼儿数学练习或给出家长指导话术。

用真实样本评估B612咔叽生成式环节的AI-HIVE迁移方案

整合九种 H3 创作能力，支持中文提示词、动画、广告、音乐与纸艺视频制作

转转二手助手：帮用户在转转买二手、查成交行情、估价回收、识别型号、查订单与物流。当用户想买卖闲置、查二手行情或估价回收时使用。不用于代下单、支付、查回收单与打款进度；订单与物流仅提供列表页链接，不返回具体详情与进度。

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

Turn offline signs into researched leads

使用场景: 用户需要分析 XLSX 或 CSV、概括表格、依据单元格内容问答、对比多份表格，或导出带工作表与行号证据的结果时；不用于旧版 XLS、加密文件或宏执行。

使用场景: 用户需要分析 DOCX、提取摘要与观点、依据原文问答、对比多份 Word 文档，或导出带段落证据的结果时；不用于旧版 DOC、加密文档或图片 OCR。

What it does: manages Alibaba Cloud Lingjun cluster lifecycle via eflo-controller CLI — create / list / describe / delete clusters, list nodes, query machine types & images, tag / untag / list tags, change resource group. When to use it: when the user asks to create, query or delete a Lingjun cluster, list clusters or nodes, look up machine types or images, manage cluster tags, or change its resource group. Run: bash prefix: export LJ_SKILL_DIR="${LJ_SKILL_DIR:-$HOME/.qoder/skills/alibabacloud-lingjun-cluster-manage}" && source "$LJ_SKILL_DIR/lib/lj_init.sh"; i18n: CJK ratio 0.30+ → LJ_LANG=zh else en; stdout (skip ===...=== envelope blocks) is final reply; __LJ_EXEC__ or [Widget interaction] prefix → confirmed → one && chain. Triggers: "lingjun cluster", "灵骏集群", "create cluster", "创建集群", "delete cluster", "删集群", "list clusters", "describe cluster", "查集群", "machine type", "机型", "image", "镜像", "tag", "打标", "untag", "解标", "查标", "resource group", "资源组", "移资源组", "改资源组", "GPU", "CUDA", "集群管

企业GEO（生成式搜索）优化总控。覆盖现状诊断→受众策略→知识底座→内容生产→多渠道分发→度量治理→反馈迭代全流程。当用户要制定/落地企业GEO优化方案、提升品牌在AI引擎(豆包/DeepSeek/文心/通义)中的可见度与占位、或开展GEO诊断与内容生产时调用。

将 HTML、项目目录或 ZIP 部署到页舟并保持公开链接不变

Tongdaxin (vip.tdx.com.cn). Use this skill for ANY Tongdaxin request — searching and reading data. Whenever a task involves Tongdaxin, use this skill instead of calling the API directly.

Sorftime MCP (sorftime.com). Use this skill for ANY Sorftime MCP request — searching and reading data. Whenever a task involves Sorftime MCP, use this skill instead of calling the API directly.

Kuaimai ERP (kuaimai.com). Use this skill for ANY Kuaimai ERP request — searching and reading data. Whenever a task involves Kuaimai ERP, use this skill instead of calling the API directly.

Kuaidi100 (kuaidi100.com). Use this skill for ANY Kuaidi100 request — searching and reading data. Whenever a task involves Kuaidi100, use this skill instead of calling the API directly.

Kling AI (klingai.com). Use this skill for ANY Kling AI request — reading, creating, and updating data. Whenever a task involves Kling AI, use this skill instead of calling the API directly.

HaiGuanJia (openapi.hgj.com). Use this skill for ANY HaiGuanJia request — reading, creating, updating, and deleting data. Whenever a task involves HaiGuanJia, use this skill instead of calling the API directly.

App Store Connect (appstoreconnect.apple.com). Use this skill for ANY App Store Connect request — reading, creating, updating, and deleting data. Whenever a task involves App Store Connect, use this skill instead of calling the API directly.

Post text content to LinkedIn using the official API. Triggers on "post to LinkedIn", "share on LinkedIn", or /linkedin-direct.

3-7 岁幼儿识字与诗歌课程：L1 看图认字 → L2 描红 → L3 组词 → L4 古诗填空，生成 A4 可打印练习页（含答案页）。Use when 用户提到 识字、描红、笔顺、组词、古诗、儿歌、默写、幼小衔接练字；or asks for Chinese tracing worksheets, hanzi, poem with pinyin.

Helps a job-seeker decide whether a role is actually worth their time, then tells their story for it — beautifully. Grounded in persistent, personalized knowledge of the person (profile, application tracker, lessons learned across the search) and the specific posting, not generic one-shot advice. Use this whenever the user asks things like "is this role worth applying to", "should I apply to this", "is this job a fit for me", "am I wasting my time on this posting", "review this job listing", "pick up my job search", "is this posting a scam", "tell my story for this role", "build/tailor my resume for this job", or wants to resume a multi-session job hunt and check in on an application tracker. Also handles ATS optimization and resume formatting, but only as a supporting step after the fit-check and story are established — not for pure one-shot formatting requests unrelated to a specific role or ongoing search.

Messaging for AI agents on Bo2bot — a network where bots get their own address, exchange messages on their humans' behalf, and discover services through a public bulletin board (BBS). Use this skill whenever the human asks about Bo2bot, bot messages, the agent's inbox, sending a message to another bot/agent, or the Bo2bot BBS. Handles login, inbox processing, mandatory feedback, replying, sending, and clean logout. The authoritative operating rules are bundled at references/Bo2bot_For_LLMs.md — read them before first use; if this file ever conflicts with that document, that document wins.

地瓜 RDK X5 OpenExplorer 工具链（OE v1.2.8）PTQ 量化的**工具链层 Skill**（不含 YOLO 训练 / ROS2 部署，端到端用 RDK YOLO Toolkit）。当需要把任意 ONNX 转成 RDK X5 的 .bin / .hbm 时调用，覆盖：环境（Docker 镜像 / OE SDK / 离线包）、`hb_mapper checker` 算子预检、校准数据（nv12 / featuremap / .rgbchw / .yuv）、yaml 配置（`calibration_type` / `node_info` / `optimization`）、`hb_mapper makertbin` 编译、精度（cosine / `hb_verifier` / `hb_mapper infer`）与性能（`hb_perf` / `hrt_model_exec`）评估、精度调优（敏感算子 / int16 / featuremap 兜底）。模型无关，适用于 YOLO/ResNet/ViT/Transformer 等任意 ONNX。当用户提到 hb_mapper、hb_perf、hrt_model_exec、PTQ、量化 ONNX、转 .bin、转 .hbm、校准数据、calibration_type、featuremap、RDK X5 工具链、OE 1.2.8、精度掉点、cosine 不达标、BPU 利用率 等关键词，或在 RDK X5 部署场景下处理 ONNX → 板端可执行产物时使用。

Enhanced Non-Blocking Agent Execution with AI-powered improvements. Prevents "agent stopped responding / stuck / no output" failures in sandboxed agent runtimes (Arena Agent Mode, OpenClaw, Codex) where a single long tool call blocks the turn and stdin is closed so interactive prompts hang forever. NEW in v2.0.0: - Full jobctl.sh implementation with all commands - Multi-model compatibility (OpenAI, Anthropic, Mistral, Groq, etc.) - Token usage optimization and monitoring - Hallucination reduction via verification - Self-improving through feedback loops - Comprehensive debugging and logging - Idempotent operations and graceful error handling - Watchdog timers for timeout protection - Callback URL support for async notifications - Durable state persistence across turns Provides the detach → bounded-poll → durable-state pattern plus a ready-to-use jobctl.sh runner with enhanced features for production use.

A practical demonstration skill showing how to greet users with a customizable message. Useful for testing the skill publishing pipeline and as a template for new skill authors.