586 skills · sorted by relevance
AI配图能力层 Skill。任何需要生成信息图的任务都调用此 Skill，而不是自行调用 API。包含：模型选择、API调用、多视角草图流程、风格库引用、配图索引联动。触发词：「需要绘图」「生成配图」「画一张图」「制作信息图」「根据这段文字画图」「图片提示词」。
The English summary is being prepared. Showing the original description.
采集科研数字分身的基础信息（研究阶段、学科领域、方法范式、技术能力、科研流程能力）。当用户开始建立科研数字分身、或基础信息尚未填写时使用。
The English summary is being prepared. Showing the original description.
为L1文档创建新的x.0版本快照，标志一次重大变更的里程碑。触发词：「创建新版本」「打一个快照」「这是v2.0了」「这次改动很大」「记录一下这个版本」。
The English summary is being prepared. Showing the original description.
生成认知结构当前状态快照，帮助用户了解知识体系全貌并决定今日优先处理项。触发词：「大脑地图」「认知状态」「今天做什么」「复盘」「系统状态」「看一下状态」「有什么积压」。
The English summary is being prepared. Showing the original description.
生成今日认知系统汇报：整合L3记录、待完成项、知识库状态，并主动提问帮助用户恢复上下文。触发词：「汇报」「今天有什么」「有什么更新」「同步一下状态」「有什么积压」「今日简报」「最近新了什么」。
The English summary is being prepared. Showing the original description.
对认知结构运行完整的C1-C10一致性验证，输出验证报告并修复发现的不一致。触发词：「一致性检查」「自洽检查」「验证认知结构」「检查有没有问题」「跑一遍验证」。批量操作完成后自动触发。
The English summary is being prepared. Showing the original description.
代码库探索与架构理解 Skill。接手任何代码库时激活：扫描目录结构，识别技术栈，读取核心文件，提取架构模式，与产品定义/需求对比，输出可信赖的架构理解文档。触发词：「阅读XXX项目」「理解这个代码库」「写技术架构文档」「这个项目是做什么的」「接手这个项目」「帮我读一下这个代码」。
The English summary is being prepared. Showing the original description.
Bug修复循环协调者。测试完成后，读取技术问题追踪台，按P0→P1→P2顺序协调修复，每修复一个触发针对性回归测试，循环直至P0+P1全清，输出可上线结论。所有信息通过文档传递，不依赖对话历史。触发词：「全自动修复循环」「按Bug清单修复」「修复所有问题」「循环修复到上线」「开始bug修复循环」。
The English summary is being prepared. Showing the original description.
管理他山公众号的配图风格库，提供风格模板调用和新风格沉淀。触发词：调用风格库/用XX风格/存入风格库/更新风格模板/风格库有哪些风格。
The English summary is being prepared. Showing the original description.
分析文章可用的多种配图视角，为每个角度生成提示词草图供用户选择。触发词：帮我分析配图角度/生成多视角草图/配图有几种选择/给我几个配图方案。
The English summary is being prepared. Showing the original description.
施测科研人员认知风格量表（RCSS），评估横向整合 vs 垂直深度的认知偏好。当用户选择填写量表、或画像中RCSS数据缺失时使用。
The English summary is being prepared. Showing the original description.
施测大五人格量表（Mini-IPIP，20题），评估外向性、宜人性、尽责性、神经质和开放性。当用户选择填写量表、或画像中人格数据缺失时使用。
The English summary is being prepared. Showing the original description.
施测学术动机量表（AMS-GSR 28），采集科研人员的内在动机、外在动机和无动机数据。当用户选择填写量表、或画像中AMS数据缺失时使用。
The English summary is being prepared. Showing the original description.
Guides developers through downloading, configuring, and installing the official open-source Google Ads MCP Server. Use this skill when a user wants to connect their AI assistant (such as Gemini, Claude Code, or Cursor) to their Google Ads account to query campaigns or retrieve reporting metrics using natural language.
The English summary is being prepared. Showing the original description.
Resume Treadmill LC (load-cell GRF) work after the 2026-08-17 English translation. Use when the user reopens treadmill_lc, asks where that work stopped, wants Antigravity/Cursor to continue coding, or mentions COP mediolateral/anteroposterior labels, tare/weight calibration files, or tests/treadmill_lc.
The English summary is being prepared. Showing the original description.
YOLO + FB chooser (Frame B), Sapiens2 Pose, and GUI→CLI terminal mirror for vailá video-AI tools. Use when reopening Cursor CLI, wiring GUI buttons, printing copy-paste CLI from Tkinter runs, or continuing work on vaila.py yolotrackerpose / vaila_sam / vaila_sapiens / yolov26track / yolotrain.
The English summary is being prepared. Showing the original description.
Master AI-integrated development environments with comprehensive coverage of Windsurf, Cursor, Antigravity, Zed, Cline, and FOSS newcomers, including intelligent usage patterns, cost optimization, and the evolution toward fully agentic development
The English summary is being prepared. Showing the original description.
Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Grok Build, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, autoloop autonomous workspace iteration, ultraapp building deployable web apps from a structured Q&A interview, switching models/tools at runtime, exposing the orchestrator's 78 tools as an MCP server to Hermes Agent / Claude Desktop / Cursor / Cline / Continue / Zed / Windsurf / Goose, or running as an Agent Client Protocol (ACP) agent that Zed / JetBrains / Neovim / Emacs / VS Code / dsh can drive directly. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "autoloop", "ultraapp", "Forge tab", "build a web app", "one-click app", "AppSpec", "autonomous iteration", "iterate until goal", "auto research", "switch model", "hand off a session", "session handoff", "switch engine", "continue on codex", "continue on claude", "move this session to another engine", "multi-agent coding", "coding session", "session inbox", "grok session", "grok build", "opencode", "mcp server", "clawo-mcp", "hermes mcp", "model context protocol", "ultracode", "dynamic workflow", "fanout", "fan-out", "best-of-N", "steer turn", "interrupt turn", "fork thread", "rollback turns", "acp", "agent client protocol", "clawo acp", "zed agent", "jetbrains agent", "external agent", "dsh subagent", "deepseek harness", "clawo runs", "run ledger", "session cost", "coding-agent token usage", "spend cap", "budget limit", "maxBudgetUsd", "durable workflow", "resume a run", "verify a coding run", "acceptance contract", "evidence bundle", "did the agent's tests actually pass", "protected tests", "agent edited the tests", "human gate", "repair loop", "clawo workflow", "clawo verify", "clawo solve", "clawo fanout", "fix and verify", "solve from the terminal".
The English summary is being prepared. Showing the original description.
Read and reuse AI coding session context across Claude Code, Codex, Antigravity/agent hooks, Cursor adapters, and compatible AI tools. Use this skill whenever the user asks to read, inspect, resume, compare, or continue another session by name or session ID, asks what happened in the previous session, or starts a new session that should inherit the nearest prior context. The paired provider adapter automatically loads the nearest previous project session at startup and resolves explicit session-read requests.
The English summary is being prepared. Showing the original description.
Research complex questions and synthesize relevant evidence into a clear, cited answer. Useful for competitive and market analysis, company research, prospect discovery, enrichment, historical comparisons, and evaluating conflicting claims. Adapt the depth and format to the question; use when a focused search or single-page read is insufficient.
The English summary is being prepared. Showing the original description.
Use when a request needs external sources, current facts, listings, a supplied URL, papers, or library and API documentation. When using Firecrawl for the request, use firecrawl_search to find sources and firecrawl_scrape to read a supplied or discovered URL. Firecrawl also retrieves documents, collects structured data, and tracks website changes. Respect explicit source and tool preferences.
The English summary is being prepared. Showing the original description.
Appwrite Ruby SDK skill. Use when building server-side Ruby applications with Appwrite, including Rails and Sinatra integrations. Covers user management, database/table CRUD, file storage, and functions via API keys.
The English summary is being prepared. Showing the original description.
Appwrite .NET SDK skill. Use when building server-side C# or .NET applications with Appwrite, including ASP.NET and Blazor integrations. Covers user management, database/table CRUD, file storage, and functions via API keys.
The English summary is being prepared. Showing the original description.
Appwrite Python SDK skill. Use when building server-side Python applications with Appwrite, including Django, Flask, and FastAPI integrations. Covers user management, database/table CRUD, file storage, and functions via API keys.
The English summary is being prepared. Showing the original description.