Explore

Analyze an upstream product, dependency, or platform release for downstream impact on the current repo. Use when the user gives a package or repo name such as `openclaw` or `GOG-CLI`, or asks about release notes, changelogs, tags, dependency bumps, or upstream announcements. Resolve the GitHub repository, read the latest release or tag notes, and assess breaking changes, redundant features, new opportunities, test needs, and recommended follow-up work for a wrapper or integration product such as AlphaClaw relative to OpenClaw.

Sync runtime data from a Railway deployment into local Docker for realistic testing. Use when the user asks to copy Railway data, clone production state locally, or test with real usage/session/config data.

Use when changing shared Free4Chat CSS, layout, responsive behavior, visual components, or interaction affordances; verify the real routes and browser hit targets affected by the change.

Strict provenance-first SOP for real deployed Free4Chat Meeting Notes, Voice Reply, Pion, Cloudflare SFU, and browser-media experiments.

free4chat local full-stack E2E loop — single wrangler instance, Turnstile bypass switches, curl/MCP validation sequences, split-brain DO and daemon env traps. Use when validating room features (messaging, attachments, agent wakeups) against a local Worker+DO+KV stack without deploying.

Diagnose one Free4Chat Room App or Generated Task App lifecycle failure across Browser, Room projection, and Runtime using bounded existing diagnostics. Requires valid Runtime provenance before comparing evidence; stops before speculative implementation.

Run a real, temporary Cloudflare Workers dogfood flow for Free4Chat without touching production.

Prepare, publish, activate, and dogfood a Free4Chat Go Agent Runtime release. Use for a new free4chat-agent version; not for an ordinary Worker-only deployment.

free4chat Agent media plane (Go runtime, in-process Pion) architecture quick reference and staged debugging discipline — multi-MID attribution, signaling direction self-inspection, lazy OnTrack, daemon/env traps. Use when debugging Meeting Notes audio, Voice Reply, image/text attachments, unresponsive agents, or non-flowing RTP.

蒸笼：蒸馏任何人的叙事入口——对齐数字永生引擎，强调生活化「蒸」与公开方法论顾问场景；委托上级 kit/personas 执行。

蒸馏陈韵的全维度数字分身：产品设计方法、沟通风格、人生经历与价值观。仅用于个人备份与辅助回忆，非对外冒充。

蒸馏王老师的指导方式与核心教诲。用于延续导师的教学智慧与指导风格，辅助学习与回顾。

模拟李工（后端工程师）在架构评审、发布流程、跨团队对齐场景下的工作方式与沟通边界。用于团队内部对齐与培训。

Distill Shield：为个人移交资料包生成 Canary 与可选加固策略，提高未授权蒸馏成本；仅适用于有权处置的数据。

蒸馏协议：为个人数字资料生成人类可读条款与机器可读 manifest；戏称「牛马保护法」仅为传播梗，非法律意见。

通用数字永生框架：从聊天记录、社交媒体、文档等多平台数据中蒸馏任何人的数字分身——支持自己、同事、导师、亲人、伴侣/前任、朋友、公众人物 7 种角色模板，接入国内外 12+ 数据平台。

Product design system for the FinSight AI evidence-driven equity research workspace.

Browse websites, use signed-in web apps, and test local web interfaces through DSCODE's session browser. Prefer a purpose-built API or CLI when it directly supports the requested operation.

Fetch tweets, replies, timelines, search results, X Lists, and X Articles from X/Twitter without login or API keys. Single tweets: zero dependencies (FxTwitter). Timelines/search/replies: a Nitter instance (XTF_NITTER). Lists/Articles: a browser driver (Camofox or Playwright). Unified JSON schema across all backends; machine-readable error_code for agent branching. Field reports and agent-use questions: Agent Waystation #22 Teahouse: https://github.com/ythx-101/openclaw-qa/discussions/22

Configure saved VNC targets, explain connection history and hidden controls, and test a real disposable x11vnc desktop without touching production.

Create final Chinese handdrawn technical article/PPT-style page images from articles, Markdown, PDFs, DOCX files, existing slide decks, course notes, scripts, outlines, or rough ideas. Use when the user asks to turn content into PPT/PPTX/slides/courseware/课件/演示稿/配图/效果图 in a refined Chinese handdrawn technical explanation style, to plan such pages, to choose page layouts from semantic content, or to generate complete image-model pages with Chinese text baked into the final visual. Default article outputs use 21:9 covers and 16:9 body illustrations.

当用户需要基于品牌官网抓取、公开事实交叉验证、内容资产诊断、站内站外 GEO 机会地图、项目启动诊断、季度复盘或投放前评估时使用；不用于问答平台采样监测、单页诊断、文章写作、标题生成、后端归因或执行路线图拆解。

Spatial and temporal convergence analysis with Richardson extrapolation and Grid Convergence Index (GCI) for solution verification

Search and retrieve preprints from arXiv via the Atom API. Use this skill when searching for papers in physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering, or economics by keywords, authors, arXiv IDs, date ranges, or categories.

当用户要求数据可视化、做图表、生成看板、数据仪表盘、可视化报告、Excel/CSV 转图表、预算/销售/运营等指标分析页面、Chart.js 可视化时使用。只处理数据可视化任务；纯网页、banner、海报、简历等非数据图表设计任务应交给 visual-design。数据报告页以图表为主体归本技能；以文案排版为主体的静态报告页归 visual-design。

何时用:仅当用户明确指定 doc/docx/word/在线文档/office文档或提供 doc.weixin.qq.com/doc/ 链接时使用;泛指「做个文档/写文档/整理成文档」默认走 wecomcli-smartpage 或本地工具,本技能不得抢占。doc 内容操作:新建、导入(.doc/.docx/.txt)、读取、追加、覆盖写入;结构化数据需求改用智能文档/智能表格;公共管理走 wecomcli-doc-manage。

Open, create, read, analyze, edit, or validate Excel/spreadsheet files (.xlsx, .xlsm, .csv, .tsv). Use when the user asks to create, build, modify, analyze, read, validate, or format any Excel spreadsheet, financial model, pivot table, or tabular data file. Covers: creating new xlsx from scratch, reading and analyzing existing files, editing existing xlsx with zero format loss, formula recalculation and validation, and applying professional financial formatting standards. Triggers on 'spreadsheet', 'Excel', '.xlsx', '.csv', 'pivot table', 'financial model', 'formula', or any request to produce tabular data in Excel format.

Use this skill when visual quality and design identity matter for a PDF. CREATE (generate from scratch): "make a PDF", "generate a report", "write a proposal", "create a resume", "beautiful PDF", "professional document", "cover page", "polished PDF", "client-ready document". FILL (complete form fields): "fill in the form", "fill out this PDF", "complete the form fields", "write values into PDF", "what fields does this PDF have". REFORMAT (apply design to an existing doc): "reformat this document", "apply our style", "convert this Markdown/text to PDF", "make this doc look good", "re-style this PDF". This skill uses a token-based design system: color, typography, and spacing are derived from the document type and flow through every page. The output is print-ready. Prefer this skill when appearance matters, not just when any PDF output is needed.

Convert photos (people, pets, objects, logos) into 4 animated GIF stickers with captions. Use when: user wants to create cartoon stickers, GIF expressions, emoji packs, animated avatars, or convert photos to Funko Pop / Pop Mart blind box style animations. Triggers: sticker, GIF, cartoon, emoji, expression pack, avatar animation.

使用AI大模型根据文字、首尾帧图片或图片/视频/音频参考素材生成带对白和环境音的视频。适用于文生视频、图生视频、首尾帧过渡和多模态参考视频生成，通过 Deep Code Plus 试算积分、确认后上传素材并生成视频。

Reviews and improves another DeepCode skill's SKILL.md description field, and guides Agent Skill installation into user or project .agents/skills roots. Use when the user asks to digest a skill, install an Agent Skill, install a skill to user/project scope, or says "消化技能" or "安装 agent skill".

为 PanWatch 的功能开发或修复完成本地隔离验收、证据报告、自动创建或更新 PR 并附上测试报告，以及人工验收交接。用户要求完整交付、本地真实 UI 验收或验收报告时使用；按本次需求生成业务用例。

Build and maintain a company knowledge base as a wiki of interlinked markdown notes in the workspace — a private, compounding Wikipedia. Use when the user wants to start or organize a knowledge base / wiki, ingest sources (URLs, documents, pasted notes) into it, ask questions answered from it, or audit (lint) it. Defines the wiki layout (SCHEMA / index / log / raw / pages), the frontmatter contract, [[wikilink]] conventions, and a deterministic lint script that catches broken links, orphan pages, index drift, and frontmatter problems.

Sign a Google account into its own gws config dir and register it (tagged). Used by google-workspace-setup; runs the OAuth login + records the account.

Detection engine for Gmail email watches: iterates the watch list, polls gws for new matching mail per watch, dedups, drops automated/self, and hands matches (labeled by sender) to the shared drafting turn. Provisioned and run automatically by the shared email-watch backing job.

Move bytes between Gini upload space, external URLs, and workspace files. Used by every attachment / file-upload / file-download flow regardless of the target system (Linear, GitHub, S3, Notion, etc.).

面向 Deepseek Harness EAC 源码仓库的全栈开发与维护技能。处理 Tauri/Rust 桌面壳、Node sidecar、Web bridge、DSH 插件与 preset、profile 治理、更新打包、可靠性修复、测试验收和发布准备时使用；不用于客户端功能使用说明，也不负责专项 JS 到 TS 迁移。

SolidWorks VibeCAD 参数化设计规划子技能。用于把自然语言机械设计需求转成结构化设计计划、制造规则检查、SolidWorks API 执行摘要和审查门禁；当任务涉及 text-to-CAD、vibecoding 固化、行业知识库、提示词模板、参数化建模计划、CNC 安装座/连接块/支架批量生成时使用。

SolidWorks ISO 公制内螺纹孔自动化子技能。用于创建和审查 M3-M12 粗牙或用户明确底孔的自定义公制内螺纹，覆盖攻丝底孔、盲孔/贯穿孔、孔口倒角、右旋/左旋、ThreadFeatureData/CosmeticThread 降级和交付证据。用户要求 Hole Wizard、修改现有零件、外螺纹、英制/管螺纹或显式牙型时也应读取本技能，但这些能力必须按路线图标为 pilot 或人工复核，不得宣称已稳定实现。

SolidWorks CNC 零件的多圆角/倒角自动化子技能。用于安装座、连接块、支架、沉孔板等模型的参数预检、语义选边、多控制点可变半径、face/full-round/setback、G2 曲面组合、宽度-宽度倒角、角度倒角、孔口倒角、CNC 友好口袋、有界降级和重建证据。

SolidWorks 工程图生成与制造交付审视子技能，支持 GB/T 第一角零件图、装配图、尺寸链、孔表、BOM、PDF/BMP 证据和钣金能力门禁。

AutoCAD 自动化技能。用于让 Codex/Claude 在 Windows 上通过 Python COM/ActiveX 直连本机 AutoCAD 进行二维绘图、图层/文字/标注/块处理、DWG/DXF/PDF 导出、批量修改、工程图自检，以及在 COM 不足时切换到 AutoLISP/SCR 或 AutoCAD .NET 插件路线；当用户提到 AutoCAD、CAD、DWG、DXF、画图、出图、图层、标注、块、批量改图、AutoLISP、ObjectARX、.NET 插件、Codex 接入 CAD 软件时都应优先使用。

Use only for explicit legacy GEOFlow template skill questions, old PHP template-package contracts, or historical outputs using root index.php/article.php/category.php/archive.php and includes/*.php. Route current Laravel Blade themes, reference-site cloning, homepage modules, lead_form, theme editor, channel frontend, and target-package mapping to yao-geoflow-design. Do not use for new frontend design, backend implementation, raw HTML copying, or live activation.

Discover, compare, preview, clone, and orchestrate current GEOFlow frontend experiences across the default site and GeoFlow Agent channel sites, including Laravel Blade themes, homepage module/style JSON, lead_form conversion modules, theme editor, target-package capabilities, and cross-channel sync planning. Use for frontend theme discovery, reference-site mapping, homepage builder design, channel capability audits, and preview-first design iteration. Do not use for CLI operations, backend implementation, lead-form CRUD, raw HTML copying, unsupported remote edits, or direct live activation.

Use when operating an existing GEOFlow 2.1+ system from CLI, API v1, or authenticated admin web for catalog/material/task/job/article operations, enterprise knowledge, growth-center leads, distribution, analytics, URL import, theme editor, frontend-capability sync, system updates, settings, tokens, users, or preflight. Do not use for implementation, schema changes, direct DB edits, frontend design, or invented API routes.

用浏览器采集小红书顶部搜索框的联想词，按词根和第一层联想词做两层扩展，逐次截图、记录下拉位置与来源路径，按行业转化目标评 1–10 分商业价值并生成 Excel。适用于小红书相关搜索词拓展、两层关键词采集包和截图留证；仅查笔记内容、话题热度或账号排名时不触发。

Use when Chinese content teams need GEO title candidates, scoring, compliance review, or title-to-article mapping for articles, pages, FAQs, comparisons, and topic hubs.

当用户需要基于品牌 Brief、选题配置、关键词、竞品库和可信来源生成 GEO 榜单评测文章、best/top/alternatives/vs/persona/use-case 意图内容、评选方法、核心对比表、榜单正文、适合人群、FAQ、来源表和 Word/PDF/HTML/Markdown 四格式文章包时使用；适配 DeepSeek、豆包、千问、Kimi、元宝；不用于全景诊断、后台归因、单页审计、纯标题生成或无证据软文排行。

GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]

Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.

Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.

Design scientific experiments including sample size calculation, randomization, control groups, blinding, and study protocols. Covers RCTs, quasi-experiments, factorial designs, A/B tests, survey design, and observational studies. Use when user asks to design an experiment, calculate sample size, plan a study, set up controls, or create a research protocol. Triggers on "design experiment", "sample size", "power analysis", "study design", "control group", "randomization", "A/B test", "factorial design", "survey design".

Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.

Execute autonomous multi-step deep research on any topic. Use when the user asks for comprehensive research, literature reviews, competitive analysis, topic deep-dives, or wants to understand a complex subject from multiple angles. Triggers on "deep research", "research on", "investigate", "literature review", "comprehensive analysis", "what do we know about", "summarize research on".

Computer science bibliography via DBLP API. Use when: user asks about CS publications, author publication lists, or venue (conference/journal) metadata. NOT for: non-CS publications or citation counts.

Scientific data analysis including data cleaning, exploratory data analysis (EDA), statistical testing, regression, and reporting. Uses Python with pandas, scipy, statsmodels, scikit-learn. Use when user asks to analyze data, clean a dataset, run statistics, do EDA, fit a model, or process CSV/Excel files. Triggers on "analyze this data", "clean my dataset", "run regression", "EDA", "descriptive statistics", "data processing", "correlation analysis".

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.