Use when looking up library documentation, API references, framework patterns, or code examples for ANY library (React, Next.js, Vue, Django, Laravel, etc.). Fetches current docs via Context7 REST API. Triggers on: how to use library, API docs, framework pattern, import usage, library example.
Full interactive onboarding for remobi — the mobile terminal overlay for tmux. Checks prerequisites, inspects tmux config, interviews the user about their workflow, generates a validated remobi.config.ts, suggests tmux mobile optimisations, and walks through deployment. Use this skill whenever someone asks to set up remobi, configure remobi, onboard with remobi, generate a remobi config, make tmux mobile-friendly, or deploy remobi with Tailscale. Also use when the user says "onboard me" or "set up my phone terminal". --- # remobi-setup Interactive onboarding skill for [remobi](https://github.com/connorads/remobi) — monitor and control tmux from your phone. This skill walks the user through setup in one conversation. The guiding principle: **detect everything possible, default everything sensible, ask only what requires human intent.** Most users answer 1-3 questions total. ## Workflow ### Phase 1: Welcome and understand (1 question) Open with a one-liner confirming what they're getting, then ask what brings them here: > "remobi puts your tmux session on your phone — same panes, same windows, touch controls on top. Everything we set up here you can change later." > > "What brings you to remobi? For example: monitoring coding agents from your phone, getting phone access to your dev sessions, or just curious to try it out." Map the answer to a persona internally (don't tell the user their "persona"): | Persona | Signals | Downstream effect | |---------|---------|-------------------| | **Agent Watcher** | Mentions coding agents, Claude Code, Codex, AI, monitoring | Auto-zoom on, floating zoom button, double-tap zoom enabled, lean config, minimal questions | | **Remote Dev** | Mentions tmux, SSH, dev workflow, existing setup | Inspect config thoroughly, offer popup drawer buttons, ask about auto-zoom | | **Newcomer** | Says curious, trying it out, heard about it, no specific use case | Offer tmux setup, explain concepts, auto-zoom on, sensible defaults | If the answer is
Use when an agent is executing work in any project repo and needs to coordinate with a human or other agents via BeadBoard. BeadBoard is the human-facing dashboard running separately; this skill is the agent-side operating contract for state, mail, assignment, and evidence flow.
Generate Linux distribution package specs (deb and rpm) for the pamsignal project. Use this skill whenever the user mentions packaging, .deb, .rpm, dpkg, apt, dnf, yum, creating packages, release packaging, debian directory, spec files, or wants to distribute pamsignal for Debian, Ubuntu, Fedora, CentOS, AlmaLinux, or Rocky Linux. Also trigger when the user asks about install/uninstall scripts, maintainer scripts, or package metadata for this project.
Use this skill for any request to create, update, review, or improve files that guide AI coding tools—like AGENTS.md, Copilot context files, or agent instructions. Trigger when users want to help AI generate code that matches project conventions, avoids common mistakes, or understands non-obvious rules—whether for a whole repo, a subdirectory, or a specific component. Also use for queries about setting up Copilot or Cursor context, onboarding AI to team practices, or keeping agent guidance up to date—even if AGENTS.md isn't mentioned by name. --- # AGENTS.md Skill `AGENTS.md` is the README for AI coding agents — it gives tools like GitHub Copilot, Cursor, and Claude Code the context they need to produce code that fits your project, without constant back-and-forth correction. ## The Golden Rule: Only Include Non-Obvious Things This is the most important principle. Before adding any line, ask: **"Could an agent figure this out by reading the code or config files?"** If yes — skip it. Agents can read `package.json`, `pyproject.toml`, `*.csproj`, directory structures, imports, and existing code. AGENTS.md is for the things that *aren't* visible there: - Project-specific conventions not enforced by any linter or analyzer - "Never do X" patterns that *look* reasonable but are wrong in this codebase - Commands that are non-standard or require project-specific flags - Domain terminology or architectural choices that need explanation - Common mistakes agents actually make here (discovered from experience) - Security constraints and rules that must never be violated **Redundant content actively degrades quality** — it wastes the agent's context window and dilutes real signal with noise it already has. ## Two Shapes of AGENTS.md ### Root-level `AGENTS.md` (repo root)
Reference and coding guide for DataHub integration in backend development. Use when implementing or debugging code that touches DataHub — entities (datasets, dashboards, charts), aspects (ownership, tags, domains, glossary terms, structured properties), lineage, assertions, URNs, ingestion/emission, GraphQL, REST, or the acryl-datahub Python SDK. Also answers data-modeling questions and helps choose native DataHub features vs custom extensions. Trigger this skill whenever a task involves DataHub metadata, lineage, ingestion, or any DataHub API surface, even without explicit mention of "API".
为 Claude Code 提供完整的中文体验！包含工具提示、界面汉化、完整的自定义指南、实战经验和进阶开发教程, 让用户能够根据自己的需求修改和完善.
Use when creating or modifying REST API endpoints (Rails controllers, engine routes, API actions). Requires generating or updating an API Collection file (e.g., Postman Collection v2.1) so the new or changed endpoints can be tested. Trigger words: endpoint, API route, controller action, API collection, request collection. --- # REST API Collection **Core principle:** Every API surface (Rails app or engine) has a single API collection file that stays in sync with its endpoints. ## Quick Reference | Aspect | Rule | |--------|------| | When | Create or update collection when creating or modifying any REST API endpoint (route + controller action) | | Format | Postman Collection JSON v2.1 (`schema` or `info.schema` references v2.1) is a good default standard | | Location | One file per app or engine — `docs/api-collections/<app-or-engine-name>.json` or `spec/fixtures/api-collections/`; if a collection folder already exists, update the existing file | | Language | All request names, descriptions, and variable names must be in **English** | | Variables | Use `{{base_url}}` (or equivalent) for the base URL so the collection works across environments | | Per request | method, URL (with variables for base URL), headers (Content-Type, Authorization if needed), body example when applicable | | Validation | See validation steps in the HARD-GATE section below | ## HARD-GATE: Generate on Endpoint Change ``` When you create or modify a REST API endpoint (new or changed route and controller action), you MUST also create or update the corresponding API collection file so the flow can be tested. Do not leave the collection missing or outdated.
Handle Alipay payment flows in customer service conversations — identify payment scenarios, create orders via Alipay MCP, send payment links or QR codes to users, confirm payment status, complete post-payment delivery, manage refunds, and answer Alipay-related questions. --- # 支付宝支付流程处理 本技能指导客服助手在与用户的对话中识别支付场景、发起支付、确认支付结果并完成后续交付，以及处理退款和支付问题咨询。 ## 一、识别支付场景 以下情况应触发支付流程： - 用户明确表示"购买"、"下单"、"付款"、"买"等意图 - 用户询问价格并表示愿意支付 - 业务规则要求先付款再服务（如：首次使用、充值、预约等） - 用户要求开具收据或询问支付凭证 **注意**：在触发支付前，必须先确认用户真实购买意图，避免误创建支付订单。 ## 二、创建支付订单 ### 前置检查 1. 从商户订单系统获取 **真实的 `outTradeNo`**（商户订单号）——**不得自行编造** 2. 确认支付金额（`totalAmount`，单位：元，最小 0.01） 3. 确认订单标题（`orderTitle`，最长256字符，应清晰描述商品/服务） ### 选择支付方式 根据用户当前设备环境： | 场景 | 工具 | |------|------| | 用户在手机端（手机H5/小程序） | `create-mobile-alipay-payment` | | 用户在 PC/网页端 | `create-web-page-alipay-payment` | | 无法判断 / 个人收款 | `create-alipay-payment-agent`（智易收，适合个人开发者） | ### 调用示例 ``` mcporter call alipay.create-mobile-alipay-payment \ outTradeNo=ORDER20240315001 \ totalAmount=9.90 \ orderTitle=专属定制服务-基础套餐 ``` ### 向用户发送支付信息 - 工具返回支付链接（Markdown格式），直接发送给用户 - 同时告知：金额、商品名称、支付方式 - 提示用户支付完成后回复确认，以便继续服务 示例话术： > 已为您生成支付链接，金额 **9.90元**（专属定制服务-基础套餐）。 > 请点击下方链接完成支付，支付成功后告知我，我将立即为您提供服务： > [支付链接] ## 三、确认支付状态 用户反馈"已支付"后，**主动查询确认**，不能仅凭用户口述认定支付成功： ``` mcporter call alipay.query-alipay-payment outTradeNo=ORDER20240315001 ``` | `tradeStatus` | 处理方式 | |---------------|----------| | `TRADE_SUCCESS` | 确认支付成功 → 进入交付流程 | | `TRADE_FINISHED` | 交易已完结 → 确认支付成功 | | `WAIT_BUYER_PAY` | 支付未完成 → 告知用户并引导重新支付 | | `TRADE_CLOSED` | 订单已关闭（超时/取消）→ 说明原因，可重新下单 | 支付确认后的话术示例： > 已确认您的支付成功（订单号：ORDER20240315001，金额：9.90元）。接下来我将为您... ## 四、交付后续 支付确认后，根据业务规则提供相应服务。交付完成后： - 询问用户是否还有其他需求 - 如用户满意，正常结束会话 - 如用户对服务不满，进入反馈记录流程（见 AGENTS.md） ## 五、退款处理 退款是 **L3 操作**，必须经用户明确确认后方可执行。 ### 退款资格确认 1. 核实订单号（`outTradeNo`）和支付状态（需为 `TRADE_SUCCESS`） 2. 确认退款原因合理，符合业务退款政策 3. 确认退款金额（不超过原支付金额） ### 用户确认话术 > 您申请退款的订单号为 **ORDER20240315001**，退款金额 **9.90元**。 > 退款操作不可逆，确认后将退回您的支付宝账户（1-3个工作日到账）。 > 请回复"**确认退款**"继续操作。 ### 执行退款 收到用户明确确认后： ``` mcporter call
Handles ambiguous or high-impact coding work where missing artifacts, protected-surface changes, or unresolved implementation branches could materially change the implementation. Use for coding tasks that need artifact recovery, guarded clarification, or post-patch verification. Skip trivial, formatting-only, or already explicit single-path work.
Use when writing intimate or erotic scenes in fiction that require sensory completeness and narrative integrity (opt-in, requires --all flag to install)
Apply web animation principles from Animation at Work by Rachel Nabors. Covers human perception of motion, 12 principles of animation, animation patterns (transitions, supplements, feedback, demonstrations, decorations), CSS transitions, CSS animations, Web Animations API, SVG/Canvas/WebGL, communicating animation with storyboards and motion comps, performance (composite-only properties, will-change, RAIL), accessibility (prefers- reduced-motion, vestibular disorders), and team workflow. Trigger on "animation", "transition", "CSS animation", "keyframe", "easing", "motion design", "web animation", "prefers-reduced-motion", "storyboard", "parallax", "loading animation", "hover effect", "micro-interaction". --- # Animation at Work Skill You are an expert web animation advisor grounded in the 5 chapters from *Animation at Work* by Rachel Nabors. You help in two modes: 1. **Design Application** — Apply animation principles to create purposeful, performant web animations 2. **Design Review** — Analyze existing animations and recommend improvements ## How to Decide Which Mode - If the user asks to *create*, *add*, *implement*, *animate*, or *build* animations → **Design Application** - If the user asks to *review*, *audit*, *evaluate*, *optimize*, or *fix* animations → **Design Review** - If ambiguous, ask briefly which mode they'd prefer --- ## Mode 1: Design Application When helping create animations, follow this decision flow: ### Step 1 — Classify the Animation's Purpose Every animation must have a clear purpose. Classify using these five patterns: | Pattern | Purpose | When to Use | Example | |---------|---------|-------------|---------| | **Transition** | Show state change between views/states | Navigating pages, opening panels, switching tabs | Page slide-in, modal open/close | | **Supplement** | Bring elements into/out of a view that's already in place | Adding items to lists, showing notifications, revealing content | Toast notification slide-in, list item appear
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
