Always use when user asks to create, generate, draw, or design a diagram, flowchart, architecture diagram, ER diagram, sequence diagram, class diagram, network diagram, mockup, wireframe, or UI sketch, or mentions draw.io, drawio, drawoi, .drawio files, or diagram export to PNG/SVG/PDF.
Creating and refining Mermaid diagrams with live reload. Use when users want flowcharts, sequence diagrams, class diagrams, ER diagrams, state diagrams, or any other Mermaid visualization. Provides best practices for syntax, styling, and the iterative workflow using mermaid_preview and mermaid_save tools.
Automatically analyze a codebase and generate an architecture diagram with zero configuration. Use when the user asks to "diagram this repo", "visualize the architecture", "auto diagram", or requests a codebase overview without specifying components. Do NOT use when the user provides a specific description, sample diagram, or component list — use the excalidraw skill instead.
Desktop-first Draw.io diagram creation, editing, replication, and conversion (redraw, remake, 重画, 绘图, 画图, 做个图) with a YAML design system supporting 6 themes. Use when creating visual diagrams, drawings, figures, schematics, charts, system architecture diagrams, network diagrams, flowcharts, UML, ER diagrams, sequence diagrams, state machines, org charts, mind maps, cloud infrastructure diagrams, research workflows, paper figures, IEEE-style diagrams, or diagrams containing formulas, equations, LaTeX, AsciiMath, MathJax, inline math, block math, 公式, 行内公式, or 行间公式. Accepts Mermaid, CSV, and YAML input; convert to drawio from mermaid to drawio or any structured source. Default to offline/local generation with `.drawio` + sidecars; use an optional live backend only when browser or inline refinement is genuinely needed.
Interactively generates production-ready SVG diagrams including flowcharts, sequence diagrams, mind maps, org charts, timelines, ER diagrams, and state diagrams. Use when the user wants to create, visualize, or export any kind of diagram, flowchart, process map, or visual representation of relationships and workflows. Guides users through selecting diagram size, color scheme, information density, layout direction, and connector style before generating clean, accessible SVG code.
Living Architecture Map — auto-generate Mermaid diagrams of your codebase. Use when user wants to visualize architecture, understand code structure, generate diagrams, or document system design.
Generate clean SVG diagrams (flowchart, tree, mindmap, architecture, sequence, quadrant, gantt, state machine, ER, timeline, swimlane, bubble chart, radar chart) from a markdown string or a JSON config via fig(). Auto-layout, zero coordinates needed. Works in browser and Node.js.
Use when user asks to draw, create, or generate diagrams, flowcharts, charts, architecture diagrams, wireframes, or visual illustrations. TRIGGER on "draw", "diagram", "flowchart", "chart", "pie chart", "bar chart", "line chart", "architecture diagram", "excalidraw", "visual", "wireframe", "comparison table", "画图", "流程图", "图表", "架构图", "示意图", "生成图", "做个图".
Use this skill whenever the user wants to extract architecture diagrams from academic papers, filter out invalid images, analyze the structure and components of diagrams, automatically match suitable color schemes, or says "提取论文架构图", "架构图分析", "从PDF中提取图表", "自动分析架构图", "architecture diagram extraction", "extract figures from pdf", "analyze architecture diagram".
Brand guidelines for Cosmonic and wasmCloud. Use this skill when creating visual content, presentations, websites, diagrams, or any materials that need to follow Cosmonic or wasmCloud brand standards. Includes an Excalidraw library for diagrams.
Beautifies and generates ASCII art diagrams in markdown files. Use when
Router skill for all MCS-MCP chart visualizations. Trigger this skill whenever any mcs-mcp analysis tool result is present in the conversation and the user asks to visualize, chart, plot, or show it. This router maps the tool that produced the result to the correct chart sub-skill. Do NOT attempt to build any chart ad-hoc — always read the sub-skill first. --- # MCS Charts Router This is the sole entry point for all MCS-MCP chart skills. When a chart request arrives, identify which analysis tool produced the data, then read and follow the matching sub-skill before writing any code. --- ## Step 1 — Identify the data source Look at the conversation for the most recent mcs-mcp tool result. Match it to one of the tools in the routing table below. --- ## Step 2 — Routing Table ``` Tool that produced the data Sub-skill path (relative to this file) ──────────────────────────────── ────────────────────────────────────────────── analyze_process_stability analyze_process_stability/s.md analyze_throughput analyze_throughput/s.md analyze_wip_stability analyze_wip_stability/s.md analyze_wip_age_stability analyze_wip_age_stability/s.md analyze_work_item_age analyze_work_item_age/s.md analyze_process_evolution analyze_process_evolution/s.md analyze_residence_time analyze_residence_time/s.md generate_cfd_data generate_cfd_data/s.md analyze_cycle_time analyze_cycle_time/s.md analyze_status_persistence analyze_status_persistence/s.md analyze_flow_debt analyze_flow_debt/s.md analyze_yield analyze_yield/s.md forecast_monte_carlo forecast_monte_carlo/s.md forecast_backtest forecast_backtest/s.md ``` Sub-folder names match the exact tool name as registered in the MCP server. --- ## Step 3 — Read the sub-skill, then build Use the `view` tool to read the matched
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:
