Dynamic Archify logo

Dynamic Archify

CommunityPopular
Unclecheng-li
dynamic-archify

Create professional architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as standalone animated HTML files with SVG graphics, flowing animation effects, a built-in dark/light theme toggle, and one-click export to PNG / JPEG / WebP / SVG / GIF / WebM. Accepts plain-language descriptions or pasted Mermaid code and lays the diagram out from scratch. Use when the user asks for system architecture diagrams, infrastructure diagrams, cloud architecture visualizations, security diagrams, network topology, technical workflows, approval flows, runbooks, CI/CD flows, process diagrams, API call sequences, request lifecycles, data pipelines, ETL/ELT maps, PII boundaries, data lineage, state machines, lifecycle diagrams, status transitions, or asks to convert/beautify a Mermaid diagram.

Overview

PublisherUnclecheng-li
RepositoryAI_Animation
Skill namedynamic-archify
Stars
1.3K
Forks
104
Bundled files
47
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 47 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Unclecheng-li on GitHub. Read the source before you install it.

Installation

Install the Dynamic Archify AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Unclecheng-li/AI_Animation.git /tmp/AI_Animation
mkdir -p .claude/skills
cp -r /tmp/AI_Animation/skills/dynamic-archify .claude/skills/dynamic-archify
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dynamic Archify in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dynamic Archify on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dynamic Archify is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Dynami-carchify Skill

Create professional technical diagrams as self-contained HTML files with inline SVG, a theme toggle, and a built-in image/SVG export menu.

Every diagram ships with a dark/light theme toggle (persists in localStorage, respects prefers-color-scheme), an export menu (copy PNG to clipboard; download PNG/JPEG/WebP rasterized natively at up to 4× resolution; download a dual-theme SVG that follows the embedding host's prefers-color-scheme — ideal for GitHub READMEs), and a CSS-variable color system that keeps both themes consistent.

Setup (one-time, renderer modes only)

The four typed renderers validate JSON against schemas via ajv. From this skill's folder:

bash
npm install

Without it the renderers still run — they print a warning and skip schema validation, keeping their own layout checks. The generated HTML never has dependencies; only the renderers do.

If you have no shell access at all (e.g. the skill was added as project knowledge), fall back to architecture mode for every request: hand-place SVG into assets/template.html following the Design System below, and run the self-review checklist before delivering.

Choosing a Diagram Type

TypeUse forHow
architectureSystem components, cloud resources, services, security boundaries, infrastructurerenderers/architecture/render-architecture.mjs + JSON (or hand-place SVG when renderers can't run)
workflowTechnical flows, approval gates, tool calls, runbooks, CI/CD, incident responserenderers/workflow/render-workflow.mjs + JSON
sequenceAPI call chains, request lifecycles, cache fallback, async traces, return pathsrenderers/sequence/render-sequence.mjs + JSON
dataflowPipelines, ETL/ELT, PII isolation, lineage, warehouse sync, consumersrenderers/dataflow/render-dataflow.mjs + JSON
lifecycleState machines, status transitions, wait states, retries, terminal statesrenderers/lifecycle/render-lifecycle.mjs + JSON

Trigger phrases: "architecture/system/cloud diagram" → architecture (unless clearly process-oriented). "workflow/flow/process/runbook/approval/CI-CD/incident" → workflow. "sequence/interaction/call chain/who calls whom" → sequence. "data flow/pipeline/ETL/lineage/PII/governance" → dataflow. "state/status/lifecycle/state machine/retry/terminal" → lifecycle.

Mermaid as an Input Dialect

When the user pastes Mermaid code, do NOT try to render or parse it mechanically — read it for structure and lay out from scratch in the matching archify mode:

MermaidArchify modeMapping
flowchart / graphworkflow (or architecture if it's a component map)subgraph → lane or region boundary; node shape {} (diamond) → decision/security node; --> labels → edge labels (use sparingly); classDef/style → nearest semantic type
sequenceDiagramsequenceparticipant → participants (pick semantic type from the name); ->> → message, -->>return variant; Note → message note; rect blocks → segments
stateDiagramlifecyclestates → states (pick start/active/waiting/success/failure from names); [*] start/end → start type / terminal lane; transition labels → event-like labels

Drop Mermaid styling; keep only the topology and meaning. You choose grouping, lane order, and what deserves emphasis — that judgment is the product.

Renderer Modes (workflow / sequence / dataflow / lifecycle)

All four modes follow the same loop:

  1. Read first: the schema (schemas/<type>.schema.json) and the complete worked example (examples/*.{workflow,sequence,dataflow,lifecycle}.json) — copy its patterns instead of guessing field shapes.
  2. Write <name>.<type>.json.
  3. Render: node renderers/<type>/render-<type>.mjs <input>.json <output>.html (paths relative to this skill's folder).
  4. If it fails, the error names the JSON path or the fix (thresholds, valid ranges, which knob to change). Fix the JSON and re-run; never edit the renderer.

Schema violations exit non-zero with path-prefixed messages like /nodes/3 (id/label: "router") must NOT have additional properties. The renderers additionally fail fast on layout problems: node/state overlap (including cross-lane), labels colliding with nodes or other labels, labels wider than their node, out-of-range columns/rows, too-short edges, and legends outside the viewBox. CJK text is measured at double width automatically.

Workflow

json
{
  "schema_version": 1,
  "diagram_type": "workflow",
  "meta": { "title": "Release Workflow", "subtitle": "PR to production", "output": "release.html" },
  "lanes": [ { "id": "dev", "label": "Developer" }, { "id": "ci", "label": "CI" } ],
  "nodes": [
    { "id": "pr", "lane": "dev", "col": 0, "type": "frontend", "label": "Open PR", "sublabel": "feature branch" },
    { "id": "build", "lane": "ci", "col": 1, "type": "backend", "label": "Build", "sublabel": "lint + test", "tag": "blocking" }
  ],
  "edges": [
    { "from": "pr", "to": "build", "label": "webhook", "variant": "emphasis", "fromSide": "bottom", "toSide": "top", "route": "drop" }
  ],
  "cards": []
}

Layout budget: 6 columns (col 0–5) at fixed x positions [88, 220, 300, 430, 500, 625] — columns 1↔2 and 3↔4 are only 70–80px apart, so default-width (92px) nodes in those adjacent columns of the same lane overlap; skip a column or shrink width. Lane content width is 640px. Omit meta.viewBox — the renderer sizes height to the lane count automatically. Edge routes: straight, drop (bend between lanes; bias 0–1 picks where), outside-right, return-left, bottom-channel, up-channel, or explicit via points. Keep adjacent-step edges unlabeled; reserve labels for cross-lane transitions, approvals, async writes, and returns.

Sequence

json
{
  "schema_version": 1,
  "diagram_type": "sequence",
  "meta": { "title": "Cache Miss Request", "subtitle": "auth and cache fallback", "output": "cache-miss.html" },
  "participants": [
    { "id": "web", "type": "frontend", "label": "Web App", "sublabel": "React UI" },
    { "id": "api", "type": "backend", "label": "API", "sublabel": "handler" }
  ],
  "segments": [ { "from": 160, "to": 320, "label": "01 / AUTH" } ],
  "messages": [
    { "from": "web", "to": "api", "y": 200, "label": "GET /data", "variant": "emphasis" },
    { "from": "api", "to": "web", "y": 290, "label": "200 JSON", "variant": "return" }
  ],
  "activations": [ { "participant": "api", "from": 190, "to": 300, "type": "backend" } ],
  "cards": []
}

Layout budget: participants sit at x = 62 + index×108, so a 920-wide viewBox fits at most 8. Message y must stay within [160, viewBox_height − 83]; messages that share horizontal space need ≥28px vertical separation; arrows need ≥60px horizontal span. segments[].from/to and activations[].from/to are y pixel coordinates, not participant ids. A taller meta.viewBox (default [920, 760]) buys more timeline room. Keep labels short: "GET /path", "verify JWT", "cache miss", "200 JSON".

Dataflow

json
{
  "schema_version": 1,
  "diagram_type": "dataflow",
  "meta": { "title": "Product Analytics", "subtitle": "events to consumers", "output": "analytics.html" },
  "stages": [ { "label": "Sources" }, { "label": "Ingest" }, { "label": "Store" } ],
  "nodes": [
    { "id": "web", "type": "frontend", "label": "Web App", "stage": 0, "row": 0, "sublabel": "clickstream" },
    { "id": "kafka", "type": "messagebus", "label": "Kafka", "stage": 1, "row": 0, "tag": "accepted events" }
  ],
  "flows": [
    { "from": "web", "to": "kafka", "label": "events", "classification": "PII touch", "variant": "emphasis" }
  ],
  "cards": []
}

Layout budget: 2–5 stages at x = 100 + stage×215; 5 rows (row 0–4) at y [128, 242, 356, 470, 584]; default node 112×58. Default viewBox [940, 720]. Flow labels are mandatory and asset-like ("clickstream", "identity map", "feature vectors"); put sensitivity in classification ("PII touch", "approved only", "non-PII"). Variants: emphasis = primary path, security = PII/policy/consent, dashed = async/batch.

Lifecycle

json
{
  "schema_version": 1,
  "diagram_type": "lifecycle",
  "meta": { "title": "Agent Run Lifecycle", "subtitle": "states and terminal outcomes", "output": "agent-run.html" },
  "lanes": [
    { "id": "main", "label": "Lifecycle phases" },
    { "id": "waiting", "label": "Interruptions" },
    { "id": "terminal", "label": "Terminal exits" }
  ],
  "states": [
    { "id": "queued", "type": "start", "label": "Queued", "lane": "main", "col": 0, "step": "01" },
    { "id": "running", "type": "active", "label": "Executing", "lane": "main", "col": 2, "step": "02" },
    { "id": "approval", "type": "waiting", "label": "Needs Approval", "lane": "waiting", "col": 0 },
    { "id": "done", "type": "success", "label": "Completed", "lane": "terminal", "col": 2 }
  ],
  "transitions": [
    { "from": "queued", "to": "running", "variant": "emphasis" },
    { "from": "running", "to": "approval", "label": "needs approval", "variant": "security", "fromSide": "bottom", "toSide": "right" },
    { "from": "running", "to": "done", "label": "success", "variant": "emphasis", "fromSide": "bottom", "toSide": "top" }
  ],
  "cards": []
}

Layout budget — lane ids are semantic and reserved: main is required and maps to the top phase band (cols 0–4); terminal maps to the bottom outcome band (cols 0–2); every other lane id shares the single middle event band (cols 0–2) — separate same-band states with different col or yOffset. Band headers render from your lane labels. Default viewBox [980, 660]. Keep transition labels event-like and sparse ("retry", "timeout", "cancel"); prefer state tags, step numbers, and summary cards over label-heavy arrows. Put terminal states in the terminal lane so endings are unambiguous.

Per-mode deep guidance

Each renderer has a README with its full design language (route presets, semantic types, story guidance): renderers/workflow/README.md, renderers/sequence/README.md, renderers/dataflow/README.md, renderers/lifecycle/README.md. Read the matching one before your first diagram of that mode in a session.

Architecture Mode

Architecture has the same read-schema-then-render loop as the other modes — prefer it. Hand-placed SVG is the fallback for when renderers can't run.

json
{
  "schema_version": 1,
  "diagram_type": "architecture",
  "meta": { "title": "Sample Web App", "subtitle": "3-tier SaaS on AWS", "output": "web-app.html" },
  "components": [
    { "id": "users", "type": "external", "label": "Users", "sublabel": "Browser", "pos": [40, 300] },
    { "id": "api", "type": "backend", "label": "API Server", "sublabel": "FastAPI :8000", "pos": [460, 300] },
    { "id": "db", "type": "database", "label": "PostgreSQL", "sublabel": ":5432", "pos": [680, 300] }
  ],
  "boundaries": [
    { "kind": "region", "label": "AWS us-west-2", "wraps": ["api", "db"] }
  ],
  "connections": [
    { "from": "users", "to": "api", "label": "HTTPS", "variant": "emphasis" },
    { "from": "api", "to": "db", "label": "SQL" }
  ],
  "cards": []
}

Render: node renderers/architecture/render-architecture.mjs <input>.json <output>.html.

The renderer does the mechanical work that used to be hand-tuned, so you only choose coordinates and meaning:

  • Free coordinatespos: [x, y] is the component's top-left; size: [w, h] defaults to [120, 60]. Unlike the typed modes there is no lane/stage grid — asymmetric placement is yours to choose. meta.viewBox is optional (auto-fitted to your components + a legend row).
  • Boundaries from wraps — list the component ids a region (dashed amber) or security-group (dashed rose) encloses; the renderer computes the box with correct 30/50 padding automatically. Never hand-arithmetic a boundary again.
  • Connections route like edges (variant, fromSide/toSide, route: straight|orthogonal-h|orthogonal-v|auto, via, labelDx/labelDy/labelAt). For a vertical labeled connection, push the label into the gap with labelDy (the validator will tell you if it lands on a box).
  • The renderer auto-emits the two-rect c-mask pattern, draws arrows before boxes (z-order), builds the legend from the component types you used, and fails fast on component overlap, off-canvas components/boundaries, unknown wraps/connection ids, label-vs-component collisions, and non-finite coordinates — the same reliability the other four modes already had.

Hand-placed fallback (no renderer available)

When Node/ajv can't run, copy assets/template.html and place SVG by hand. Study the worked diagram inside the template and examples/web-app.html for coordinate idioms, follow the Design System below, and run the self-review checklist before delivering.

The Cardinal Rule: CSS classes, not inline colors

The theme toggle works by switching CSS custom properties. Hardcoded fill="rgba(...)" or stroke="#22d3ee" will NOT update on theme change. Always use the class system:

svg
<rect x="X" y="Y" width="W" height="H" rx="6" class="c-mask"/>
<rect x="X" y="Y" width="W" height="H" rx="6" class="c-backend" stroke-width="1.5"/>
<text x="CX" y="CY" class="t-primary" font-size="11" font-weight="600" text-anchor="middle">API Server</text>
<text x="CX" y="CY+16" class="t-muted" font-size="9" text-anchor="middle">FastAPI :8000</text>

Design system

Component fills c-frontend (clients/UI), c-backend (services/APIs), c-database (stores/caches), c-cloud (managed infra), c-security (auth/secrets), c-messagebus (Kafka/queues), c-external (3rd parties); text accents t-<same> plus neutrals t-primary / t-muted / t-dim. Arrows a-default, a-emphasis (hot path), a-security (dashed), a-dashed (async) — always set stroke-width and pair marker-end="url(#arrowhead[-variant])" with the matching class. Boundaries: c-security-group (dashed rose), c-region (dashed amber), c-lane (swimlane).

Typography inherits JetBrains Mono from the SVG root. Sizes: 11–12px component names, 9px sublabels, 8px annotations, 7px tiny labels.

Hard layout rules

  • Two-rect pattern everywhere: opaque c-mask rect first, styled c-<type> rect on top — semi-transparent fills otherwise let arrows bleed through.
  • Arrows before components in document order (SVG paints in order; arrows must sit behind boxes).
  • Vertical stacking: ≥40px gap between components; inline connectors (message buses, 20px tall) live inside the gap, never overlapping boxes.
  • Boundary padding: boundary y = inner y − 30, boundary height = inner height + 50, label baseline 18px below the boundary top.
  • Legend placement: outside ALL boundary boxes, ≥20px below the lowest one; grow the viewBox if needed.

Self-review checklist (run before delivering)

  1. grep -E 'fill="(#|rgb)|stroke="(#|rgb)' out.html inside the SVG returns nothing except the template's own defs (Cardinal Rule).
  2. Every c-<type> rect has an identical-geometry c-mask rect immediately before it.
  3. All <line>/<path> arrows appear before all component rects in document order.

Export Options

Archify supports multiple export formats for both static and animated diagrams:

Static Exports

  • PNG — High-resolution raster image (4x source resolution)
  • JPEG — Compressed raster image with background
  • WebP — Modern compressed format with transparency
  • SVG — Vector format with auto-theme support
  • Copy to Clipboard — Quick PNG copy for pasting

Animated Exports (for diagrams with flowing animations)

  • GIF — Animated GIF capturing flowing animations

    • Uses gif.js library for client-side encoding
    • User-configurable settings dialog appears before export:
      • Resolution: 1x / 2x (default) / 3x / 4x
      • Frame rate: 10 / 15 / 20 (default) / 24 / 30 / 60 fps
      • Duration: 2 / 3 (default) / 5 / 8 seconds
    • Shows live frame count preview (e.g. "60 frames · 20 fps · 3s")
    • File size: typically 1-10 MB depending on settings and complexity
  • WebM — High-quality video format

    • Uses MediaRecorder API for native video capture
    • Same user-configurable settings dialog as GIF
    • Better quality than GIF, smaller file size
    • Supported in Chrome, Firefox, Edge

Export Tips

For best GIF quality:

  1. Use dark theme (better contrast for animations)
  2. Keep diagram size moderate (large diagrams = larger GIF files)
  3. Wait for "GIF exported successfully!" toast message

For WebM video:

  1. Works best in Chrome and Firefox
  2. Safari has limited MediaRecorder support
  3. Use VLC or browser to play WebM files

File size optimization:

  • GIF: 1-5 MB for typical diagrams
  • WebM: 0.5-2 MB for same content
  • For sharing: WebM is recommended (better quality/size ratio)

Flowing Animation Effects

All diagrams now include automatic flowing animation effects on connection paths. This feature is built into the renderers and template — no additional configuration needed.

Animation Behavior

CSS Animations (stroke-dasharray flow):

  • a-emphasis: Fast flow (0.8s cycle) with pulse effect, 3px glow
  • a-default: Medium flow (1.2s cycle), 2px glow
  • a-dashed: Steady flow (1s cycle)
  • a-security: Steady flow (1s cycle)

SVG Animations (moving dots):

  • Each connection path has an animated dot that flows along the path
  • Dot properties vary by variant:
    • emphasis: 3px radius, high opacity (0.9), 2-3.5s duration
    • default: 2.5px radius, medium opacity (0.8), 2.5-3.7s duration
    • dashed: 2px radius, lower opacity (0.7), 2.2-3.4s duration
    • security: 2px radius, lower opacity (0.7), 2.5-3.5s duration

Flow Direction Rule

Critical constraint: Flowing animations must flow from the source (no arrow) to the destination (arrow).

The renderers automatically handle this:

  • All paths use marker-end for arrowheads
  • Animation direction follows the path from start to end
  • Dots travel from the component without arrow toward the component with arrow

Visual Effects

  1. Stroke dash animation: Creates the illusion of flowing dashes along the path
  2. Moving dots: Animated circles travel along the path trajectory
  3. Glow effects: Emphasis paths have enhanced drop-shadow filters
  4. Pulse effects: Emphasis paths have subtle opacity pulsing

Customization

The flowing effects are automatically applied based on the variant property of connections/edges/flows/transitions:

json
{
  "from": "source",
  "to": "target",
  "variant": "emphasis",  // Fast flow with glow
  "label": "data flow"
}

Available variants:

  • emphasis — Primary data flow, fastest animation, strongest glow
  • default — Standard connections, medium animation
  • dashed — Async/batch operations, steady flow
  • security — Security/policy paths, steady flow

Technical Implementation

The flowing effects are implemented in two layers:

  1. CSS layer (assets/template.html):

    • @keyframes flowDash — Animates stroke-dashoffset for flowing dashes
    • @keyframes flowPulse — Animates opacity for emphasis pulse
    • Applied via .a-emphasis, .a-default, .a-dashed, .a-security classes
  2. SVG layer (renderers):

    • <animateMotion> elements on <circle> dots
    • Path data from connection routing
    • Duration varies by variant and index for visual variety

Backward Compatibility

  • Existing diagrams without animations will continue to work
  • Animations are purely additive — no breaking changes
  • All theme toggle and export features remain fully functional
  1. Compute max(y + height) over all SVG elements: viewBox height must exceed it by ≥20px; same for x/width.
  2. Legend y is below every boundary's y + height.
  3. The .toolbar, <script> blocks, and :root / [data-theme] CSS are untouched — they ARE the theme toggle and export menu.

Output

A single self-contained .html: embedded CSS (Google Fonts loads async and degrades to system monospace offline), inline SVG, embedded gif.js library + worker for animated GIF export, ~60KB embedded JS for theme + export + animation. It renders directly in any modern browser. Raster exports render natively at up to 4× the viewBox (large diagrams step down to 3×/2× to stay under canvas limits); the SVG download is dual-theme self-contained and follows the host's prefers-color-scheme (manual override via svg[data-theme="..."]). Animated GIF/WebM exports capture the flowing animations with user-configurable resolution, frame rate, and duration.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Dynamic Archify AI skill do?

Create professional architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as standalone animated HTML files with SVG graphics, flowing animation effects, a built-in dark/light theme toggle, and one-click export to PNG / JPEG / WebP / SVG / GIF / WebM. Accepts plain-language descriptions or pasted Mermaid code and lays the diagram out from scratch. Use when the user asks for system architecture diagrams, infrastructure diagrams, cloud architecture visualizations, security diagrams, network topology, technical workflows, approval flows, runbooks, CI/CD flows, process diagr...

Why use Dynamic Archify on TypingMind?

Because you install it once and use it with any model. Dynamic Archify is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dynamic Archify in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Unclecheng-li/AI_Animation/tree/master/skills/dynamic-archify. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Dynamic Archify?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dynamic Archify?

As many as you like. As long as a model supports skills, you can use Dynamic Archify with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dynamic Archify AI skill free?

Yes. It is published on GitHub by Unclecheng-li under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇