Agent skill

Ade Mosaic

by arul28 in arul28/ADE

A skill your agent uses when you want to ask the user for structured input (choices, toggles, numbers, short text, approvals) inside an ADE chat.

AGPL-3.0Auto-check passed

Install Ade Mosaic

skills CLI
$ npx skills add arul28/ADE --skill ade-mosaic -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install arul28/ADE ade-mosaic --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/arul28/ADE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/desktop/resources/agent-skills/ade-mosaic .claude/skills/ade-mosaic && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ade-mosaic
GitHub stars
114
Token cost
~734 tokens
SKILL.md length
223 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
AGPL-3.0

At a glance

A skill your agent uses when you want to ask the user for structured input (choices, toggles, numbers, short text, approvals) inside an ADE chat.

  • You want to ask the user for structured input (choices
  • SKILL.md covers Schema (v1), Example and Guidance
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Approvals) inside an ADE chat

What it does

Ade Mosaic is an agent skill from arul28/ADE. Use this skill when you want to ask the user for structured input (choices, toggles, numbers, short text, approvals) inside an ADE chat. Emit a fenced mosaic code block and ADE renders it as a native interactive card; the user's answers come back as your next user message.

Its SKILL.md is about 730 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is AGPL-3.0.

When your agent uses it

  • You want to ask the user for structured input (choices
  • Approvals) inside an ADE chat

Example prompts

  • “/ade-mosaic”

What it can do on your machine

Read from SKILL.md and the folder at commit 36aab9e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are mosaic).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ade Mosaic loads about 734 tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 223 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~734

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from arul28/ADE at commit 36aab9e, republished under its AGPL-3.0 licence (© arul28). 223 words, ~734 tokens.

Download SKILL.mdSave it as .claude/skills/ade-mosaic/SKILL.md (or your agent's skills folder).
name
ade-mosaic
description
Use this skill when you want to ask the user for structured input (choices, toggles, numbers, short text, approvals) inside an ADE chat. Emit a fenced mosaic code block and ADE renders it as a native interactive card; the user's answers come back as your next user message.

ADE Mosaic cards

Emit a fenced code block with language mosaic containing strict JSON. ADE desktop renders it as an interactive card in the transcript. When the user submits, their selections arrive as the next user message: readable lines plus a json fence with {"mosaic":1,"values":{...}} keyed by element id.

The card is data only — no expressions, no code, no host actions. If the JSON is malformed or uses unknown element types or versions, ADE shows the raw fence instead, so validate your JSON.

Terminal (TUI) chats show a one-line summary; iOS shows the raw fence. Ask plain-text questions when the user is likely not on desktop.

Schema (v1)

Top level: {"v": 1, "title"?, "submitLabel"?, "elements": [...]} — 1 to 24 elements. Interactive elements need a unique id.

ElementShape
Text{"type":"text","text":"..."}
Single select{"type":"select","id":"env","label"?,"options":[{"value":"prod","label"?}],"value"?}
Multi select{"type":"multiselect","id":"features","label"?,"options":[...],"values"?}
Number / slider{"type":"number","id":"n","label"?,"min"?,"max"?,"step"?,"value"?} (renders a slider when both min and max are set)
Short text{"type":"input","id":"name","label"?,"placeholder"?,"value"?,"maxLength"?}
Approve / deny{"type":"approval","id":"go","label"?,"approveLabel"?,"denyLabel"?}
Key-value table{"type":"table","rows":[{"key":"...","value":"..."}]} (display only)

Limits: 40 options per select, 50 table rows, labels ≤ 200 chars, values ≤ 1000 chars.

Example

mosaic
{
  "v": 1,
  "title": "Release checklist",
  "elements": [
    {"type": "text", "text": "v1.3.0 is tagged and CI is green."},
    {"type": "table", "rows": [
      {"key": "Commits", "value": "18"},
      {"key": "Risk", "value": "low"}
    ]},
    {"type": "select", "id": "channel", "label": "Channel",
     "options": [{"value": "beta"}, {"value": "stable"}], "value": "beta"},
    {"type": "multiselect", "id": "targets", "label": "Targets",
     "options": [{"value": "mac"}, {"value": "ios"}]},
    {"type": "number", "id": "rollout", "label": "Rollout %", "min": 5, "max": 100, "step": 5, "value": 25},
    {"type": "approval", "id": "ship", "label": "Publish the release?"}
  ],
  "submitLabel": "Send"
}

Guidance

  • text and table are display-only, so a card needs at least one interactive element to be submittable; use the display rows for the context the user needs to decide.
  • Do NOT use a mosaic card for plan approval or permission prompts — ADE has dedicated native surfaces for those.

© arul28, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in apps/desktop/resources/agent-skills/ade-mosaic of arul28/ADE.

Open the folder on GitHubat commit 36aab9e

Compare with similar skills

Ade Mosaic next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ade Mosaic compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ade Mosaic this skillarul28/ADE114—~734Automated safety check: PassAGPL-3.0
Adelanding-ai/ade-cli2.4k—~2.4kAutomated safety check: PassApache-2.0
Nexrad Mosaic Constructionsickn33/agentic-awesome-skills47k1 repos~3.1kAutomated safety check: PassMIT
React Mosaicnomcopter/react-mosaic4.8k—~2.5kAutomated safety check: PassCustom licence
Nexrad Mosaic Accesssickn33/agentic-awesome-skills47k1 repos~3.2kAutomated safety check: PassMIT
Mosaicadaptyvbio/protein-design-skills1641 repos~1.7kAutomated safety check: PassMIT

Similar skills

  • Ade

    landing-ai/ade-cli

    Parse documents and extract schema-shaped data with the ADE (Agentic Document Extraction) v2 APIs through the ade CLI.

    2.4k GitHub stars~2.4k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Nexrad Mosaic Construction

    sickn33/agentic-awesome-skills

    Construct a quality-aware NEXRAD multi-radar mosaic from aligned single-site products with explicit coverage, beam geometry, quality weighting, overlap resolution, and provenance.

    47k GitHub starsUsed in 1 repo~3.1k tokens
    Auto-check passed
  • React Mosaic

    nomcopter/react-mosaic

    Build tiling window manager layouts in React with react-mosaic-component (v7) - resizable, drag-and-drop rearrangeable panels, splits and tab groups.

    4.8k GitHub stars~2.5k tokensUpdated 12 days ago
    DevelopmentAuto-check passed
  • Nexrad Mosaic Access

    sickn33/agentic-awesome-skills

    Access official NOAA/NCEP MRMS radar and multisensor composites for a region and time; validate product, grid, domain, quality, timestamp, and provenance.

    47k GitHub starsUsed in 1 repo~3.2k tokens
    Auto-check passed
  • Mosaic

    adaptyvbio/protein-design-skills

    Multi-objective, gradient-based protein binder design with Mosaic.

    164 GitHub starsUsed in 1 repo~1.7k tokens
    Research & ScienceAuto-check passed
  • Render Mosaic Grid Reveal

    gooseworks-ai/goose-skills

    Render a 'mosaic-grid-reveal' video from a config — a real-DOM FULL-BLEED N×N mosaic of real product tiles that pops in one tile at a time (scatter order, ease-out-back overshoot), the grid clears…

    1.2k GitHub stars~1.1k tokensUpdated yesterday
    Media & CreativeAuto-check passed

More from arul28/ADE

All 28 skills in this repo
  • Ade App Control

    arul28/ADE

    A skill your agent uses when you need to run or drive a local Electron/desktop app and capture what it does — launch it or attach to a running renderer, read its logs or answer its terminal prompts…

    114 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Iteratively optimize an ADE tab's CPU/memory/IPC/render performance.

    114 GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • Ade Browser

    arul28/ADE

    A skill your agent uses for any browser behavior at all — opening a URL, checking a localhost page, clicking or filling a form, logging in, screenshotting, inspecting the DOM, or verifying a page…

    114 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Ade Deeplinks

    arul28/ADE

    A skill your agent uses when an agent needs to mint, share, or open ADE deeplinks (lane, work session, file, commit, artifact, branch, PR, Linear issue) so users — or the agent itself — can jump…

    114 GitHub stars~3.2k tokensUpdated today
    Auto-check passed
  • Ade Harnesses

    arul28/ADE

    A skill your agent uses when you need to run a chat, a CLI session, or a subagent on a specific setup — any model you pay for inside any harness (e.g.

    114 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Ade Lanes Git

    arul28/ADE

    A skill your agent uses when creating, inspecting, syncing, committing, pushing, archiving, or rebasing ADE lanes and lane worktrees through ade lanes and ade git.

    114 GitHub stars~594 tokensUpdated today
    Auto-check passed

Questions about Ade Mosaic

What does Ade Mosaic do?

A skill your agent uses when you want to ask the user for structured input (choices, toggles, numbers, short text, approvals) inside an ADE chat. Ade Mosaic is an agent skill from arul28/ADE. Use this skill when you want to ask the user for structured input (choices, toggles, numbers, short text, approvals) inside an ADE chat.

When should I use Ade Mosaic?

Ade Mosaic fits situations like: you want to ask the user for structured input (choices; approvals) inside an ADE chat.

How do I install Ade Mosaic in Claude Code?

Run `npx skills add arul28/ADE --skill ade-mosaic -a claude-code`. Or copy the skill folder (apps/desktop/resources/agent-skills/ade-mosaic in arul28/ADE) into .claude/skills/ade-mosaic in your project. Claude Code loads it when a task matches its description.

How do I install Ade Mosaic in Codex?

Run `npx skills add arul28/ADE --skill ade-mosaic -a codex`. Or copy the skill folder (apps/desktop/resources/agent-skills/ade-mosaic in arul28/ADE) into .agents/skills/ade-mosaic in your project. Codex loads it when a task matches its description.

Can I use Ade Mosaic in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add arul28/ADE --skill ade-mosaic -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ade-mosaic, .gemini/skills/ade-mosaic, .github/skills/ade-mosaic and .opencode/skills/ade-mosaic in your project.

What does Ade Mosaic need to run?

SKILL.md names no scripts, command-line tools or credentials: Ade Mosaic is instructions for the agent only.

Does Ade Mosaic access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ade Mosaic safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ade Mosaic use?

Ade Mosaic is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ade Mosaic use?

About 734 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ade Mosaic?

Skills that share tags, products or a category with Ade Mosaic: Ade (landing-ai/ade-cli, 2.4k stars), Nexrad Mosaic Construction (sickn33/agentic-awesome-skills, 47k stars), React Mosaic (nomcopter/react-mosaic, 4.8k stars) and Nexrad Mosaic Access (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ade Mosaic?

arul28 (a GitHub user) maintains it in arul28/ADE, which has 114 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 10, 2026.

Source: arul28/ADE on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.