Agent skill

Design Arena

by archestra-ai in archestra-ai/archestra

Run a design arena: a coordinator fans out N subagents (default 7) that each prototype one UI section through a different lens, switchable in-app via a temporary prototype selector, refined in rounds.

Custom licenceAuto-check passedAgent Workflows

Install Design Arena

skills CLI
$ npx skills add archestra-ai/archestra --skill design-arena -a claude-code

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

GitHub CLI
$ gh skill install archestra-ai/archestra design-arena --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/archestra-ai/archestra.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/design-arena .claude/skills/design-arena && 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
design-arena
GitHub stars
4.4k
Token cost
~1.1k tokens
SKILL.md length
466 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
Custom licence

At a glance

Run a design arena: a coordinator fans out N subagents (default 7) that each prototype one UI section through a different lens, switchable in-app via a temporary prototype selector, refined in rounds.

  • Works in 6 steps: Mount the selector with "Current" =… → Pick N lenses: genuinely different takes… → Fan out N subagents in parallel, one… → …
  • Tasks that involve Subagents
  • SKILL.md covers Inputs, The prototype selector (same…, Commit guard (Biome) and Round loop, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Design Arena is an agent skill from archestra-ai/archestra. Run a design arena: a coordinator fans out N subagents (default 7) that each prototype one UI section through a different lens, switchable in-app via a temporary prototype selector, refined in rounds.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Subagents. The repository describes itself as: Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator.

When your agent uses it

  • Tasks that involve Subagents

Example prompts

  • “/design-arena”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Mount the selector with "Current" = today's section.
  2. Pick N lenses: genuinely different takes (layout, density, metaphor, interaction, scale). Post them as a numbered one-liner list.
  3. Fan out N subagents in parallel, one file each. Brief: requirements, its lens, accumulated feedback constraints, the taste skill, its…
  4. Check each variant renders; re-spawn broken ones.
  5. Present the URL and numbered list; ask which wins and what to change.
  6. Refine: the winner (or a blend) becomes the baseline. Restate feedback as concrete constraints carried into every future brief (ask first…

What it can do on your machine

Read from SKILL.md and the folder at commit df802e7. 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 typescript and grit).

    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

Design Arena loads about 1.1k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 466 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 466 words (~1,070 tokens).

“Hammer out many design directions for ONE section of a real app page and find what looks good. You (the coordinator) mount a temporary prototype selector in that section, fan out N subagents that each build one variant through a…”

— opening of SKILL.md by archestra-ai, Custom licence
name
design-arena

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/design-arena of archestra-ai/archestra.

Open the folder on GitHubat commit df802e7

Compare with similar skills

Design Arena 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.

Design Arena compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Design Arena this skillarchestra-ai/archestra4.4k—~1.1kAutomated safety check: PassCustom licence
O2 Review Loopopenobserve/openobserve22k—~3.7kAutomated safety check: PassAGPL-3.0
V2 Perf Iterationmirage-project/mirage2.5k—~4kAutomated safety check: PassApache-2.0
Clone App Pat Proper-simmons/clone-app-pat-pro-public259—~1.9kAutomated safety check: NotesNone
Kimi Code DelegationCherryHQ/cherry-studio53k—~504Automated safety check: PassAGPL-3.0
Team Modeoil-oil/codex-team-mode217—~1.3kAutomated safety check: PassMIT

Similar skills

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • V2 Perf Iteration

    mirage-project/mirage

    Runtime-V2 performance-iteration workflow. An agent skill from mirage-project/mirage.

    2.5k GitHub stars~4k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Clone App Pat Pro

    per-simmons/clone-app-pat-pro-public

    Clones any web app pixel-for-pixel from a URL. An agent skill from per-simmons/clone-app-pat-pro-public.

    259 GitHub stars~1.9k tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check: notes
  • Kimi Code Delegation

    CherryHQ/cherry-studio

    Delegates one bounded repository task to Kimi Code in non-interactive prompt mode and reads back the final result from its JSON event stream.

    53k GitHub stars~504 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Team Mode

    oil-oil/codex-team-mode

    A skill your agent uses when a task may benefit from a bounded subagent for implementation, large-codebase discovery at task start, independent review, requested or pre-commit code simplification…

    217 GitHub stars~1.3k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed
  • Review

    getsentry/sentry-react-native

    Official

    Three-axis review of the branch diff — Standards (this repo's documented standards + public API/bridge surface), Spec (the originating Linear/GitHub issue or PR), and Correctness (runtime bugs + the…

    1.8k GitHub stars~1.9k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

More from archestra-ai/archestra

All 23 skills in this repo
  • Migrate To Archestra

    archestra-ai/archestra

    Migrate an existing agentic PoC/pilot (Claude Code project files, MCP configs, hooks, local tools, openclaw config, or similar hand-rolled setup artifacts) into an Archestra instance.

    4.4k GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Archestra Dev Testing

    archestra-ai/archestra

    A skill your agent uses for test selection and quality across backend, frontend, and e2e; load its backend reference for Vitest projects, mocking, DB fixtures, and performance.

    4.4k GitHub stars~3.2k tokensUpdated today
    Auto-check passed
  • Archestra Dev Backend

    archestra-ai/archestra

    A skill your agent uses when adding or changing Archestra backend routes, models, services, API request/response schemas, endpoint permissions, or OpenAPI/codegen for the generated API client.

    4.4k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Archestra Dev E2E

    archestra-ai/archestra

    A skill your agent uses when writing, debugging, or running Archestra Playwright e2e tests, API/UI fixtures, WireMock-backed tests, local/CI e2e setup, or test selectors.

    4.4k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Archestra Dev Frontend

    archestra-ai/archestra

    A skill your agent uses when modifying Archestra frontend Next.js/React code, UI components, forms, TanStack Query hooks, generated API client usage, frontend copy, or documentation links.

    4.4k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Archestra Dev LLM Providers

    archestra-ai/archestra

    A skill your agent uses when adding an LLM provider, changing proxy adapters or provider routes, fixing streaming/tool-call translation bugs, editing model fetchers or model handling, or touching…

    4.4k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Questions about Design Arena

What does Design Arena do?

Run a design arena: a coordinator fans out N subagents (default 7) that each prototype one UI section through a different lens, switchable in-app via a temporary prototype selector, refined in rounds. Design Arena is an agent skill from archestra-ai/archestra. Run a design arena: a coordinator fans out N subagents (default 7) that each prototype one UI section through a different lens, switchable in-app via a temporary prototype selector, refined in rounds.

When should I use Design Arena?

Design Arena fits situations like: tasks that involve Subagents.

How do I install Design Arena in Claude Code?

Run `npx skills add archestra-ai/archestra --skill design-arena -a claude-code`. Or copy the skill folder (.agents/skills/design-arena in archestra-ai/archestra) into .claude/skills/design-arena in your project. Claude Code loads it when a task matches its description.

How do I install Design Arena in Codex?

Run `npx skills add archestra-ai/archestra --skill design-arena -a codex`. Or copy the skill folder (.agents/skills/design-arena in archestra-ai/archestra) into .agents/skills/design-arena in your project. Codex loads it when a task matches its description.

Can I use Design Arena 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 archestra-ai/archestra --skill design-arena -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/design-arena, .gemini/skills/design-arena, .github/skills/design-arena and .opencode/skills/design-arena in your project.

What does Design Arena need to run?

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

Does Design Arena 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 Design Arena 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 Design Arena use?

Design Arena has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Design Arena use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 Design Arena?

Skills that share tags, products or a category with Design Arena: O2 Review Loop (openobserve/openobserve, 22k stars), V2 Perf Iteration (mirage-project/mirage, 2.5k stars), Clone App Pat Pro (per-simmons/clone-app-pat-pro-public, 259 stars) and Kimi Code Delegation (CherryHQ/cherry-studio, 53k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Design Arena?

archestra-ai (a GitHub organization) maintains it in archestra-ai/archestra, which has 4,368 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 10, 2026.

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