New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Arena

by sreichholf in sreichholf/dreamDroid

Spawn parallel candidate implementations for the same task, cross-judge, and graft the best parts into the winning base.

GPL-3.0Auto-check passed

Install Arena

skills CLI
$ npx skills add sreichholf/dreamDroid --skill arena -a claude-code

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

GitHub CLI
$ gh skill install sreichholf/dreamDroid 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/sreichholf/dreamDroid.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/arena .claude/skills/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
arena
GitHub stars
116
Token cost
~273 tokens
SKILL.md length
133 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
GPL-3.0

At a glance

Spawn parallel candidate implementations for the same task, cross-judge, and graft the best parts into the winning base.

  • Works in 6 steps: Frame: Define the artifact contract, 3-6… → Fan out: Run parallel candidate attempts… → Cross-judge: Score each candidate… → …
  • Exploring competing designs
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Critical artifacts

What it does

Arena is an agent skill from sreichholf/dreamDroid. Spawn parallel candidate implementations for the same task, cross-judge, and graft the best parts into the winning base. Use when exploring competing designs or critical artifacts.

Its SKILL.md is about 270 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: DreamDroid is an open-source enigma2 client for android based devices. The licence is GPL-3.0.

When your agent uses it

  • Exploring competing designs
  • Critical artifacts

Example prompts

  • “/arena”

Workflow steps

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

  1. Frame: Define the artifact contract, 3-6 concrete rubric criteria, and isolated candidate output paths.
  2. Fan out: Run parallel candidate attempts on isolated workers (via delegate when supported, or labeled sequential passes). Require a…
  3. Cross-judge: Score each candidate against the rubric criteria, compare trade-offs, and recommend the strongest base.
  4. Pick a base: Select the implementation that is cleanest, easiest to maintain, and safest under domain invariants.
  5. Graft: Port the best independent ideas or edge-case handling from losing candidates into the base by hand.
  6. Verify: Validate the synthesized result against the full test and verification suite.

What it can do on your machine

Read from SKILL.md and the folder at commit 36f622a. 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.

    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

Arena loads about 273 tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 133 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~273

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 sreichholf/dreamDroid at commit 36f622a, republished under its GPL-3.0 licence (© sreichholf). 133 words, ~273 tokens.

Download SKILL.mdSave it as .claude/skills/arena/SKILL.md (or your agent's skills folder).
name
arena
description
Spawn parallel candidate implementations for the same task, cross-judge, and graft the best parts into the winning base. Use when exploring competing designs or critical artifacts.

Arena

Fan out N parallel attempts at the same task, score them against concrete criteria, pick a base, and graft the best ideas from the others.

  1. Frame: Define the artifact contract, 3-6 concrete rubric criteria, and isolated candidate output paths.
  2. Fan out: Run parallel candidate attempts on isolated workers (via delegate when supported, or labeled sequential passes). Require a concrete artifact and short rationale from each.
  3. Cross-judge: Score each candidate against the rubric criteria, compare trade-offs, and recommend the strongest base.
  4. Pick a base: Select the implementation that is cleanest, easiest to maintain, and safest under domain invariants.
  5. Graft: Port the best independent ideas or edge-case handling from losing candidates into the base by hand.
  6. Verify: Validate the synthesized result against the full test and verification suite.

© sreichholf, GPL-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 .agents/skills/arena of sreichholf/dreamDroid.

Open the folder on GitHubat commit 36f622a

Compare with similar skills

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.

Arena compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Arena this skillsreichholf/dreamDroid116—~273Automated safety check: PassGPL-3.0
Arena Parallel Candidatescursor/plugins10k8 repos~1.2kAutomated safety check: PassNone
Implementsickn33/agentic-awesome-skills47k5 repos~306Automated safety check: PassMIT
Spawnalirezarezvani/claude-skills28k—~829Automated safety check: PassMIT
Implementcodewhale-hq/Codewhale41k—~190Automated safety check: PassMIT
Nv Implementnovuhq/novu40k—~1.7kAutomated safety check: PassCustom licence

Similar skills

  • Arena Parallel Candidates

    cursor/plugins

    Official

    Runs several parallel attempts at the same task, picks the strongest as a base, grafts the best ideas from the others into it, then verifies the merged result.

    10k GitHub starsUsed in 8 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Implement

    sickn33/agentic-awesome-skills

    Implement a piece of work based on a PRD or set of issues. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 5 repos~306 tokens
    Product & Project ManagementAuto-check passed

  • Spawn

    alirezarezvani/claude-skills

    Launch N parallel subagents in isolated git worktrees to compete on the session task.

    28k GitHub stars~829 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Implement

    codewhale-hq/Codewhale

    Carry an authorized, defined request or approved plan through scoped edits and proportionate verification.

    41k GitHub stars~190 tokensUpdated today
    Auto-check passed

  • Nv Implement

    novuhq/novu

    Implement planned work by fanning out parallel subagents on isolated worktrees — TDD at pre-agreed seams, per-slice nv-park-and-review, merge back, full suite once at the end.

    40k GitHub stars~1.7k tokensUpdated today
    Testing & QAAuto-check passed

  • Parallels Discord Roundtrip

    openclaw/openclaw

    Run macOS Parallels smoke with Discord send, host verification, host reply, and guest readback proof.

    392k GitHub stars~788 tokensUpdated today
    Auto-check passed

More from sreichholf/dreamDroid

All 12 skills in this repo

  • Verify Dreamdroid

    sreichholf/dreamDroid

    Prove dreamDroid phone UI. An agent skill from sreichholf/dreamDroid.

    116 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Poteto Mode

    sreichholf/dreamDroid

    Lauren Tan-inspired rigorous engineering mode for concise communication, deliberate decomposition, simple code, independent review when available, and runtime verification.

    116 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Principle Never Block On The Human

    sreichholf/dreamDroid

    Run the experiment or make the reversible best-effort change, then show the result.

    116 GitHub stars~235 tokensUpdated today
    Auto-check passed

  • Architect

    sreichholf/dreamDroid

    Settle data shapes, ownership, boundaries, and interfaces before code crosses a function/module boundary.

    116 GitHub stars~224 tokensUpdated today
    Auto-check passed

  • Automate Me

    sreichholf/dreamDroid

    Create a personal mode skill from recurring workflow patterns in available history.

    116 GitHub stars~208 tokensUpdated today
    Auto-check passed

  • Create Verification Skill

    sreichholf/dreamDroid

    Generate a project-local verification skill that drives the real app and captures evidence.

    116 GitHub stars~205 tokensUpdated today
    Auto-check passed

Questions about Arena

What does Arena do?

Spawn parallel candidate implementations for the same task, cross-judge, and graft the best parts into the winning base. Arena is an agent skill from sreichholf/dreamDroid. Spawn parallel candidate implementations for the same task, cross-judge, and graft the best parts into the winning base.

When should I use Arena?

Arena fits situations like: exploring competing designs; critical artifacts.

How do I install Arena in Claude Code?

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

How do I install Arena in Codex?

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

Can I use 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 sreichholf/dreamDroid --skill 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/arena, .gemini/skills/arena, .github/skills/arena and .opencode/skills/arena in your project.

What does Arena need to run?

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

Does 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 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 Arena use?

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

How many tokens does Arena use?

About 273 tokens (SKILL.md is roughly 1.1k 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 Arena?

Skills that share tags, products or a category with Arena: Arena Parallel Candidates (cursor/plugins, 10k stars), Implement (sickn33/agentic-awesome-skills, 47k stars), Spawn (alirezarezvani/claude-skills, 28k stars) and Implement (codewhale-hq/Codewhale, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Arena?

sreichholf (a GitHub user) maintains it in sreichholf/dreamDroid, which has 116 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 9, 2026.

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