Developing PDF Viewer
TriliumNext/Trilium
A skill your agent uses when changing Trilium's built-in PDF viewer — anything under packages/pdfjs-viewer (the code injected into Mozilla's PDF.js viewer: bootstrap.ts, annotations.ts, pages.ts…
Design and verify Jev Arenas in OpenHarness's live viewer, where Jev plays the world you build.
MITAuto-check passed
Install Jev Arena
$ npx skills add autonomous-ai/openharness --skill jev-arena -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install autonomous-ai/openharness jev-arena --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/jev-arena/skills/arena .claude/skills/jev-arena && rm -rf skills-srcUse ~/.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/
Install the "jev-arena" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/jev-arena/skills/arena into .claude/skills/jev-arena/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-arena", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/autonomous-ai/openharness/tree/main/store/agents/jev-arena/skills/arenaType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add autonomous-ai/openharness --skill jev-arena -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install autonomous-ai/openharness jev-arena --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/store/agents/jev-arena/skills/arena .agents/skills/jev-arena && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "jev-arena" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/jev-arena/skills/arena into .agents/skills/jev-arena/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-arena", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autonomous-ai/openharness --skill jev-arena -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install autonomous-ai/openharness jev-arena --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/store/agents/jev-arena/skills/arena .cursor/skills/jev-arena && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "jev-arena" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/jev-arena/skills/arena into .cursor/skills/jev-arena/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-arena", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/autonomous-ai/openharness.git --path store/agents/jev-arena/skills/arena--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add autonomous-ai/openharness --skill jev-arena -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install autonomous-ai/openharness jev-arena --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/store/agents/jev-arena/skills/arena .gemini/skills/jev-arena && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "jev-arena" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/jev-arena/skills/arena into .gemini/skills/jev-arena/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-arena", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install autonomous-ai/openharness jev-arenaInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add autonomous-ai/openharness --skill jev-arena -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/store/agents/jev-arena/skills/arena .github/skills/jev-arena && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "jev-arena" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/jev-arena/skills/arena into .github/skills/jev-arena/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-arena", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autonomous-ai/openharness --skill jev-arena -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install autonomous-ai/openharness jev-arena --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/store/agents/jev-arena/skills/arena .opencode/skills/jev-arena && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "jev-arena" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/jev-arena/skills/arena into .opencode/skills/jev-arena/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-arena", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
jev-arena- GitHub stars
- 1.2k
- Token cost
- ~511 tokens
- SKILL.md length
- 213 words
- Files
- 1
- Skills in repo
- 100
- Repo updated
- First seen
- Licence
- MIT
At a glance
Design and verify Jev Arenas in OpenHarness's live viewer, where Jev plays the world you build.
- Works in 3 steps: Update arena.json. The viewer watches it… → node "$JEV_DSH/toolchain/check.mjs"… → Watch Jev play. When the layout changes,…
- SKILL.md covers The loop, Reading Jev, Verifying a world and Driving Jev yourself
- Calls node; needs TYPESAFE_API_KEY
What it does
Jev Arena is an agent skill from autonomous-ai/openharness. Design and verify Jev Arenas in OpenHarness's live viewer, where Jev plays the world you build.
Its SKILL.md is about 510 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across… The licence is MIT.
Example prompts
- “/jev-arena”
Requirements
- A credential in TYPESAFE_API_KEY
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Update arena.json. The viewer watches it and adapts live — no restart, no second server.
- node "$JEV_DSH/toolchain/check.mjs" verifies the workspace's arena.json is a valid, playable
- Watch Jev play. When the layout changes, that's the moment to look: does Jev's confidence dip and
What it can do on your machine
Read from SKILL.md and the folder at commit cc4983e. 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
Shell commands in SKILL.md call:
node
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 these keys or tokens, usually read from environment variables:
TYPESAFE_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Jev Arena loads about 511 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 213 words of instructions outside code blocks.
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 autonomous-ai/openharness at commit cc4983e, republished under its MIT licence (© autonomous-ai). 213 words, ~511 tokens.
Download SKILL.mdSave it as
.claude/skills/jev-arena/SKILL.md (or your agent's skills folder).- name
- jev-arena
- description
- Design and verify Jev Arenas in OpenHarness's live viewer, where Jev plays the world you build.
Jev Arena design
Jev Arena shows a live grid and a "Jev's brain" panel: Jev (TypeSafe's System One model) chooses a
move every arena.speed ms, and the viewer streams the probability distribution and confidence for
up / down / left / right / wait.
The loop
- Update
arena.json. The viewer watches it and adapts live — no restart, no second server. node "$JEV_DSH/toolchain/check.mjs"verifies the workspace'sarena.jsonis a valid, playable world, and reports the current verdict / status. Run it before you call a world done.- Watch Jev play. When the layout changes, that's the moment to look: does Jev's confidence dip and recover? Is the route interesting?
Reading Jev
The viewer shows, per action, a probability bar and the chosen action highlighted. confidence is
a 0..1 concentration of the distribution. A confident Jev puts most mass on one move; a confused Jev
spreads it. Good arenas produce both states.
Verifying a world
node "$JEV_DSH/toolchain/check.mjs" returns non-zero when arena.json is invalid (missing fields,
out-of-bounds, goal covered by a wall). It does not replace watching Jev actually play. Always
confirm Jev can reach the goal by stepping or running it.
Driving Jev yourself
toolchain/jev.mjs exports a small client. Example (from the workspace):
node --input-type=module -e '
import { evaluate, jev } from "$JEV_DSH/toolchain/jev.mjs";
import { readFileSync } from "node:fs";
const world = JSON.parse(readFileSync("arena.json"));
const res = await evaluate({
state: JSON.stringify(world),
questions: {
hard: jev.noul("Is this arena hard for a reactive agent?"),
vibe: jev.score({0:"empty",1:"ok",2:"brilliant"}, "How good is this arena to watch?"),
},
});
console.log(JSON.stringify(res.answers, null, 2));
'Without TYPESAFE_API_KEY this uses the deterministic mock; set the key to hit live Jev.
© autonomous-ai, MIT. 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 store/agents/jev-arena/skills/arena of autonomous-ai/openharness.
Open the folder on GitHubat commit cc4983e
Compare with similar skills
Jev 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Jev Arena this skillautonomous-ai/openharness | 1.2k | — | ~511 | Automated safety check: Pass | MIT | |
| Developing PDF ViewerTriliumNext/Trilium | 38k | — | ~1.8k | Automated safety check: Pass | AGPL-3.0 | |
| Jev Socialsickn33/agentic-awesome-skills | 47k | 1 repos | ~3.4k | Automated safety check: Pass | MIT | |
| Jev Usesickn33/agentic-awesome-skills | 47k | 1 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Arena Parallel Candidatescursor/plugins | 11k | 8 repos | ~1.2k | Automated safety check: Pass | None | |
| Jev Memorysuperdesigndev/treg | 4.9k | — | ~1.7k | Automated safety check: Pass | Custom licence |
Similar skills
Jev Social
sickn33/agentic-awesome-skills
Run read-only, browser-grounded Instagram, TikTok, or LinkedIn research through Jev routing and socai CLI, returning source-linked evidence and reports.
Jev Use
sickn33/agentic-awesome-skills
Route enumerable judgment steps - did it work, which option, how risky, is this safe to run - to the Jev judgment model through the jevjudge and jevgate MCP tools, batched into one call per state.
- Official
Arena Parallel Candidates
cursor/plugins
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.
Jev Memory
superdesigndev/treg
A skill your agent uses when the user wants Claude Code to remember their preferences across sessions, asks for a memory mod or memory harness for Claude Code, mentions the Jev memory classifier or…
Design Arena
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.
More from autonomous-ai/openharness
All 100 skills in this repoG-code Slicer Tool
autonomous-ai/openharness
Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.
Home Assistant Automation Builder
autonomous-ai/openharness
Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.
Score Music Composer
autonomous-ai/openharness
Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.
OrcaSlicer 3MF and G-code Workflow
autonomous-ai/openharness
Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.
Sheets and Docs Report Builder
autonomous-ai/openharness
Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.
Bambu Labs
autonomous-ai/openharness
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
Questions about Jev Arena
What does Jev Arena do?
Design and verify Jev Arenas in OpenHarness's live viewer, where Jev plays the world you build. Jev Arena is an agent skill from autonomous-ai/openharness. Design and verify Jev Arenas in OpenHarness's live viewer, where Jev plays the world you build.
How do I install Jev Arena in Claude Code?
Run `npx skills add autonomous-ai/openharness --skill jev-arena -a claude-code`. Or copy the skill folder (store/agents/jev-arena/skills/arena in autonomous-ai/openharness) into .claude/skills/jev-arena in your project. Claude Code loads it when a task matches its description.
How do I install Jev Arena in Codex?
Run `npx skills add autonomous-ai/openharness --skill jev-arena -a codex`. Or copy the skill folder (store/agents/jev-arena/skills/arena in autonomous-ai/openharness) into .agents/skills/jev-arena in your project. Codex loads it when a task matches its description.
Can I use Jev 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 autonomous-ai/openharness --skill jev-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/jev-arena, .gemini/skills/jev-arena, .github/skills/jev-arena and .opencode/skills/jev-arena in your project.
What does Jev Arena need to run?
Going by SKILL.md and its folder, Jev Arena needs the command-line tools its instructions call (node) and credentials named TYPESAFE_API_KEY. Our summary lists: A credential in TYPESAFE_API_KEY.
Does Jev 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 Jev 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 Jev Arena use?
Jev Arena is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Jev Arena use?
About 511 tokens (SKILL.md is roughly 2k 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 Jev Arena?
Skills that share tags, products or a category with Jev Arena: Developing PDF Viewer (TriliumNext/Trilium, 38k stars), Jev Social (sickn33/agentic-awesome-skills, 47k stars), Jev Use (sickn33/agentic-awesome-skills, 47k stars) and Arena Parallel Candidates (cursor/plugins, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Jev Arena?
autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,210 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 10, 2026.
Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.