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

Bench Run

by xD3I in xD3I/PZ_Optimization

Launch a hands-off Project Zomboid measurement run (bench, drive, parity, verify) with harness/run.sh, respecting the shared-machine and run-etiquette rules.

No licenceAuto-check passedTesting & QA

Install Bench Run

skills CLI
$ npx skills add xD3I/PZ_Optimization --skill bench-run -a claude-code

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

GitHub CLI
$ gh skill install xD3I/PZ_Optimization bench-run --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/xD3I/PZ_Optimization.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/bench-run .claude/skills/bench-run && 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
bench-run
GitHub stars
114
Token cost
~1.9k tokens
SKILL.md length
658 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
None found

At a glance

Launch a hands-off Project Zomboid measurement run (bench, drive, parity, verify) with harness/run.sh, respecting the shared-machine and run-etiquette rules.

  • Works in 5 steps: Use the queue (preferred, 2026-09-21;… → Preflight (every time, when not using… → Announce → …
  • Any request to benchmark
  • SKILL.md covers 0. Use the queue (preferred,…, 1. Preflight (every time, when…, 2. Announce and 3. Launch, plus 2 more sections
  • Calls python3

What it does

Bench Run is an agent skill from xD3I/PZ_Optimization. Launch a hands-off Project Zomboid measurement run (bench, drive, parity, verify) with harness/run.sh, respecting the shared-machine and run-etiquette rules. Use for any request to benchmark, measure, A/B, smoke-test or reproduce a frame-time or chunk-latency number.

Its SKILL.md is about 1.9k 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 Testing & QA, covering QA and bug reports. The repository describes itself as: Project Zomboid Build 42 performance work: class overrides, harness, findings.

When your agent uses it

  • Any request to benchmark
  • Reproduce a frame-time
  • Chunk-latency number

Example prompts

  • “/bench-run”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Use the queue (preferred, 2026-09-21; the run-queue skill has the full workflow)
  2. Preflight (every time, when not using the queue)
  3. Announce
  4. Launch
  5. Validate before trusting

What it can do on your machine

Read from SKILL.md and the folder at commit 84b483c. 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:

    • python3

    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

Bench Run loads about 1.9k tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 658 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 658 words (~1,868 tokens).

“A session always runs on the machine it first submitted to (--rebind to move); laptop jobs are rsync'd out, run there through the machine's conf entry (harness/queue/machines.conf) and collected back as harness/runs/--*. A disconnected laptop's jobs wait and the session…”

— opening of SKILL.md by xD3I
name
bench-run

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/bench-run of xD3I/PZ_Optimization.

Open the folder on GitHubat commit 84b483c

Compare with similar skills

Bench Run 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.

Bench Run compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bench Run this skillxD3I/PZ_Optimization114—~1.9kAutomated safety check: PassNone
Reproduce Chat Statesdifferent-ai/openwork24k—~673Automated safety check: PassCustom licence
Dynamo Jira TicketDynamoDS/Dynamo2k—~1.1kAutomated safety check: PassApache-2.0
Minimal Run And Auditlllllllama/RigorPilot-Skills4972 repos~691Automated safety check: PassMIT
Moav E2EMotherofallVPNs/MoaV448—~1.9kAutomated safety check: NotesMIT
Anchor Reprolynxlangya/techne1051 repos~1.2kAutomated safety check: PassMIT

Similar skills

  • Reproduce Chat States

    different-ai/openwork

    Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.

    24k GitHub stars~673 tokensUpdated today
    Testing & QAAuto-check passed

  • Dynamo Jira Ticket

    DynamoDS/Dynamo

    Create structured Jira tickets for Dynamo from bug reports, failing tests, or feature requests.

    2k GitHub stars~1.1k tokensUpdated today
    Testing & QAAuto-check passed

  • Minimal Run And Audit

    lllllllama/RigorPilot-Skills

    Rigor Run skill for README-first deep learning repo reproduction.

    497 GitHub starsUsed in 2 repos~691 tokens
    Testing & QAAuto-check passed

  • Moav E2E

    MotherofallVPNs/MoaV

    Run and debug MoaV's end-to-end tests — real protocol connectivity (client-test.sh) and the moav CLI smoke test — against a LIVE server, via the self-hosted e2e workflow or a local test VPS.

    448 GitHub stars~1.9k tokensUpdated yesterday
    Testing & QAAuto-check: notes

  • Anchor Repro

    lynxlangya/techne

    Reproduce a behavioral bug before fixing it, record the failing probe, and verify the fix with the same probe.

    105 GitHub starsUsed in 1 repo~1.2k tokens
    Testing & QAAuto-check passed

  • Creating A Coral Task

    Human-Agent-Society/CORAL

    Author a new CORAL task — the three pieces that must line up (task.yaml, seed/, a packaged grader/), the coral init → coral validate → smoke-test loop, and how to pick a grader pattern (stdout…

    1k GitHub stars~2.2k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

More from xD3I/PZ_Optimization

All 11 skills in this repo

  • Release Windows

    xD3I/PZ_Optimization

    Build the release zip of the class overrides (same zip for Windows and Linux) and publish it with the install.sh / install.ps1 installers as GitHub release assets.

    114 GitHub stars~3.1k tokensUpdated today
    Auto-check passed

  • Run Queue

    xD3I/PZ_Optimization

    Schedule any game run (bench, drive, preset, verify, multiplayer, Workshop upload, showcase recording) or media encode / stitch through harness/queue.sh on the desktop or one of the laptops (flip…

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

  • Workshop Comparison

    xD3I/PZ_Optimization

    Make the Workshop page's stock-vs-enhanced comparison animations (the 630x630 AVIFs of the Features section, the headline's template) from laptop or desktop runs - capture and numbers runs, the…

    114 GitHub stars~3.7k tokensUpdated today
    Auto-check passed

  • Analyze Run

    xD3I/PZ_Optimization

    Read and compare finished harness runs - frame-time tails, utilization, chunk latency, JFR waits, load phases - and look them up in Grafana.

    114 GitHub stars~536 tokensUpdated today
    Auto-check passed

  • Showcase Drive

    xD3I/PZ_Optimization

    Record the stock-vs-optimized driving showcase videos (60 and 120 km/h) with the big MangoHud overlay and stitch them into the quad-view video.

    114 GitHub stars~503 tokensUpdated today
    Auto-check passed

  • Game Update

    xD3I/PZ_Optimization

    Re-sync the repo after a Project Zomboid update (jar mtime changed) - re-decompile, regenerate and re-apply overrides, rebuild, and re-baseline.

    114 GitHub stars~336 tokensUpdated today
    Auto-check passed

Categories

Questions about Bench Run

What does Bench Run do?

Launch a hands-off Project Zomboid measurement run (bench, drive, parity, verify) with harness/run.sh, respecting the shared-machine and run-etiquette rules. Bench Run is an agent skill from xD3I/PZ_Optimization.sh, respecting the shared-machine and run-etiquette rules.

When should I use Bench Run?

Bench Run fits situations like: any request to benchmark; reproduce a frame-time; chunk-latency number.

How do I install Bench Run in Claude Code?

Run `npx skills add xD3I/PZ_Optimization --skill bench-run -a claude-code`. Or copy the skill folder (.claude/skills/bench-run in xD3I/PZ_Optimization) into .claude/skills/bench-run in your project. Claude Code loads it when a task matches its description.

How do I install Bench Run in Codex?

Run `npx skills add xD3I/PZ_Optimization --skill bench-run -a codex`. Or copy the skill folder (.claude/skills/bench-run in xD3I/PZ_Optimization) into .agents/skills/bench-run in your project. Codex loads it when a task matches its description.

Can I use Bench Run 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 xD3I/PZ_Optimization --skill bench-run -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bench-run, .gemini/skills/bench-run, .github/skills/bench-run and .opencode/skills/bench-run in your project.

What does Bench Run need to run?

Going by SKILL.md and its folder, Bench Run needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Bench Run 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 Bench Run 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 Bench Run use?

No licence was found for Bench Run or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Bench Run use?

About 1.9k tokens (SKILL.md is roughly 7.5k 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 Bench Run?

Skills that share tags, products or a category with Bench Run: Reproduce Chat States (different-ai/openwork, 24k stars), Dynamo Jira Ticket (DynamoDS/Dynamo, 2k stars), Minimal Run And Audit (lllllllama/RigorPilot-Skills, 497 stars) and Moav E2E (MotherofallVPNs/MoaV, 448 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bench Run?

xD3I (a GitHub user) maintains it in xD3I/PZ_Optimization, which has 114 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 8, 2026.

Source: xD3I/PZ_Optimization on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.